Podcasts about VMS

Change can happen in an instant and 2026 has already reminded us how quickly the financial landscape can shift and create volatility. Yet through it all, the bull market has remained remarkably resilient. So, the question remains: can the momentum continue? Join the Market Sense team for a timely midyear conversation with Fidelity leaders about what's driving the current environment, and how the economic backdrop may shape the rest of the year. Bookmark the Fidelity Viewpoints 2026 Midyear Investing Outlook page for the latest on market headlines, risks, opportunities, and ways to potentially safeguard your retirement. Read the full transcript View the slides Watch the video replay

Slide Into Our “unhinged” VMs.

Hey friends! Backups are not as cool as pentesting, but boy do they matter when things go sideways. This week I'm sharing how a Proxmox backup disk space meltdown led me to a completely overhauled — and honestly pretty bulletproof — backup setup for both home and work. Claude played a big role in helping me sort it all out. Here's what we get into: The backup history tour — I've been through CrashPlan, Dropbox, Backblaze (which saved my bacon after my house fire in 2019!), and a mystery one that may or may not have had "Panda" in the name. These days I'm settled on ARQ for personal backups — dead simple, backs up to just about everything (Dropbox, OneDrive, Google Drive, even their own ARQ Cloud for ~$80/year), and all data is encrypted at rest. Not a sponsor, but they should be. The 3-2-1 rule — I actually asked Siri mid-episode, and she initially thought it was a grounding/anxiety technique. (Valid, I guess?) The real answer: three copies, two different media, one offline. I've got a local copy plus OneDrive, Google Drive, and Dropbox — so I think I'm covered. The work side: Proxmox + PBS — My "data center" is a beefy Hetzner Proxmox box with about a dozen VMs. I had Proxmox Backup Server (PBS) set up on a secondary Hetzner box, happily cranking away… until it ran out of disk space and started yelling at me every night. Claude to the rescue — I spun up a Claude project, fed it terminal output and retention configs, and it gave me a straight-up honest assessment: either gut your retention policy (risky) or get more disk. It then walked me through Hetzner's auctions page — which I didn't even know existed — to find a storage-heavy, low-horsepower box. Ended up with two mirrored 8TB drives plus a 14TB drive for around $40/month. Not cheap, but totally worth it as a business expense. The new setup — PBS is now on its own dedicated Hetzner box. VMs from both my data center and my home NUC Proxmox box back up there nightly. Claude also suggested using that 14TB drive as an SFTP target for ARQ, giving me yet another redundant copy of all my personal data. It'll take a few weeks to fully sync, but I'm running some flavor of the 4-3-2-1 rule now (I made that up). Proxmox forever — Someone wrote in asking if I'd go back to ESXi now that Broadcom brought back the free version. Hard no. I've fallen in love with Proxmox and I'm not going back. 7MinSec wiki scripts repo — Head over to 7MinSec.wiki and click the Scripts button to find a new GitHub repo where I'm publishing pentesting scripts. First one up: a push-button Exegol installer. More to come — and I'll probably tease new scripts first over at 7MinSec.club on TuesdayTOOLSday! Have a backup horror story — or a setup you're proud of? Hit us up! And if you need assessments, pentesting, training, or other security goodness, find us at 7MinSec.com.

The podcast Gods have blessed us this week with VMs from The Pitt's key hairstylist, first name/last name (FNLN) Lynnae Duley as well as a check in from your best-friend's-best-friend, FNLN Daphne Arnold. Also, we highly recommend Tide evo AKA "laundry detergent tiles."ENOJY!!!!!Instagram and TikTok - momstomppodcastEmail - thismomstomps@gmail.comVM hotline - 213-640-7494Substack -  Mom Stomp Weekly

Matt Filgate, President and CEO of GreenLight Metals Inc. (TSXV: GRL) (OTCQB: GRLMF), joins us for a comprehensive introduction to this Wisconsin-focused exploration company advancing copper and gold projects across the Penokean Volcanic Belt-one of North America's most prospective VMS districts-and the Kalium Canyon epithermal gold project in Nevada's Walker Lane, which is subject to a binding term sheet for a proposed staged earn-in and joint venture with Barrick.   In Wisconsin, GreenLight's portfolio includes the flagship Bend copper-gold VMS Project in Taylor County, Wisconsin; along with the Lobo and Lobo East massive sulfide targets, and Reef high-grade gold project. Matt shares that their management team and board has deep roots in the state, and GreenLight is building a modern minerals company for Wisconsin, committed to responsible exploration, transparent engagement, and creating durable local opportunities as it helps supply the critical metals that power the energy transition.     The focus at the flagship Bend project is following up on last year's 2,000 meters of drilling, and utilizing data from the 18,000 meters of historic drilling by other operators, to guide a larger 17,000 meter follow up program. The ongoing Phase 2 Drill Program at Bend is for the initial 7,000 meters of that larger program, further delineating the VMS-style mineralization down-dip and along strike to the east of the main deposit area. The Company will also drill 2,000 meters into the Lobo and Lobo East target area later this drill season.   Next we shifted over to the Nevada asset, where on May 7, 2026, GreenLight Metals announced that it has signed a binding term sheet with a wholly owned subsidiary of Barrick Mining Corporation, for a proposed staged earn-in and joint venture at the Kalium Canyon gold project in Esmeralda County, Nevada.  Matt outlined the terms and different thresholds of this proposed earn-in process for Barrick, which if executed on, would give GreenLight a 20% fully-carried interest all the way through a Pre-Feasibility Study.  Additionally, this transaction brings in periodic stage-gate payments into the company treasury, while allowing Barrick's exploration team to focus on delineating the mineralization.   Matt highlights the strong company treasury at present, the background and experience of the management team, and the potential rerating of the company valuation should their exploration program at Bend have success in growing the mineralized footprint to a level where a resource estimate can be released next year, putting it on par with other important US-based VMS copper-gold systems.   If you have any questions for Matt regarding GreenLight Metals, then please email those in to us at Fleck@kereport.com or Shad@kereport.com.   Click here to follow the latest news from GreenLight Metals     For more market commentary & interview summaries, subscribe to our Substacks:   The KE Report: https://kereport.substack.com/ Shad's resource market commentary: https://excelsiorprosperity.substack.com/     Investment disclaimer: This content is for informational and educational purposes only and does not constitute investment advice, an offer, or a solicitation to buy or sell any security. Investing in equities and commodities involves risk, including the possible loss of principal. Do your own research and consult a licensed financial advisor before making any investment decisions. Guests and hosts may own shares in companies mentioned.

I'm excited to work with Microsoft once again as the presenting sponsors of the AI Engineer World's Fair! We'll streaming live from MS Build today for a special crossover pod with our friends at No Priors and the one and only Satya Nadella. However we did not hold back with this interview - we asked all the burning questions about uptime and Copilot that we know you have in your minds. Lets go!For almost two decades, GitHub has been the home of software, where both open source and closed flow, through commits, pull requests, reviews, actions, etc.This ecosystem flourished as open-source maintainers and contributors would continue shipping code for the benefit of the community. However as coding agents began to ship mass quantities of code - growing 1400% in 2026, it marked a new era that was both extremely exciting and challenging for GitHub.While these agents help more people ship more projects, they also significantly increase the floor of how much code is shipped, how often it is shipped, how many people commit code, and basically orders of magnitude multiples in every dimension of GitHub infrastructure:Now GitHub inevitably experiences more pressure on their infrastructure which was originally designed around human developers moving at human speed. This has resulted in a very publicly notable uptime story:So it begs the question of whether current systems around code can absorb what AI produces. Can CI/CD keep up when every idea becomes a build? Can open source maintainers survive floods of AI-generated slop contributions? Can GitHub preserve the human social contract of software while becoming the operating layer for agents?Which brings us to the perfect person to answer these questions: GitHub COO Kyle Daigle. In this episode, he joins swyx to unpack what happens when AI doesn't just autocomplete code, but starts changing how companies operate, how open source works, how pull requests get reviewed, and how GitHub itself has to scale. We go deep on GitHub's internal AI workflows: micro-skills, WorkIQ, MCP, Slack, Teams, email, Copilot workflows, the new Copilot desktop app, CLI, cloud agents, and how Kyle uses agents to look backwards across company context before deciding what to do next. Kyle also reflects on GitHub's history building webhooks, APIs, Actions, npm, Dependabot, and Semmle, why the AI era is breaking GitHub in new ways, how Actions became a general-purpose compute layer, and what Copilot becomes after code completion.Full Video PodWe discuss:* Kyle's expanded role across GitHub* How AI got Kyle coding again after years in leadership* Why GitHub rolls out AI through existing workflows instead of forcing new tools* WorkIQ, MCP, Slack, Teams, email, and GitHub as company context* Why massive “mega-skills” are giving way to small, atomic micro-skills* How AI changes summarization, communications, marketing, and analyst work* Why former developers in leadership may have a unique advantage in the AI era* Kyle's “15 agents on Saturday” workflow* How Kyle built an AI-generated executive presentation for CRO/CFO teams* Why AI changes the chief of staff role without removing the human work* GitHub Actions, webhooks, arbitrary code execution, and secure agent compute* The npm acquisition, supply-chain security, 2FA, and token invalidation* Slop forks, vendoring, and whether AI agents change dependency management* What pull requests become when most PRs come from agents* Prompt requests, vouching, AI review, and trust in open source* What counts as a “developer” when AI lowers the barrier to building* GitHub Spark, low-code, and why GitHub refuses to hide the code* 14x commit growth, Actions load, databases, monorepos, and availability* Copilot's evolution from completion to CLI, desktop app, cloud agents, and SDK* Context, memory, rules, and making GitHub “act like Kyle wants it to act”* Ambient AI, OpenClaw, enterprise security, and the new operating system for agents* What swyx should ask Satya Nadella about Microsoft's AI futureKyle Daigle* LinkedIn: https://www.linkedin.com/in/kyledaigle* X: https://x.com/kdaigleTimestamps00:00:00 Introduction00:03:36 Why AI Got Kyle Coding Again00:07:04 Running GitHub with AI: WorkIQ, MCP, Slack, Teams, and Skills00:15:39 The Golden Age for Former Developers in Leadership00:17:31 15 Agents on Saturday and AI-Generated Executive Work00:20:20 How AI Changes the Chief of Staff Role00:21:45 GitHub's History: Actions, npm, Webhooks, and Open Source00:28:45 Slop Forks, Vendoring, and AI Dependency Management00:33:57 Pull Requests, Prompt Requests, and Trust in Agent-Generated Code00:41:21 GitHub Stars, 200M+ Developers, and the New AI Builder Wave00:45:15 GitHub Spark, Low-Code, and Why GitHub Still Shows the Code00:47:38 GitHub's Hardest Era: 14x Growth, Reliability, and Scale00:59:21 Actions as the Compute Layer for CI/CD and Automation01:02:04 The State and Future of GitHub Copilot01:08:24 Ambient AI, Background Agents, and the Future of the SDLC01:13:09 OpenClaw, Enterprise Security, and the New OS for Agents01:18:03 Build Announcements, WorkIQ, FoundryIQ, and Microsoft Context01:21:41 What Should swyx Ask Satya?TranscriptIntroduction: Kyle Daigle's Expanded Role at GitHub and MicrosoftSwyx [00:00:00]: We're here with Kyle Daigle, COO of GitHub. Welcome.Kyle [00:00:07]: Hey, thanks for having me.Swyx [00:00:08]: You're not just CEO of GitHub. People know you as that. You have a new role.Kyle [00:00:11]: So I have an expanded role now. I've been working at GitHub for thirteen years and doing all things developer. Joined as a developer myself. And now, I'm also responsible as the CMO of Developer for Microsoft. And so all the kind of learnings and passion for developers and how we work with them and how we communicate and how we bring our products to market, we're also bringing that expertise to the broader Microsoft ecosystem and helping every developer that uses a Microsoft product or would like to have a sort of similar experience that they've had with GitHub over the years. So it's a different role in some ways, but it's also just building on the experience that I've had at GitHub of just sort of tell the truth, be authentic, show people how to use it and then let the products speak for themselves. Now just doing that with, all of Microsoft.Swyx [00:01:09]: We'll be releasing this in conjunction with Build. You got lots of stuff planned, and we can sort of touch on that whenever it's appropriate. I think one of the interesting things is I rarely meet a COO who's also a CMO. I think you're a very outward facing and you're very confident publicly. That's rare. Do you actually view yourself as COO? What's What is your thing?From GitHub Developer to COO/CMO: Building the Platform and Operating GitHubKyle [00:01:33]: I think for me, it's been funny. The titles have always been, a— have always felt a little strange to me. I joined GitHub as a developer? I wrote so much of theSwyx [00:01:46]: Let's bring that up. You wrote the back ends?Kyle [00:01:48]: I was going through, I was going through, some old photos, when folks were talking about how things were being built or how there was a build GitHub. I built, webhooks and worked with teams building the API, built the platform layer. Anything that integrated with GitHub, up until really twenty eighteen, I built or ran the engineering teams. And that's kind of where my the beginning of my passion always was helping people build things, deliver them to, their customers. And so being a developer, building for developers was always super unique. In a— I think as my role expanded, it became my ability to talk to not just developers, but also enterprise customers or business leaders and have this translation layer. And then through all those years, GitHub has always operated pretty uniquely. Post-pandemic, working remotely was not as novel as it was when GitHub started in two thousand and eight. But all that expertise of running remote teams, doing it well, became this sort of bigger role, ultimately turning into the COO role of how do we operate GitHub in the way that GitHub's always operated after the Microsoft acquisition. And kind of so on from there. So like for me, I think the— I've, I still code. I love coding but the problem has always been, people. It's a much harder problem to both support our own employees, a harder problem to communicate to developers and enterprise buyers what we're building why it matters, ‘cause those are two very different messages. And so getting to work in the mix of COO, CMO, also just being a dev, I think is what's kept me at GitHub for so long.AI Workflows for Leadership: Commits, Retrospectives, and ContextSwyx [00:03:40]: Apparently, you have— your commits have gone up. What's this? What's going on?Kyle [00:03:45]: Rui's called me out pretty aggressively. So I think— as you can imagine, right, you can see my normal era of being a dev In the twenty thirteen, twenty fourteen era, and then moving into management, and then ultimately the COO role. I think what you see there is me, really getting back to coding thanks to AI. I— similar to, attaching problems between how to market and how to operate a business and how to code, I find, building agents and workflows that are connecting very disparate problems to be what's driving this. So that's, some of it's writing software. A lot of it is, connecting a ton of a different data sources to, help me out. But that is completely me really diving in on the AI side in trying out our tools, trying out everyone's tools, But building for me, building for the non-technical leader, though I'm technical and how we're, able to use these tools more than just the simple, call and response that I think a lot of the non-technical, your employers, you have to get— you have to use AI, and so everyone uses, ChatGPT or Copilot or Claude or whatever. To really get into, how is this going to help me out, it— I find that it's not the I need to write a blog post, I need to those simple examples. Helping people find the workflows of, “Okay, I need you to go through all the PRs today. I need you to go through everything that we've posted online. I need you to go through what we did the last three months. Go through all of my Obsidian notes for any mentions of this then go through my transcripts at work.” We use, Teams, so, using WorkIQ, go call that MCP server, grab all the transcripts, go through all the Slack, and then build me out the plan of, what this week's messaging actually was. That's something that was, impossible because for me, I find AI in a what most of this launch here is actually, less building forward. It's actually, a recursive loop backwards. I'm always looking at what had happened first. Go back through the week and tell me what we did, what worked, what didn't work? And then tell me in the next three or four days-What would you tweak based on this sort of like looking backwards and then looking ahead a little bit? I find that to be so much more valuable, especially for like non-technical, because that retrospection is actually LLMs are very good at that. Like finding all the patterns, pulling them out, and then applying that retrospection to just a couple of days or just like a short period of time. Is all a bunch of apps that I've built and launched a bunch of, internal tools. I use the new, GitHub Copilot app, the desktop app with workflows. Every time I crack open my laptop, it's running workflows for me. It's just a ton of different stuff and of course, it all ends up on, it all ends up on GitHub.Swyx [00:06:47]: Of course. That's where, that's where, stuff is hosted. Man, there's so much to ask you. I was going to leave the how do you run a company with AI thing at the end. I have to ask one— double click one thing. You said, you are looking back at the week. You're, you're understanding what happens. When you say we That's three thousand people. How?Rolling Out AI Internally: Skills, CLIs, and Company ContextKyle [00:07:09]: I think when we started rolling out AI internally beyond engineering, right? One of the things that I was really, passionate about is like we have to do this in a way where no one has to change how they work. I don't want to have to teach you a tool. I don't want to have to teach you something new. And so for us, we tried out a few tools. Most of them don't work because I got to get you on board? I got to teach you how to use it. What we've actually ended up doing is we've built like a set of skills internally. We have we each have our set of skills, and we've just been distributing even to the non-technical folks, the CLI. And then effectively, we're just giving it access to like read about everything that we're writing. So that's for us, that's usually GitHub, Teams, Email, and Slack. So Teams for, video chat, generally speaking.Swyx [00:08:03]: Teams and Slack?Kyle [00:08:04]: so we use Teams for video communication, but we don't use it for chat. W-we— GitHub for a long history, right? We're alwaysSwyx [00:08:13]: Also SlackKyle [00:08:14]: Talking about ChatOps and like everything is built into Slack. Like every command, every flow.Swyx [00:08:18]: So even though you have been acquired for I don't know, eight years nowKyle [00:08:22]: we stillSwyx [00:08:23]: You still use Slack?Kyle [00:08:23]: it's a purpose-built tool for us, and I think the reality is that moving off of it would be so bluntly expensive? Simply because all the tooling is, baked in with that paradigm. And they both have their pros and cons but they don't work the same way at all. We still use a bunch of different tools Because it's the purpose-built tools that We need. And thenSwyx [00:08:47]: Well, the same doesn't go for the rest of Microsoft, presumably.Kyle [00:08:50]: like the like various teams like operateSwyx [00:08:53]: They make their own decisionsKyle [00:08:54]: Various ways. I think it just matters what you're trying to what you're trying to do. But we do we do work across kind of every tool that we use, and then by giving everyone access to all of that context and the new WorkIQ MCP server, which is quite cool if you do live in the M365 like world. I can ask it all these backwards-facing questions, and it's incredibly important for our teams that are working remotely. There's a lot of stuff you miss when you're not in an office, and we are spread out all over the world. So most of that is looking back. And then we post, we post either auto-automatically into GitHub issues or discussions, these sorts of like findings or like our industry reports. Like what's happening this morning, today, yesterday. A little automation gets run. We'll use the app. We might use GitHub Actions like with, our agentic workflows just to go do that run, and then we push it into GitHub, and w-we keep having a conversation. So usually for us, it's about that sort of like looking back, looking forward on the non-technical side. And then of course for a lot of those folks, it's also building an app, pushing it to GitHub pages or pushing it somewhere to host it et cetera. But it's just like enabling everyone with that power of it's going to take me a week to figure this out. Instead, we're going “Okay I built a skill. Let's put it into a repo. We'll all share that skill together, and then we'll use the CLI or now the app-” “just to run it.”Micro Skills vs. Mega Skills: How GitHub Uses AI at WorkSwyx [00:10:26]: All right. I think, I think we're going straight into like the team management and productivity thing. I think a lot of people are getting various levels of LLM psychosis. How do you manage the bloat of skills? Like everyone Has their thing, and they're Like trying to promote it to the rest of their peers in their org, right? And obviously, whoever becomes a skill influencer internally becomes like an AI leader, right? Of sorts. I assume you have those.Kyle [00:10:50]: like I think we haveSwyx [00:10:52]: And I assume it's a mess a Yeah.Kyle [00:10:54]: there's like I— like I think the reality is there's two pieces. Like first is I think that we're ending the era of these like massive, beautiful, perfect skills that are just like not any of those things. ‘cause for a while, right every tweet every day is like go download the skills, the perfectly managed thing to do this entire workflow. And I think that like what we've found and what— I was just with my team, this week, and we were talking about the skill side, and we're really talking about these like incredibly micro skills that are just doing one thing for us very well Versus a skill that's going to do I said, that full report. That doesn't really exist on our side anymore. It's usually how do— like a single skill that's going to identify the most important marketing information given any MCP server. Like this is the most important thing. Less about stitch a bunch of tools together and have it produce this mega output because then weeks go by, months go by, things change, and you want to tweakSwyx [00:11:58]: It's brittleKyle [00:11:58]: Your mega skill and you're screwed? You can't do that. And so now we're really just talking about the Legos we're using and just letting the instruction book be something we're all putting together. Whereas I think a lot of AI skills for a while have been that mega instruction book style.Swyx [00:12:15]: I've, thought a lot about Postel's law. I don't know if that's a term that is, means things to folks. It's the idea that you should be liberal in what you accept and strict in what you output, right? And I think that's like a good framing principle for skills. This is my skills, obviously on GitHub. I feel like everyone should have like how like some repos In GitHub are special repos? I feel like we should sort of reify the slash skills and everyone like give it some kind of special presentation. Anyway, so, yeah, this is one of those like download Download anything, transcribe anything, and then you can string together the atomic skills that do one thing well Into like some kind of orchestration skill that calls other skills. I assume, does that match?Kyle [00:12:56]: I like I think so. I think that theSwyx [00:13:00]: Summarize anything.Kyle [00:13:01]: Like I think the- For me, summarizing something for I do communications and PR and analyst relations and marketing and customer activities, and so my summarize everything is very different for each one of those like Contexts. What ‘Cause if I'm summarizing something for an analyst, that's a very different thing than, probably how I'm going to summarize something for like a customer meeting or an engagement. So that's I think like the difference when we're talking about the like the tools I might use on Saturday or the skills I might use on a Saturday when it's just for Kyle. Yeah, those are kind of like they have an atomic actual tool underneath or maybe skill, and then Kyle cares about X. But I think when we're talking about work and enabling the the marketers, communicators there, it's the atomic, this is what good summarization is, and then this is what I care about as for marketing for communications For whatever. And that I think is like the interesting matrix problem when we go from like a developer set of concerns to all kinds of different professions, is that what that word means to me is different than it means to you is different than it means to the analyst or the salesperson, and that's where I think the matrix mess is that we're starting to like still starting to find. It's about these mega skills but they're all just slight permutations, but those permutations are really important. It's the difference between someone reading this and going “Did AI make this?” what Or “This makes total sense, and I would expect this when I'm giving a briefing to Gartner,” or like whatever else.Swyx [00:14:37]: I think the beauty of it maybe is that you don't have to be that careful about what goes in there. It doesn't have to exactly fit as long as it like roughly is contained in there. I used to complain about plugin hell, basically. Like when you have a framework and then you have a hundred things that you need to integrate, everyone does like the GitHub used to be bloated full of these things. And now we don't need them anymore ‘cause now you just use skills.Former Developers in Leadership: AI as a Creation MultiplierKyle [00:15:00]: And like I think the most magical thing is the just that like I can just also crack it open. Like Like yes, I could go like change the how the plugin is coded, or like I could go do that now with AI, but I think there's just something more magical about getting a response back and being “That's not right,” and then you just crack the skill open, you just type English words and it's different. That building block is just, I think very unique. Once I get everyone to kind of understand how to best how to best make those changes to get the most power out of them.Swyx [00:15:36]: Is there a— you have a your peer group that Of people like you. Is there a common framing for Something I'm feeling is, which is true, is that is this a golden age for former developers who are now in leadership? Because you can wield the tools, you would know the right words, you're maybe not too close to the details. Doesn't matter. But like you're more effective than someone who doesn't come from that background.Kyle [00:15:59]: I think that like the secret has always been your ability to identify patterns and solve problems, and I think that for folks that like myself that don't code day to day anymore, that has made me successful as a developer, made me successful as a COO and now CMO. And so now that I have access to get and write code, I'm now applying that sort of like pattern finding and problem solving, and I know enough still about how to then go and say, “Oh, I want to make an app, but I don't want to break into jail or create something that's not going to be able to work or to be deployed scale or whatever.” that ability to apply all that additional business knowledge and still code I think is what makes that so interesting to me. Slightly different than I think some of the other like technical leaders that became business leaders and now are going back to their apps and updating them. Good for them? But I think the more, much more interesting thing is, well, now I have this whole new set of expertise over ten plus years. Why not take that and use that as a developer with these AI tools? So I definitely think that makes me more powerful, but I think that's true for like every dev as well. Most of the dev friends I still have also have some other underlying skill and passion. There's really talented, very kind of linear computer science software devs, absolutely. I just find that the folks that came from a different career, went to school for something else, went off and did this random thing, and then became a software dev, or were a dev, did a random thing, came back. Learning that extra set of information, learning those extra skills, and now having the power of an AI where I can crank up fifteen agents on Saturday while my kids are doing lacrosse, That's like really powerful. And I think it gets me back to that feeling of like creation, and it's very hard to replicate that in most other senses? That first time you build an app and you click it and you show someone that's magical. And so being able to do that not just in code, but across all kinds of different assets that's, that's huge. We were doing we're doing our every year we do our revenue planning. We talk about okay, what is it going to look like for next year? And of course as you imagine, there's, slideshows everywhere talking about what are we going to talk about, what's the narrative, et cetera. And so as you said I'm “Okay, well, I could probably just like build something to build this and then that way I don't have to go build the whole spreadsheet or I have to pass it to my team.” So we went through this process, and I got all the information and used the skills I mentioned. I built like a little app just to make it so I could look at some of the information in a SQLite database, more easily. And I ultimately built this entire presentation without touching any of it and I was “Okay, I'm just going to present this to our CRO, the CFO, their teams,” without mentioning I'd built it with AI. I like built a skill to make it look very much not AI driven. Just not pretty.AI-Generated Presentations, Human Taste, and the Changing Chief of Staff RoleSwyx [00:19:03]: Like a design. Yeah.Kyle [00:19:03]: Not pretty. But just like very clearly not AI. Kind of like don't do anything interesting.Swyx [00:19:08]: That's, yeah, that is valuable.Kyle [00:19:08]: Just go Exactly. We did the whole thing through. It used my notes from Obsidian, it used all the context I mentioned before, the plans, and Never came up once that it was AI generated.Swyx [00:19:20]: It didn't matter.Kyle [00:19:20]: Never once. D It didn't matter. And so now I takeSwyx [00:19:23]: This is a toolKyle [00:19:23]: I can take that tool and go, “Look, I don't want you to go build slideshows.” They're just helping us share information with each other. If this thing can do it With a little bit of crafting from you and then we can look at it together, awesome. There's no value in all that extra work. I think that the ability to, make it look humanly bad and and build a little app to, manipulate the data I think is part of, that upside for devs that are now in leadership roles. Because, the thing that I feel like I said before, this that's all a people, that's all a people problem. I know if you've used a coworker or not to build a slide deck, unless you spent a bunch of time to not do it.Swyx [00:20:07]: I know, but like it was so, I think there's a certain charm to just being blatantly AI. ‘Cause I think that you're well, you're just honest about There may be mistakes here that I cannot vouch for. So how much value is there? But anyway I think, actually the real question I want to ask is, there's a— You were a chief of staff To Thomas. And in the pre-AI world, the that job would've been a chief of staff job of like Can you prep me these slides and all that? And now you do it yourself.Kyle [00:20:35]: I still, I still have a chief of staff. Because, the difference is it's sort of the discussion every time we have some sort of technology evolution is it's not that the jobs the roles don't all go away, they just change? And so yeah, I don't have someone spending all their time building out slides for me and presentations ‘cause I don't need that anymore. But now I need that person that is able to go and find all the different connections between humans in those discussions to help me find out, okay, I should be meeting with this group and this team, and they have an opportunity, and I'm going to be in San Francisco today, I'm going to be in Seattle tomorrow. Those sorts of human connection aspects are still incredibly valuable and has always been a big part of that chief of staff role. But now just like chiefs of staff are not opening up, letters to process, they're doing emails. What It's the same thing. And now they're, they're not building out as many of these presentations because they have the the ability to have a AI take it on for, and share that with me and great. Let's keep moving ‘cause it's allowing us to go faster and make better decisions more quickly.Swyx [00:21:45]: Awesome. Well, so we can dive into more sort of, Productivity insights as you go. I did want to do a little bit of a brief history of colleague and hub. Because, we started here. And then you also involved the NPM acquisition. I did, I do want to touch upon that. And then more recently, I just want to bring up to present day where we're having uptime issues Which transparently we've already Addressed publicly, but we'll, we'll discuss in the pod. Did I miss anything? Like what, any other major highlights? Obviously, it's, it's a lot of years to cover.A Brief History of GitHub: Webhooks, Actions, Acquisitions, and Platform EvolutionKyle [00:22:15]: No the I think one of one highlight was right before the acquisition closed in twenty eighteen, I got to launch the first version of ActionsSwyx [00:22:27]: OhKyle [00:22:27]: At GitHub Universe. So it was OSwyx [00:22:29]: They're that young?Kyle [00:22:30]: It was October of twenty eighteen, I think. Yeah. Yeah.Swyx [00:22:33]: Gee, Jesus.Kyle [00:22:34]: I got to I was the engineering leader on that project and got to launch that. And then, yeah, we did acquisitions of NPM you said, Semmle, Dependabot Pul Panda a whole bunch of things. That was a bigSwyx [00:22:47]: Pul Panda.Kyle [00:22:48]: Abi is doing well.Swyx [00:22:51]: DX. Holy crap.Kyle [00:22:52]: Did well on DX. I and like that was a that was the big shift, after the acquisition. I had to join the sort of business side.Swyx [00:23:00]: So I need to hit you on some of these things ‘cause you were there. Right? And how often do I get to talk to someone who was there? But yeah, Actions. Is that the number one source of security issues on GitHub?Kyle [00:23:11]: Oh, sh I think that the number one source of, security issues is probably like all, the literal code in everyone's like underlying repositories. I would say back further than that is, if you remember I had to show in this graph was this is, I'm, didn't say this before, this is ultimately webhooks.Swyx [00:23:30]: You yeah.Kyle [00:23:31]: Like circa whatever it was.Swyx [00:23:32]: It says Hookshot in there.Kyle [00:23:32]: I forget. Yeah. Yeah, Hookshot's in there. And so like back then, it says GitHub Services. Do you see, it says Hookshot FE for front end, and then it says GitHub Services. GitHub Services back in the old days, right? You we had a repository that was Ruby code, and you could write any Ruby code in there, and then we would execute that On your behalf As a service, and then that way if an if you were trying to integrate with something, it didn't we would run it for you.Swyx [00:23:57]: And of course no containers ‘causeKyle [00:23:58]: No, ‘cause it wasSwyx [00:23:59]: Well, no containersKyle [00:24:00]: Twenty fourteen. And so there was some isolation obviously, but it was mostly the separations on the server level. That's like an example as long as the very old version of Pages, which ran on its own containerization infrastructure, not on Actions.Swyx [00:24:15]: Which like all-time great product.Kyle [00:24:16]: Pages powers the internet at this point to some degree. Those were places where like clearly there were no like issues like to my knowledge. But it was those things where I'm looking at and going “Okay, well we can't be running arbitrary Ruby code,” like on everyone's behalf. Then containerizing all of that up intoUh into actions now where yeah the containerization, is r-really good. The pinning most folks aren't pinning it the like to a particularSwyx [00:24:48]: ImagesKyle [00:24:48]: Sha, et cetera like their workflows, and so that's a big that's a big place Of pain for folks if they're just doing similar to any dependency management, just V1 or newest or latest, I think. But, that journey from that day to “Okay, we're just going to run all this arbitrary code, and, it'll basically be okay,” to now, no, we have, really good containerization. We have a new, underlying, ag-agent, containerization, service. It's like we're using it under the hood. It's through Azure. They recently announced it. The Azure, Dev Compute, but it's, very fast, very fast compute to be able to, spin up your own cloud agents, or whatnot. We're using it under the hood for some parts of the new,Swyx [00:25:36]: Microsoft Dev Box?Kyle [00:25:37]: No. Dev Compute, yeah.Swyx [00:25:41]: Hmm. Not finding it just yet.Kyle [00:25:44]: Oh, it's, it's in there somewhere.Swyx [00:25:46]: All right. Well, we'll cut that out.Kyle [00:25:47]: Sorry. But with, Dev Compute, you can, run, really fast, spin up really, small VMs really quickly, so you're doing a tool callSwyx [00:25:58]: Same conceptKyle [00:25:58]: Just do it containerize exact-exactly. So we're using that so definitely moving that direction to protect us from every every piece of code that we're ultimately running.Swyx [00:26:07]: look, that grows into the full SDLC? Code hosting was just the start and and then it's grown beyond that. Let's talk about NPM may-maybe ‘cause I think that's also, a very major point in the industry. I do think, it was looking for a home. It was, kind of struggling as a business, right? I don't know, I don't know how you would characterize that whole acquisition and how itNPM, Package Security, and Keeping the Internet RunningKyle [00:26:33]: like when we were talking to the team, I think the big thing for the both of us was to find a way to keep NPM, which was basically powering the internet then and way more so now to some degree running. Keep it going keep continuing to scale. It was having scaling problems, if I recall, back at that time. They were doing some rewrites. ItSwyx [00:27:00]: that's cute compared to now.Kyle [00:27:01]: Well, that's the thing is like when I'm talking to folks now, there's there's so many more underlying uses of NPM than there were back when we had them join in with GitHub. But that was ultimately the goal. It was really okay, we used to have pages. We have, the world's code. Let's make sure that we can keep NPM running well for the world. And we put a bunch of time and investment into fixing some of the underlying backend, changes, some of which we talked about some of the manifest work, et cetera. And then now, really trying to bring the the security posture of NPM up to speed. But, it is a unique challenge in that every move that we make to make it more secure will break a lot of people. And security is paramount. And also, we take it very seriously. We're, the any time that we have a problem with GitHub or we make a change that makes us more secure but hurts, there's, a snow day for developers or a really bad fire that they have to go put out. And so we've, have changed the 2FA policies. We've changed the way the tokens work. When we find tokens that have been exposed or potentially, exposed, we invalidate them, andSwyx [00:28:22]: I love that feature in GitHub. Yeah, it's greatKyle [00:28:23]: That creates issues, but, the but that's the thing is we're trying to push the community, forward without necessarily, doing something that is going to break the contract that's been for 15 years or close to it or some amount of years on NPM.Slop Forks, Vendoring, and the Future of Open Source Supply ChainsSwyx [00:28:43]: I think the— So now we're talking about, open source and publishing. And I think there's something here with what people are calling slop forks, which, I think Malta from Vercel is doing. And, part of me thinks, well, the way to get past any vulnerabilities, we just, let's just get rid of the concept of NPM. And we only publish source code. And anytime you want to import it you have your coding agent look at it and then adapt whatever subset you're going to use into your vendor it. But, the AI vendor it. Is that realistic? I don't know. Is it— Will that solve all our security issues? I don't know.Kyle [00:29:24]: I don't think it'll solve I so Mitchell was just talking Mitchell Hashimoto Was just talking about this today, and I think that I-in some ways, it's all all things, old or new again? Yeah, absolutely vendoring everything. Like I do I do remember twenty thirteen, twenty fourteen.Swyx [00:29:42]: This is Yeah. Let's, we must return toKyle [00:29:43]: That's what is We were vendoring everything. We were having actual discussions around, or at least I remember we were “Should we take this full thing?” “Why is this so big? We only need this one file.” And so I do think there's something true there where having either taking only what you need or the dependencies just getting incredibly small over time, I think will help to some degree, but it's not going to solve the fundamental problem, I don't think, because the vulnerabilities in an agent looking at them, there's time and time again, there's a million different ways in which we can convince an agent that this thing is, secure or not and pull it in. Or we can do static code analysis or runtime testing to say whether the code works or not. That is, I think, the step that needs to continue to be, invested in. The question is just on, how much scope. Should it be this enormous project that I'm pulling down, or should it be this piece? Either most companies are running some amount of security checking on the on the packages that they're bringing in or vendoring. That I think won't change. That's like what advanced security does to some degree, Socket does some degree. Like everyone is doing a piece of that. How we each do that like especially when we're talking to enterprise customers, is just like very different. No there's no one wants one single way to do it. And I think that's always been GitHub's, unique position in the world. I talk a lot to maintainers, I talk a lot to folks about this. It's we're— we rarely start like a process and a practice and like push it onto the community. We usually wait for the sort of like RFC process socially or literally, everyone agreeing, and then we'll cement something in. Because otherwise we'reMaintainers, RFCs, Vouching, and the Social Layer of TrustSwyx [00:31:35]: That fits your role in the ecosystem, yeahKyle [00:31:36]: We're GitHub. Yeah, we don't want to shape the whole thing. We want it to be figured out. But like how do you balance that like sort of Role in the industry to keep everything as secure as is possible and make sure that you're you're not going to be compromised as a human, ‘cause that's usually how it all happens. And Not not create a process or lock us into a flow that you're not going to or like Mitchell's not going to or other open source projects aren't going to like. That's always been a tricky balance for us, and I think that's something that we haven't talked about enough is we're not going to be able to fix everything for everyone in a way that everyone is going to like. So tell, help us, tell us what is working. When Mitchell was talking about, the Upvote, the upSwyx [00:32:22]: I was going to bring up his thing. Yeah.Kyle [00:32:23]: I forget what it Yeah. When he's talking to us, I was chatting with him and talking to him about this and I put it on Twitter and we talked to, also over DM, was “We're going to keep working.” but I think the important thing is I do actually want to hear what isn't working for you. And as, be as specific and clear for your project as is possible. And to every piece of credit over the many years that we've known each other through the industry, he's always done that and I appreciate that ‘cause there are places that we need to fix up, and we hear from him, and we'll fix up just like we do all other kinds of maintainers. But that that process between making those types of improvements and being more secure and like creating, I forget what he calls it's not the proof process, not the claims process. Do what I'm talking about? He has that he his projects have a way for you to kind of like,Swyx [00:33:13]: VouchKyle [00:33:13]: Vouch. Thank you. Yeah. He has like the vouch system for saying, “Hey, you should accept my PRs.” That's beenSwyx [00:33:20]: I just built this into GitHub. I don't know.Kyle [00:33:22]: Well, see, but that's the thing is that you say that and like he and his community really likes this and then I'll go talk to other maintainers and other maintainers, globally, and they're “No, this doesn't work for me.” And that is the tension, but also the kind of beauty of GitHub, depending on which way you look at it is we want to help maintainers, so we create all these tools to let you have more control over how much you take in from AI and PRs. But you can also use this. What You can go use this project, and if it takes off and becomes the kind of mostly standard, then yeah, we probably wouldn't enforce it but we would add it in because that's the flow that we tend to do?Swyx [00:34:02]: I hear a lot of people don't know the history of the pull request. And like like that's how, that's something that GitHub standardized basically.Kyle [00:34:08]: Yeah. It was a very messy process Like beforehand, and now the we have the benefit of it being the process? And now we have to go and Figure out the next best process or what adaptations change, or what does a pull request look like when eighty percent of your PRs are just coming from your agents and not From other devs?Swyx [00:34:31]: Do you like the prompt request idea from Peter?Kyle [00:34:34]: like I think that for each like each idea I think has its merits. I'm not, I'm not avoiding saying anything good or bad, but I feel like I've seen a version of we have that we have entire Thomas' store. Take all the assets of what you've built and put that in. I think that's got great ideas. There's all these various permutations of the PR flow, but I think the reason why there's not a single answer is ultimately we're trying to codify trust. We're trying to say “Okay, if Sean reviews this I'm going to trust it because you're Sean or you're the senior dev or you're the whatever.” And right now, when we are working in a flow where an agent writes code and another agent reviews code and then Kyle goes and looks at it the trust is kind of diffuse. And most of the tools that we're talking about are talking more about verification flows. We have more assets to look at, so I can probably say whether this is a good PR or not. But that still doesn't solve, I think, the human problem of I'm looking at a PR and I want to know if I can trust it. And we're still, we still tend to use human signals for that? Mitchell approving it or Kyle approving it or whatever. And so I think that's, I think that's why most of these options haven't really solved it is because, it's a social problem ultimately. It's a it's a human problem to review it and agree. Or you fully trust the tool and you're imbuing that tool with full trust Which I think in some cases that absolutely exists.AI-Generated PRs, Trust, and the Waymo AnalogySwyx [00:36:08]: And so like in the same way that there will be a tipping point in society when we don't allow humans to drive anymore Because machines are measurably better than Than humans. I'm looking for that tipping point, right? Like Mythos is ridiculously expensive. Someday we'll have Mythos on a desktop. I don't know. Will, does that change the equation?Kyle [00:36:30]: I think it's more I took a Waymo here, and I was on my phone and not looking around at all. There are other, self-driving, vehicles that I would not trust while, staring at the road. And I think that trust is something that isSwyx [00:36:48]: Is this a Zoox thing? What is itKyle [00:36:50]: I think that is both. I think that is both. LikeSwyx [00:36:53]: There's Zoox in this robo taxi. That's it. It'sKyle [00:36:56]: Well, depending on what level Of self-driving. But, my point is sort of that I think part of that is I strongly believe that's, a mixture of verifiable proof. Like how many accidents, how much data, and so on, and the human aspect of how I feel when I'm in this car, what it tells me, et cetera. And so that's why I think some of the like Some of these some of our AI tools tend to, imbue me with more of that feeling of trust, even if the data says this is 100% accurate. I feel like it takes more time for us to go, “Should I trust this or not?” And that's in the soft sense of, startups with high agency, weekend projects, and open source. And then there's enterprises and regulated industries and everything else, and that is an even harder problem to go solve because even when it is fully verified, not only do you have to have trust from the humans on the team, you probably have to have trust from multinational,Swyx [00:37:55]: Oh my GodKyle [00:37:55]: Multi governments around the world and regulating agencies. And so that's where I feel like until we tip over to your point on the sort of like human EQ side of it. I feel okay this feels okay I've been proven enough. Then the ball will start to roll a lot faster, where we'll end up getting to the “Okay, we can trust this,” and feel good about it in the Most difficult of cases.Reputation, Sponsors, Stars, and Bot Activity on GitHubSwyx [00:38:18]: If human trust is the thing that matters, I feel like GitHub as the developer social network could maybe do more there. Like vouchers are one system But, we have star counts, and then we have Contributor rights, and that's it. And I feel like there should be more in that space. I don't know if there's any other design decisions there.Kyle [00:38:37]: I think that one of the places that we don't really expose right now in this sort of way is, some degree of like hard trust and support, which would like for me is like sponsors is a good example of that.Swyx [00:38:49]: Ah.Kyle [00:38:49]: It like costs you something. To prove that I believe in your project and I trust you To some degree or I want to support you at the very least.Swyx [00:38:56]: Solve payments for open source. Why not?Kyle [00:38:58]: I think that I think that like as we keep moving forward, right, there's more and more projects where I'm, adding more and more dollars into sponsors personally because I want to like support them, but I also like know of I've probably never met them in person, but, I know of enough of their work that I want to support them. I think the thing that I don't love about stars or commit counts or anything else is ultimately, even with all of the various, abuse and de-spamming and deduplication work that we do or anti-abuse work that we do, these are all, not active social signals. They're passive ones that are ultimately gamifiable. And you may trust me, but another open source maintainer may not. And on what heuristic should you be, trusting me? That I think, is kind of where some of our thinking is right now. What signal from me is most important to you? You— If you can define that potentially, honestly in an agentic workflow that's what we see some of these open source projects do, where you have GitHub actions, and then you have like an agentic workflow that's calling AI, and you're setting these rules. Like if Kyle has submitted and gotten accepted PRs across any given project and has a social handle tied to his account in GitHub, and that social account's older than a certain amount. Really complex measures that matter to you ‘cause most open source projects have that heuristic built into their heads, if not written down in the contributing guidelines. You could take that and then go apply that and then just say, “Oh, we're not going to accept this PR.” Building something that is, I think, malleable to everyone's needs, is a little bit better, rather than going “Hmm, this account's too young.” Because what happens? The attackers just go and go and create a multitude of accounts, and they wait Until it ages up. Needs to have a certain amount of stars. That's how star inflation happens. Need to have a certain amount of reposSwyx [00:40:46]: Oh my God. YeahKyle [00:40:47]: With PRs. They all just create repos and submit PRs to each other, and then they come in and do something nefarious. And so, it's hard. It's hard to find the measure. So I think we're, we're looking more at how can we provide you tools so you can kind of choose what's best for you. And of course, we'll give you some standards. But the trust vector, gets down to I don't know, some version of like human digital ID like everyone's been talking about. Like how do I prove that it's meSwyx [00:41:13]: Give me your eyeballsKyle [00:41:14]: On the internet. Give me your eyeballs. Exactly.Swyx [00:41:18]: The I got to keep moving on Topics, but obviously I can go all day on this stuff because, I've been involved in GitHub and open source My entire professional career. Stars. Very superficial. Everyone knows it. But I think time to one hundred thousand stars is the fastest I've ever seen. Like people just reached that in I don't know, months. And then like at the same time I don't trust it right? Like how many of these are real or bot or like whatever. I don't know how to ask this but like what can we do about it? LikeKyle [00:41:49]: JustSwyx [00:41:49]: Is stars broken? Is stars fine?Kyle [00:41:51]: I think that there's kind of two, there's like two pieces. Obviously we're constantly like trying to find ways in which like your users are producing spam, which would, I would include like be like only doing star gamification. When we find them, we pluck ‘em out and we,Swyx [00:42:08]: But it's like a Whac-A-MoleKyle [00:42:10]: It's a hundred percent like a Whac-A-MoleSwyx [00:42:11]: There's no wayKyle [00:42:11]: Now, powered by AI to be helpful. But I think more so what I'm seeing is, a lot of the like fastest time to X tends to be because we're now inviting so many more people into like software development on GitHub That like the zeitgeist is just swarming? And it'sSwyx [00:42:32]: It's not just developers anymoreKyle [00:42:33]: And it's not you and I. Like like however you want to say like what a developer is it's not just folks who have been coding for a very long time. It's folks that have maybe started coding or only joined in since the AI era. And nowSwyx [00:42:44]: what's the latest Octoverse number? I know eighty million was my lastRem- member that a number of developers on GitHubKyle [00:42:50]: Oh, we're over 200 million now.Swyx [00:42:53]: Okay. Well, so you see?Kyle [00:42:55]: Like over 200 million developers now.Swyx [00:42:56]: But it's not developers, right? It's, it's people with a GitHub account.What Counts as a Developer in the AI Era?Kyle [00:43:00]: So, so this is, this is the biggest debate that I would say, everyone loves to have at GitHub at this point. From my perspective, right, I think that there's, there's clearly a difference between, professional enterprise developer and then developers. But I think that I think that the idea that we should be I don't know, splitting hairs or segmenting developers in the early era of software development is, not worth our not worth the time. SoSwyx [00:43:29]: When you get into gatekeepingKyle [00:43:31]: 100%Swyx [00:43:31]: What is a developer?Kyle [00:43:31]: 100%. ‘Cause I wasn't a developer when I started writing code? I was going toSwyx [00:43:36]: Oh, no. I made— I cloned a thing, seven years before I learned to code. And then I and then I wrote about my learning to code journey, and people Just called me a fraud ‘cause I had a GitHub account. And I'm “Well, no, I just use GitHub, but I don't know-” “I didn't know what I was doing.”Kyle [00:43:49]: I I remember that. I remember those sets of posts, and like that's, that's b******t. So I fight very clearly on the line of, if you create code, if you have an idea and you create it into some way of, I'm, I'm going to run it and use the app right now, you may still use AI in that moment, but that's okay. At some point you're going to do the next thing. You're going to create a big— You're going to have to learn about this database. You're going to fix a bug, whatever. We're all on some same journey, and those people are also hearing about the great new agent skill package or a new CLI tool or a new whatever. And those projects are going up because you want to be a part of this moment, just like I wanted to be a part of the Ruby community when Ruby was popping off when I started becoming a developer, and now I can just click the star button. And so I think that yes, there's clearly some amount of like spamming and game gamification that we're working against, but I really think we're just seeing this whole new cohort of folks that are moving from technology to technology because they're not working on a 20-year-old software application. They're working on a side app that they built on the weekend for their friends or for their new idea or whatever. And that's how you see these enormous charts going up and to the right with With stars.Swyx [00:44:59]: I think something that's remarkable is the persistence or, that GitHub extends to those folks. Usually when I see platforms go into a new audience, they usually have to, have like a second platform with a different name that wraps the main platform. But somehow GitHub has been able to sort of persist and extend, and it's friendly and whatever? So it's, it's nice.Spark, Low-Code, and Always Showing the CodeKyle [00:45:19]: I that's partially why I think as we've tried to move into I don't know, more like low-code-y things. We so we started working on Spark as like a way to, build an app and run it. I think that the reality is that we anytime we try to, kind of put even a veneer on top of it without when we put a veneer on top of something, we still always show you the code. That's kind of like a tenant. We're never going to, hide the code from you ever, because whatSwyx [00:45:52]: Why would you?Kyle [00:45:52]: That's, yeah, that's the whole point? However, I think that what we learned with things like Spark is that really the value of Spark for most devs is, easy runtime. And you may have a runtime or a host that you're going to use for that or you just build something and run it but, the package of making that even more simple isn't really needed for folks that are trying to build software and not just trying to build, an app, which is, slightly different, a slightly different goal. So I want to get you in, I want to get you comfortable. I think the best thing for me as, someone that did not traditionally come into software dev way back, I want anyone to be able to breach that chasm and not be in the I don't know, I feel like we're, we're still in an era of, STEM. I've got a 12-year-old and an eight-year-old, and it's “We got to get ‘em into STEM,”? Over and over. And I like I do, I do the things that good parents do. I was “Oh, you want to do coding?” “Yes, I want to do coding.” Do coding classes. But now they're just not afraid of doing software. And that's, I think, the thing that's honestly kept me at GitHub for so long. Anyone should be able to go and build a thing, just like I can go change a light switch in my house. I'm not going to go into the breaker box ‘cause I'll probably kill myself? But, I can go change that light switch. Everyone should be able to go and say, “This fricking app doesn't do what I want. I want it to work like this.” And that I think, is what's kind of kept us all connected with GitHub through the years and some and during the easiest of times or in the hard times because of that opportunity of, we're the home for all developers, and we want everyone to be able to have that feeling that we've had of, had an idea, I created it and holy s**t here it is.Swyx [00:47:37]: Here it is. All right, I'm going to try to do more spicy questions.GitHub's Hardest Scaling Moment: Growth, Agents, and UptimeKyle [00:47:42]: Great.Swyx [00:47:42]: Is it an easy time now or a hard time?Kyle [00:47:45]: Oh at GitHub? It's a hard time. Like, it's a hard time and also, I was just with my team and I said, “This is also, the best and most exciting time that I think I can remember at GitHub.” BecauseSwyx [00:47:57]: Best of times, worst of times. It's never oneKyle [00:47:59]: ‘cause we've we were talking about Octoverse reports and, usually we do an Octoverse report once a year, and we look at the numbers, and we say, “Oh my goodness.” I was at Universe in October saying, “This was the fastest year of growth that we've ever had,” right? And now we're doing more in a month than we did in a year last year.Swyx [00:48:20]: You're talking about PRs.Kyle [00:48:21]: Commits.Swyx [00:48:21]: Commits, yeah.Kyle [00:48:22]: PRs. Kind of like you name it by roughly every measure that we're looking at, there's some amount of sort of growth that is much bigger, and that is breaking our system in new ways, not old ways. Like webhooks were always notoriously, unreliable over the years?Swyx [00:48:38]: Whose fault is that?Kyle [00:48:39]: not anymore mine, but for a period of time, I'm sure you could pull up a tweet that was “It was me. I'm sorry.” but, now, that got rewritten at a scale level that is still working and is not having problems today. Now what we're finding isn't just the isn't the-The simple stuff that folks are on the sometimes on Twitter or on the internet are “Hey, why is this like this?” Sure. There's absolutely silly problems that we shouldn't exist. But now we're talking about, unique, novel permission problems that happen only at a scale across all different objects or whatever, that now we have to go rewrite this underlying system. And so it's, there are problems that yeah, caught us off guard, which I think I said. Like the growth is astronomical, but also we're making such material progress in that I'm excited once we're once we've kind of like reimagined the underlying foundation layer, or pieces of it at least, what's going to be possible when it's not just all of us and all the new people that are being developers and all of their agents and all the tools like working together. Because that'll still happen in that in that GitHub tool, that GitHub community. But it's a it's a hard day anytime we can't give you what you're looking for. We have the same problem internally. We operate through github. Com. Of course, we have backups when things go down and whatnot for our own operations but we feel it too. If it's not working it's not working for us, and that's kind of like the promise of dogfooding for GitHub. It's always been true. We're using the same tool you're using. We're not using a super secret version. We and so we also need it to be great for us for our customers of course for open source. And now an exponential growth of agents, Doing it too.Swyx [00:50:32]: I wanted to load for audio listeners who maybe haven't seen your tweets, whatever. So one billion commits in twenty-five. Now it's two hundred and seventy-five million per week on pace for fourteen billion this year, if growth remains linear. Is that still the pace? I don't know. It's been aKyle [00:50:48]: it's, it's speedingSwyx [00:50:50]: Roughly.Kyle [00:50:50]: It's still speeding up.Swyx [00:50:51]: It's, it's April, so yeah.Kyle [00:50:51]: Exactly. This was in April.Swyx [00:50:53]: All right. So basically you have fourteen x growth, right? Year on year on year. And I think that's a scaling issue. I think, I'm going to like try to really steel man this thing. People have experienced fourteen x growth. They haven't had your downtime. And that's like— C-can we go dig into that? Why? Like what's the— what broke? What are we doing to fix it? Like just anything for the community to reassure them.Why GitHub Reliability Is Breaking in New WaysKyle [00:51:18]: so there's a Like I was saying, there's a couple different places that we've seen the growth issues. Some of the growth issues, which is why we're t— I was talking about pushing hard on more CPUs is in actions in particular. More tools, more agents, more PRs mean more builds, more builds mean more CPUs. And so we are expanding through not just our data center, but obviously we were talking about moving to Azure and moving to, adding an additional cloud compute because we simply need more CPUs. Not as much GPUs. We definitely need GPUs too, but now CPUs are becoming a factor.Swyx [00:51:53]: It's very CPU heavy.Kyle [00:51:54]: Underneath the hood when it comes to some of the underlying services, we've been breaking up over the years our database infrastructure, so that way we have, more cognitive separation between our the various services. The place that we continue to have pain is in, permissioning. And so right now m-many of our permissioning layers sit into a database that we like internally call MySQL One, and old Hubbers will know what I'm talking about. And so we've been pulling things out of MySQL One for many years, because like and we use we use Vitess and we use other technologies to shard and we do it as one bigSwyx [00:52:31]: Famous thing, PlanetScale was born from this andKyle [00:52:32]: A hundred percent. Sam Old Hubber and friend. And so finding these opportunities to like break this out and then do that globally. The other thing that I think is interesting and both a unique opportunity and tricky is we also run everything I just talked about in a black box container with GitHub Enterprise Server for people that work on-prem. So we take everything I just said, and we also do it on-prem, and we also do all of that and we do it in a data residence setup for customers that need to have their data in a single location. Each of these has the unique characteristic around how we're sort of storing that data in MySQL or in a permissioning setup. That's where some of these outages have oc-occurred, where you're seeing it more like across the board rather than just like the one pieceSwyx [00:53:17]: Filling the databaseKyle [00:53:17]: Isn't quite working. Exactly. And so part of it is that. I think there's been some other places where agents are much more or more projects appear to be moving towards monorepo versus we were going the other direction for many years in the industry. Repos were smaller, but there were more of them, and now we're seeing the opposite. Repos are bigger, and there's, not fewer of them per se ‘cause there's new growth, but, we're just seeing many more big repos. Big repos, big monorepos have always had, a unique performance problem. Because each one, is slightly different if, particularly if the underlying blobs are incredibly big Inside the repos. And so we've done a ton of work that you pro— like most people haven't probably experienced, unless you're in this case of the monorepo. But that Git, infrastructure layer improvement does help the overall, system because, many of the improvements that make monorepos work better make all repo infrastructure work better. And so, I could kind of keep going down the line where it's another thing where we're moving out of, We're changing how we do j I'll just say job queuing for lack of a better, explanation changing the underlying technologies there.Swyx [00:54:32]: I spent two years being a job queuing guy, so.Kyle [00:54:34]: And so it's kind of a little bit of a little bit of piece by piece, and it's mostly because as we were— as it was built, we built everything in a way that assumed, I guess in some ways that the size of the pipe of work was going to remain the same. There's just going to be more people coming through each of those pipes. But instead now in places whereA git push was, generally a certain size for example, is now, no longer true.Swyx [00:55:03]: Oh, yeah.Kyle [00:55:03]: OrSwyx [00:55:05]: I push a thousandKyle [00:55:06]: On the average. 100%Swyx [00:55:06]: A thousand line commits like dailyKyle [00:55:07]: Same thing with PRs. Like PRs same thing. And like we've talked about optimizing that and making changes where, and there were technology choices that did not work there? And it got slow, and it didn't It was not fast. It did not do what the users wanted. And so we've been reeling that all out and going “Okay, that's just not right. Let's stop putting good money after bad and do it the do it the right way or the right way now.” So there's It's a it's a lot of things, not quite when I've experienced scale at GitHub historically, it's almost always two options that we've used. We go vertical scaling, particularly with databases, right? And we go horizontal scaling. Oh, we just have more people using this service. Great. We're going to add more servers, and we rack them in our data center, or we use it in a cloud. And now we're sort of in a like diagonal, where like vertical doesn't really work anymore. Horizontal isn't work either because we're all We all have some CPU or GPU constraints in the world now, and now we have to go in and like crack open services that have been running for 10 or 15 years and go, “Okay, the rules of this service have legitimately changed, and now we have to rewrite them.” None of this is an excuse. This is like we're We have to do the work. We have to make it better.Swyx [00:56:22]: actually as an infra guy, I'm “This is like one of the most fascinating scaling challenges I've ever seen.”Kyle [00:56:26]: That's that's, that's the thing that's the thing that it's hard for Like when we weren't talking about it publicly, and I was like I came out, and I was “Hey, I just want to explain what's going on.” Part of it comes from a very old GitHub ethos, which is it's our it's our uptime. It's down. W What I know you're a developer, so you're, you're inclined to want to understand more what's going on. But at the same time us going “Hey, this service didn't, perform the way we expected, and now we have to go change it,” we weren't We're not trying to hide anything from you i

Are health care stocks poised for a comeback? In this episode of Market Sense, a veteran Fidelity portfolio manager breaks down the sector's strong fundamentals and explains why he believes this sector has long been overlooked and undervalued. From the growing impact of AI to breakthroughs in biotech and diagnostic technology, we explore the key trends reshaping the industry and why investors should be paying attention. Plus, all the latest market news, all in just 20 minutes. If you want more insights from our Fidelity portfolio managers regarding potential investing opportunities and risks, bookmark this page for the latest articles and videos. Read the full transcript View the slides Watch the video replay

Nick Hodge, Co-Owner of Digest Publishing and editor of Foundational Profits and Underground Alpha, joins us for our monthly longer-format discussion on different macroeconomic factors and market reactions to the war in the Middle East, his key takeaways from 2 different site visits to South Dakota and Wisconsin, and investing strategies in select copper, gold, and critical minerals stocks.   We start off reviewing the mix of macroeconomic movers and knock-on effects from geopolitics as it relates to the closure of Strait of Hormuz, the US/China meetings last week, projections around central bank monetary policy options, rising bond yields and interest rates, a strengthening US dollar, GDP growth, rising inflation, sovereign debt loads, and AI datacenter buildouts.      The US stock markets have shrugged off most of these economic datapoints and geopolitical news, continuing to blast up to new all-time highs over the last week. He points out that the CRB commodities index has also been strong lately, lead by base metals, soft commodities, and the energy space.     When reviewing the commodities,  it has been hard to ignore the strength in the copper pricing, which has been up at all-time highs over the last few weeks of May, and Nick shares his approach is to investing in the copper equities.   For exposure to the base metals producers he has been positioned in the iShares MSCI Global Metals and Mining Producers ETF (PICK), which has performed quite well over the last year and especially in 2026. Nick reiterated points from our prior conversation about 2 of the copper developers with good investor engagement, solid pounds in the ground resources, and good fundamental catalysts being: Gunnison Copper Corp. (TSX: GCU) (OTCQB: GCUMF) and Aldebaran Resources Inc.  (TSX-V: ALDE) (OTCQX: ADBRF).   Nick highlighted the recent acquisition of Arizona Sonoran Copper Company Inc. (TSX:ASCU | OTCQX:ASCUF) by Hudbay Minerals Inc (TSX, NYSE: HBM) and how that may be used as a good case study and lens for consideration of other advanced copper development assets and what kind of projects and jurisdictions may interest the senior producers. Gladiator Metals Corp. (TSXV: GLAD) (OTCQB: GDTRF) is a copper and gold exploration story in Nick's portfolio that just released some high-grade intercepts in the Yukon, and still has a lot of drilling on tap for this season as a catalyst. When reviewing why he prefers safer jurisdictions in the Americas for copper investing, he did point out a company like Ivanhoe Mines (TSX: IVN) (OTCQX: IVPAF) is an exception, due to the quality of the management team to navigate the risks when operating in Africa.   Next we got a boots-on-the-ground recap of Nick's 2 recent company site visits: Lion Rock Resources Inc. (TSXV: ROAR) (FSE: KGB) (OTCQB: LRRIF) – The company recently announced Phase One drill results at their Volney Project in South Dakota. The system features high-grade lithium, tin and tantalum hosted within spodumene-bearing LCT (Lithium-Cesium-Tantalum) pegmatites. GreenLight Metals Inc. (TSXV: GRL) (OTCQB: GRLMF)- GreenLight is a Wisconsin-focused exploration company advancing copper-gold and gold projects across the Penokean Volcanic Belt-one of North America's most prospective VMS districts. GreenLight's Wisconsin portfolio includes the Bend copper-gold deposit, the Reef high-grade gold project, and the Lobo and Lobo East massive sulfide targets.   We wrapped up getting the near-term technical price support levels that Nick is watching for in gold.  For now he is not concerned about gold falling into a true bear market, and he is treating the pullback we've seen in the precious metals a buying opportunity. Any short-term consolidation in pricing should be juxtaposed against the fundamental structural drivers for the longer-term precious metals bull market that are all still solidly in place. He's been using periods of sector weakness in the PMs to add to positions in both GDXJ and Royal Gold, Inc. (NASDAQ: RGLD), along with some other junior precious metals stocks.   Click here to follow Nick's analysis and publications over at Digest Publishing     For more market commentary & interview summaries, subscribe to our Substacks:   The KE Report: https://kereport.substack.com/ Shad's resource market commentary: https://excelsiorprosperity.substack.com/     Investment disclaimer: This content is for informational and educational purposes only and does not constitute investment advice, an offer, or a solicitation to buy or sell any security. Investing in equities and commodities involves risk, including the possible loss of principal. Do your own research and consult a licensed financial advisor before making any investment decisions. Guests and hosts may own shares in companies mentioned.

The new AIEWF website is live! CFPs close in 2 days and we will run our first New Engineer Orientation this weekend, get your tickets booked ASAP as they -will- sell out. Take the AI Engineering Survey and get >$2k in credits and free AIE WF tickets!One of the central tensions in the agents industry is that even while there are major decacorn agent labs like Sierra, Decagon, Notion and Cursor being built up, it is also true that it has never been easier to DIY agents, with a plethora of agent frameworks like LangGraph and Pydantic and Flue, and managed agents from Anthropic and Gemini and Amazon. There has been a wave of companies building their own background agents from Shopify to Stripe to Paradigm to Razorpay, and even Cognition's friends Ramp have built their own coding agent with other friend Modal.You'd think Cognition might feel a bit threatened, but they're not - even after all this, they were way oversubscribed for the $1B Series D they just announced:Walden Yan, coiner of context engineering and Chief Product Officer/Cofounder of Cognition, invited OpenInspect's Cole Murray to talk about why the Devin is in the Details.Full conversation live on the pod today: In retrospect, async agents were the most AGI pilled bet you could make in 2024 - the models weren't good enough yet to vibecode, and people didn't trust AI enough to let it rip, nobody (including early Cognition) was sure about the form factors. Now it is obvious:* The first wave of AI coding tools made the developer faster but remain heavily in the loop. Copilor and Cursor's tab autocomplete are prime examples However, the workflow was still heavily centered around and bottlenecked by the developer's local workflow: a developer in an IDE, watching the model, accepting or rejecting changes, and pushing code one interaction at a time.* The second wave was local agents: Claude Code, Windsurf, Cursor's agents pane: first one and increasingly many terminals all running concurrently.* The current Age of Async Agents points to a different future focused more on agent orchestration which drives end-to-end development.According to previous guest Steve Yegge, there are finer-grained 8 levels to agent adoption, but we have collapsed it into three.As Cursor's Michael Truell put it in The third era of AI software development:Cursor is no longer primarily about writing code. It is about helping developers build the factory that creates their software. This factory is made up of fleets of agents that they interact with as teammates: providing initial direction, equipping them with the tools to work independently, and reviewing their work.The agent should not sit solely inside the developer's flow. It should be setup to work in the background so that you can give it a task, a repo, a machine, a shell, a browser, tests, memory, and review loops to go do the work somewhere else.In less than a year, the sentiment has shifted from avoiding multi-agent systems:to suggesting approaches that actually work:From coining “context engineering” to building the infrastructure behind Devin's 7x PR growth and jump from 16% to 80% of commits across Cognition repos, Walden Yan has had a front-row seat to the background-agent shift. In this episode, Cognition co-founder and CPO Walden Yan joins swyx alongside Cole Murray, creator of OpenInspect, to unpack why everyone is building their own Devin, what changed after the December 2025 model inflection, and why “spec to pull request” is now becoming a real production workflow.We go deep on the architecture of background agents: harness-in-the-box vs out-of-the-box, why Devin separates the “brain” from the machine, why repo setup is still one of the hardest problems, why Docker is not always enough, and how full VMs, snapshots, scoped secrets, GitHub bots, Slack integrations, and video-based testing all fit together. Walden and Cole also dig into memory, MCP limitations, multi-agent orchestration, AI code review, SRE auto-triage, PMs shipping code from Slack, Windsurf 2.0, hybrid frontier/sub-frontier systems, and the real failure mode of uncontrolled vibe coding: your codebase regressing to your worst engineer.And as agents eat software… and software eats the world… you can draw the conclusion on what is next:We discuss:* Why the engineering world is waking up to background agents and cloud agents* The December 2025 model inflection that made spec-to-PR workflows practical* Devin's 7x merged PR growth and rise from 16% to 80% of commits* Why Cole built OpenInspect as an open-source background-agent system* The economics of $20/seat agent products and why monetization is tricky* What Cognition actually sells beyond Devin: infra, onboarding, integrations, and adoption* Harness in the box vs out of the box, and why architecture matters* Why Devin separates the brain from the machine for security and permissions* Repo setup, scoped secrets, Docker Compose, and agent-ready dev environments* Why full VMs matter when agents need to run real applications and test them* Android, macOS, Windows, nested virtualization, and machine-specific agent work* Why testing is much harder than “computer use”* Screenshots, video verification, and the “I know it works” merge moment* GitHub UX, Devin Review, AI reviewers, and agents responding to PR comments* Why MCP alone is not enough for first-class Slack and enterprise integrations* Memory, Knowledge, skills, Claude.md, and why retrieval is still unsolved* Devin's auto-generated memories and the challenge of memory pruning* Always-on agents as permanent PMs for issues, tickets, and product areas* Sub-agents, meta-Devin management, and what multi-agent systems actually add* Why pure auto-merge vibe coding breaks down after about two weeks* AI code smells, lint rules, reward hacking, and Semgrep for agent-written code* GitAI, inline context, and preserving the “why” behind code changes* Local testing, mock servers, older codebases, and preparing companies for agents* Windsurf 2.0 and the handoff between local foreground agents and cloud background agents* SRE auto-triage, support workflows, and agents as first responders* PMs, marketing, and non-engineers creating pull requests from Slack* AI agent budgets, $1k-$5k per engineer spend, and hybrid frontier/sub-frontier systems* The rise of autonomous coding factories and who Cognition is hiringWalden Yan* X: https://x.com/walden_yan* LinkedIn: https://www.linkedin.com/in/waldenyan/Cole Murray* X: https://x.com/_colemurray* LinkedIn: https://www.linkedin.com/in/colemurray/* OpenInspect / Background Agents: https://github.com/ColeMurray/background-agentsTimestamps00:00:00 Introduction00:00:43 Why Everyone Is Building Their Own Devin00:01:57 Devin's 2025 Ramp: 7x PR Growth and 80% of Commits00:03:49 OpenInspect and the Rise of Open-Source Background Agents00:07:59 What Cognition Actually Sells Beyond Devin00:09:56 Background Agent Architecture: Harness In vs Out of the Box00:12:08 Separating the Brain from the Machine00:14:07 Repo Setup, Secrets, Docker, and Full VMs00:19:13 Why Testing Is Harder Than Computer Use00:22:40 Video Verification and the “I Know It Works” Merge Moment00:23:19 GitHub UX, Devin Review, and AI Code Review00:25:42 MCP, Slack, and Enterprise Agent Integrations00:28:59 Memory, Knowledge, and Always-On Agents00:36:16 Sub-Agents, Multi-Agent Orchestration, and Meta-Devin00:43:55 Vibe Coding, Auto-Merge, and Codebase Decay00:48:38 Agent Infra, VPCs, Cloud Providers, and Fast VM Restore00:52:25 AI Code Smells, Reward Hacking, and Code Review Systems00:56:10 Making Codebases Agent-Ready00:58:30 Windsurf 2.0 and the Local-to-Cloud Agent Handoff01:01:15 SRE Auto-Triage, PMs Shipping Code, and Agent Use Cases01:04:32 Agent Budgets, Hybrid Models, and Autonomous Coding Factories01:06:51 Hiring at Cognition and OpenInspect Consulting01:07:45 OutroTranscriptIntroduction: Walden Yan, Cole Murray, and Context EngineeringSwyx [00:00:00]: All right, we're in the studio with Walden Yan, co-founder of Cognition, CPO.Walden [00:00:08]: Happy to be here.Swyx [00:00:09]: Which is a cool title. And coiner of context engineering.Walden [00:00:15]: Although I think there are many people who'd used the terms in various ways beforehand, but I did find that people, both internally and externally, enjoyed the upgrade from prompt engineering or model wrapping into maybe a more thoughtful way to build agents.Swyx [00:00:33]: For those who haven't caught up on that, I have on screen the Don't Build Multi-Agents post, which you should go read on and we might refer to, and Cole Murray, who created OpenInspect.Cole [00:00:43]: Great to be here.Swyx [00:00:43]: So let's talk about it. Everyone is building their own Devins. What's going on?The December Shift: From Handholding Models to Autonomous PRsCole [00:00:51]: So I think the engineering world is waking up to this idea of background agents, cloud agents, whatever you'd like to call it. And I think we saw a shift around the December timeframe of 2025, where the models Opus 4.5 and GPT 5.2, they reached a capability where we moved away from handholding the model and being able to actually more or less autonomously drive the model. And what I mean by that is that we could pretty much go from a specification to a completed pull request, assuming the spec was good enough, with very little friction. And that paradigm alone, I think, changed a lot of how we interact with agents, and opened this world where background agents became more practical.Swyx [00:01:41]: I think for Cole, everyone experienced this in December, but I feel like there was just this increasing ramp, right? There was this moment which was, I think, Sonnet 3.7, where, You guys rewrote Devin in one night or something. So describe 2025 or how it felt from your side.Walden [00:02:01]: In retrospect, we always thought it was ramping up, but then even now, over the last three, four months from today, it's been ramping up even faster. So it's almost funny to be talking about how, big of a leap Sonnet 3.7 was, and honestly, a lot of it was stripping out parts of Devin that were no longer needed with that jump in of intelligence. But I also just think that a lot of the recent leaps, especially, you look at, models like Opus and the latest GPT models, they are reaching levels of autonomy where people are actually finding that they actually can just be hands-off. And people who were once debating, “Oh, do I need to be in the weeds with my model in the IDE? Can I just completely move it off into the cloud?” That's a more serious conversation, and we've seen that in all of our growth charts. Internally there's this funny graph where our usage has, of PRs, our merged PRs, has grown 7X since I forget what it was called.Swyx [00:02:57]: I think Dev, maybe tweeted that. Yes.Walden [00:03:01]: it grew like 7X over, the last, I think it was, two months, three months, something like that. And then you see our engineering headcount growth. It's, gone up by, 10% or something.Swyx [00:03:11]: We were, we were afraid To release this. So this is Devin commit percentages on all Devin repos, was 16% in January and now 80% in March.Walden [00:03:25]: It's a big shift right now. And so it makes sense that a lot of people are now thinking about, buying Devin, but also maybe, trying to build their own and there's Lots of I have a lot of fun building Devin, so I can see why other people would want to build their own cloud agents as well. Matt, well, maybe it's good to hear, what initially inspired you to try to build OpenInspect?OpenInspect: Ramp, Cloud Agents, and Open SourceCole [00:03:49]: OpenInspect came about, through primarily my clients observing how they were using tools like Claude, OpenAI's Codex at the time, and seeing some of the friction that they were having with it. Primarily the Claude was being used through Slack, and a big issue they ran into was that the sessions that were launched were specific to whoever called it via Slack. And so if a PM was the one who invoked the session and they would then go to pass context to engineering can't see the session. And that in itself was a deal breaker because the PM, “Hey, engineering, can you jump in?” But there's nothing to jump in on unless they're copy-pasting out or the single response that came back. And so seeing some of these problems, I had built a similar architecture internally, just to experiment with, test out different ideas as this trend of moving off of localhost was starting to become, And as Ramp released their blog post, I had a lot of the pieces for this already in place, and just thought it would be funny to, see what Claude could do just purely from the blog post. And on my X account, there's actually a thread of where I live tweeted, going through thisCole [00:05:14]: comparing GPT and Claude as both of them are going through it.Swyx [00:05:17]: On the announcement thing or something else?Cole [00:05:19]: right after it got released. We can put it in the show notes. Yeah, it was helpful that I had already knew how to verify the system. I knew what I was looking for. I think Ramp did a great job of really illustrating, the technical aspects of how to build something. It was much more than just like, “Hey, we built a great system.” It was, “And here's how you can build it too.” And so, I resonated a lot with that, just with the problems that I was already seeing, and I thought that, looking around, I didn't really see anything in the open source community that, met this type of system. I think there's a lot that run, in localhost like Superset, Conductor, and many others.But nothing that was actually running in the cloud. And so, I built it, and I thought it was interesting to just open source it and allow anyone to then have a foundation that they can mix and match on top of.The Business of Background Agents: Open Source vs. DevinSwyx [00:06:16]: So literally after Devin was launched was, there was OpenDevin Which became All Hands. I don't know if you tried that orWalden [00:06:22]: I was going to say, one of the things that interested me a lot with OpenInspect was, you didn't try to go make it then something you monetize. There are a lot of, I think, these open source projects would then go and really try to, raise VSwyx [00:06:36]: That's why no OpenDevin. Yeah.Walden [00:06:38]: yeah, and how did you think about that? I thought that was very interesting.Cole [00:06:44]: I thought, and just what I had seen across my clients, was that having a background agent system is going to become a critical infrastructure within their company. And so because of that, I think that I wanted to open source it so that they could fork it and put in whatever customization they wanted. To that question though, I get asked all, “Oh, are you going to raise? Are you going to turn this into a service?”Walden [00:07:08]: I'm sure you've gotten offers.Cole [00:07:09]: but primarily I don't want to do that for a few reasons. One, I think that I don't want to compete for, $20 a seat. I think that is just a really difficult business. I think it's very easy to copy the main pieces of it. Again, I built this fairly quickly. And I think because you are not owning, I guess, the entire stack, it's hard to monetize. You have money being made at the sandbox layer with Daytona, E2b, many other players. You have money being made at the model layer. And you sit in this weird in-between gray area where what are you actually selling? You're selling, I guess, the infrastructure. You're selling, the integrations maybe.Swyx [00:07:55]: let's ask the guy. What are you What are you selling?Walden [00:07:59]: Well, yeah, there's multiple layers to this in practice, and actually it's funny you mentioned the infrastructure, ‘cause when we got started building Devin as well, we had to go figure out how to make the infrastructure as well because,Swyx [00:08:10]: You had to build this two years before everyone else,?Swyx [00:08:15]: Including, the model sideWalden [00:08:17]: It was not, it was not very polished at the start, when we just built it off of raw VMs from cloud providers like EC2, the boot up time was so slow, I think, And especially then, turning off the machines, saving them, and then to be able to bring them back up again when the, when you want Devin to wake up again later. It would just be out cold for like 10 minutes because that's just how long these systems took. They were not built for this repeated down and up usage. And so we actually had to go do all of that. And as a result now, one thing we offer when we go and sell Devin to people is, you don't have to worry about all the compute side of things. We'll make it work. We'll make it work in your cloud if you want it to. But aside from the product, and I want to go into the agents and the tuning of the intelligence part later, but I think a big part of what we do at Cognition as well is to just make sure that your company learns and uses and adopts these coding agents. ‘Cause I think for especially the largest enterprises in the world, you find that there is a lot of people who want to move over to using AI for their day-to-day workloads. But because of the way projects are planned, because, not everyone is literate in using AI in these ways, having a team of engineers who can actually go in and onboard you, set up all the integrations you need, the automations you need to really get to that level of, leverage with AI, is super helpful. And so We do that. We show thought partners to the customers that we work with as well.Swyx [00:09:56]: So let's talk about, architectural stuff. I think that's always, that is something that was the topic of conversation between the two of you. Is this, the mental model that you want to start with or something else? I'll just leave the floor open to you guys.Agent Architecture: Harness in the Box vs. Out of the BoxCole [00:10:11]: I think, maybe we can start here as just a general what are the pieces of a background agent system. And then maybe we can go into some of the nuances of, Decisions that you can make.Swyx [00:10:22]: But I guess I also Like, what, maybe what Walden is saying is the agent is like in this open code box, I guess. Right? This is infra, and then there's, that's the agent. And you had this discussion about whether you put the agent in here or in Out externally. Can you tease that out?Cole [00:10:39]: In a background agent systems, you have a decision to make of where the agent is actually going to run. This is typically described as the harness in the box or out of the box. With running the agent in the box, you're making some trade-offs by doing that. The negative trade-off you're making is primarily security. Because the agent is running in that box, unless you otherwise design it, all of your secrets need to go into that box as well. And given the nature of AI, it can be unpredictable, and you could very easily end up accidentally exfilling your secrets, or other unintended behavior. Now, the out of the box is the idea that we are going to have the actual agent running not directly in the sandbox, and we will have, quote-unquote, the brain of the agent running in some type of worker, control plane. That sandbox then is going to serve as the hands where the brain is basically operating and making tool calls into that environment to manipulate it. I guess other trade-off that you're making between the two systems is that, in my opinion, running it out of the box is much more complex because, you have state that has to be managed, whereas if you're running it in the box, all of the state of that agent is actually in the box, and yes, it's you could persist it elsewhere, but it's all localized and you have less concerns to worry about.Walden [00:12:08]: I think a lot of that, what you mentioned, is why we actually from the start built Devin to what we called separate the brain from the machine. The other thing that this allows you to do is reuse any existing infrastructure you have for dev boxes Perhaps. And so you don't have to worry as much about making a new type of dev box that has all the dependencies the brain needs, as you mentioned, the secrets the brain needs as well. One thing that we've seen some customers run into is, you have a GitHub app and you want Devin, your agent, whatever, be able to interact with GitHub through this application, but then you have different users with different actual permissions. If they are all interacting through the same GitHub app and there's no actual, separation between the system that decides, what it does and the actual secrets on the machine, then you run into an issue where, okay, it's hard to do the separation. But in practice, with Devin, it's much easier because we just say whatever you put on the machine, that is, the scope of basically what the user is free to do, what the agent is free to do. So only put the most scoped secrets on that machine, and then the brain is fully not accessible from the machine. So you don't have to worry about messing with the, any of the most secure parts of the brain if the user is free to do whatever they want with the machine.Swyx [00:13:31]: I was going to just bring, I have this, chart from OpenAI, where I don't know if this is, in the box, out of the box. That is something that they do use to describe it. And then also recently Anthropic did, managed agentsSwyx [00:13:44]: Which is, this is their thing. I don't know. It's all, it's all variations of the same pattern, right?Cole [00:13:49]: So this would be out of the box.Swyx [00:13:51]: Which, is preferable for them because it's less work?Cole [00:13:56]: I would say it's more work.Swyx [00:13:58]: It's more work?Cole [00:13:58]: But it, in my opinion, it is the better architecture of the two. It's just, you're taking on a bit of complexity by doing that.Repo Setup, Docker, and VM-Based Development EnvironmentsWalden [00:14:07]: One thing I've not seen a lot of other players do well is how do you manage what's actually on the box? And this can be complex for many reasons. Let's say you have a big repository that's changing and updating a lot with changing dependencies. How do you make sure that the working environment of the agent actually stays up to date, has all the credentials it needs to, let's say, run the app and test it, and all the things you want your autonomousSwyx [00:14:34]: So a repo setup.Walden [00:14:35]: Exactly. So in, internally At Cognition, we call this repo setup.Cole [00:14:39]: The hardest part ofWalden [00:14:40]: It's been a perennial problem since the start of the company, of how do we help people get this set up? Because not everyone just has, working cloud environments working out of the box. And do you find this to be a common problem withSwyx [00:14:53]: How do you solve it?Walden [00:14:53]: Your clients?Cole [00:14:54]: This is a very common problem, and through my consulting, this is a lot of what I help teams do. A lot of teams don't really have great developer environment setups, if any. A lot of the times it's, “Go talk to Bob and get the secrets,” and that obviously doesn't work when the agent needs to actually set this up. And so a lot of that, most teams are using Docker Compose or some type of microservices. And so for theSwyx [00:15:19]: Even in prod?Cole [00:15:20]: Not in prod. With the OpenInspect, you are using this primarily to interact, and make code changes. There is other use cases, but you can hook, whether through CLI, MCPs, other tools, you can then hook that into your production systems primarily for, SRE type use cases. But you are not, necessarily, trying to test your prod internal microservice through the system.Walden [00:15:48]: And you mentioned Docker Compose. I think one direction we saw some of our friends take early on was, using Docker containers as the level of abstraction for their models. There's lots of reasons, I think, why Docker containers are not great. One thing is, Docker container's not really a true security boundary, for one. But the other is, if you are running real applications, a lot of times those applications use Docker, and then you have to think about Docker in Docker, which is, really weird. And so I think part of, the really hard challenge of getting VMs to work, why did we do that? Well, it was because we realized that you actually needed, full VMs to be able to do these types of things. And especially nowadays where there's actually value in running the application and clicking around and sending you screen recordings of these things. The value just, keeps adding on top of that. But it is a decision I see people run into when they try to build their own systems, is, “Oh, do we, in addition to this, do we put the agent in the machine or out of the machine? Do we use Docker? Do we use something else?” What do you recommend people nowadays?Cole [00:16:57]: I think Docker is a good solution for maybe not running the agent, but running your infrastructure, because that is more or less the same setup your engineers are probably already using. If they're not, then I don't know what they're using. But they're probably already using Docker Compose.Swyx [00:17:14]: I've always had a small candle for web containers. I don't know if you guys have tried them before.Swyx [00:17:19]: To me, they were, supposed to be like Docker Light.Cole [00:17:22]: Is it?Swyx [00:17:22]: I don't know.Cole [00:17:22]: No, I haven't tried it. But yeah, I think any environment that you've set up that is a good experience for your developer naturally lends itself to being easy to set up for the agent. And once you figure out that local developer story, you've more or less solved the agent in a sandbox, environment setup. OpenInspect does have hooks as well, where you can, run a setup SH script that will pre-install everything. You can then pre-snapshot that build so it starts instantly, and then there is a second hook to actually then, restore the state of the sandbox when it comes back. And so you can already have all of those microservices running and basically get the same experience that you would on your machine within the sandbox.Testing Agents: Computer Use, Screenshots, and Real App WorkflowsWalden [00:18:08]: Another thing that we've been thinking a lot about is like Different VM service offerings. Have you had customers where they needed like macOS specific VMs or like Windows specificWalden [00:18:20]: VMs?Walden [00:18:22]: There are like many technologies in the world that only work on specific types of machines, right? If you're building a.NET application that has to run on Windows or like, maybe more commonly if you want to build iOS or macOS Does that workSwyx [00:18:32]: Does Commission supportSwyx [00:18:33]: Choices like that?Walden [00:18:35]: The fundamental architecture we do, because we do the separation, it does support, but the actual work in progress is happening right now on these. Another thing that we've actually recently added support now for, it's in beta, is doing Android development. To do that, we needed to support, I think, nested virtualization within our machines because the VM itself is like a, is a virtualized Firecracker instance, and then you had to then run another Android emulator inside. And there's like weird performance issues that like, it, which is why it's like still in beta. We have to think through these problems, but it unlocks a lot for anyone who wants to do Android development.Swyx [00:19:13]: I was trying to find like a reference video for the testing thing. I couldn't find it, but I think you worked on the testing, capability. Why call it testing and not like computer use or I don't know, it's, what's the general Category of problem?Walden [00:19:26]: I think that when people think about the ability of an AI to run your app and test it, I think they actually over-index on the computer use part of it because computer use in my mind is the literal, okay, you want what button you want to click. Can you emit the right coordinates to go click that button? I think testing is actually a really interesting likeWalden [00:19:48]: Problem-solving, challenge for these AIs because if you wanted to do arbitrary testing, imagine you make a change that spans the frontend and the backend, maybe, even some other like even more deeply nested service. To actually test that change, we have to reason through what-- how do you first run these applications to orchestrate with each other with the right version of the code? Then, okay, how do I trigger the feature or how do I make the thing actually happen? And this can get arbitrarily hard, maybe you have to be an admin. Maybe a certain thing has to be feature flagged on. Maybe, you have to like run two sessions and then send us a very specific word into one of them to trigger a specific behavior. And figuring out how do you do that requires a lot of code base context, requires, a lot of orchestration that we've specifically done. And in some cases, we found that you actually, no one frontier model can actually do this full end-to-end task itself.Walden [00:20:42]: We've seen cases where we actually had to orchestrate different frontier models together to solve this problem together. That is where we spend most of our time when we think about this testing problem, not so much the computer use part. Computer use for what it's worth has gotten a lot better with recent models and it's made that part of the job certainly easier.Swyx [00:20:58]: Especially with like even 4.7, that they released yesterday, apparently like way better in terms of the vision stuff, which is going to be encompassing computer use.Walden [00:21:08]: Having evals for all these as well is something that like takes a while to build up. And having the evals be right is tricky as well. Do you ever see like, clients who are building their own agents have to start standing up evals to make sure things don't regress?Swyx [00:21:25]: Not so much evals in the traditional sense, but specific to the testing part that has just gone in. I just added support for screenshots And in theory you can also do video. I need to put in a plugin to do that. But they do show up natively, and it was a very heavily requested feature, especially after Cursor's recording came out. I think that was very enlightening for everyone of like, “Oh, this is a very good feature to actually have.”, I think with Devin you guys have had this for a while.Swyx [00:21:57]: Oh, yeah. See how screenshots work. Yeah, I don't know if there's anything, super and not obvious. It's like once what feature to build, you can just prompt it and it Will mostly work.Walden [00:22:09]: I think to Walden's point, though, the computer use is a subset of the larger testing problem, and I think that's very specific to the code base that you're working and it's not something that, out of the box that you could just solve it. The-- you do need the code base context to actually know how to test it. And I think in the case of a background agent system, you fortunately do have that code base locally that what is changing and could then inspect it and use that to drive the model.Swyx [00:22:40]: For those who haven't seen it before, this is an example of how it works. You, after the PR is done, you click testing approved, and then it sends you back a video. What I really like is that it labels, It's very small here, but it actually labels what it's testing. And then it-- and then you actually see the cursor and everything. So I don't know, yeah, the engineering in this, just Whatever you want to show. ‘cause this is like, this is one of those like, oh, few of the AGI moments, right? ‘cause Once I look at this, I actually don't I wish I can just merge inside Of Slack instead of going to GitHub ‘cause I don't need to see the code. I know it works.Walden [00:23:19]: Maybe a new feature in Cursor. Yeah, the annotations at the bottom was also a big difference for me when I, when I added those.Swyx [00:23:27]: It's just like, what am I looking at? What are you trying to demonstrate?Walden [00:23:30]: Exactly. There's a surprisingly long tail of small details that ends up making a big difference for this end metric of like how fast do you actually merge the code in. One experience that we spent a lot of time tuning early on was what is the right experience on GitHub for these tools. Because I think, most tools out there when you build the agent, you'll think about, oh, it'll create the PR for you. We try to take that a step further and say, “Oh, what if we actually made sure you could interact Devin, with direct Devin directly on GitHub?” And so we made sure that you can comment on GitHub, and Devin would actually receive those comments and address them back. But there's actually quite a bit of tuning you have to do here because you can imagine that actually like-We recently have Devin Review, for example. Devin Review will post comments on his own PR And then Devin has to then goGitHub Workflows: Devin Review, Comments, and PR AutomationSwyx [00:24:23]: He answers his own comments, which is Really loopy. So like, yeah, I like that it just updates here that it's, that I have commented But usually it's just me saying like, “Hey, merged, fix any merge conflicts.”Walden [00:24:37]: The, so when Devin fixes his own comments, you might be scared that, oh, maybe I'll infinite loop. But we've put a lot of work into making sure it doesn't, both by making sure that the comments are high signal, but also that the agent is thoughtful about what comments it immediately goes and tries to fix, and what comments it's like, “Wait a second, I think you're wrong.” Actually, that's one of my favorite moments is when Devin tells me that I'm wrong, when I try to get it to do something different. But tuning that behavior, actually makes a big difference in terms of how useful the actual GitHub experience is.Cole [00:25:06]: I think to touch on that as well, I think having the AI reviewer integrated into the system is a critical part of this background system. OpenInspect does have that. It has a GitHub code reviewer that you can control the prompt. It does do comments as well. It doesn't do them automatically yet. The capability is there, but it's not fully used.Swyx [00:25:27]: So you have to ask for it?Cole [00:25:28]: you do, yeah. You can tag it on GitHub, and then whatever you named your, GitHub bot, it will then follow up on it. It will then, if you have merge conflicts or whatever you have asked it to resolve, it will then resolve it, but it doesn't do it automatically yet.Integrations: Slack, MCP, and First-Party Agent InterfacesWalden [00:25:42]: Well, I'm curious, what is, the most common thing that people end up requesting, that they still need on top of OpenInspect when you help them go implement it?Cole [00:25:52]: I think a lot of it comes down to actually integrating it into the company. It's one thing to have the background agent system set up, but if it isn't actually integrated into your larger ecosystem, it isn't that useful. It is useful to be able to kick off sessions, but what we really want to be able to do is hook it into all of our other systems, whether that is the production database with read-only credentials, the logs, a Confluence or internal knowledge-based system. I think that is where I see the huge leap for companies, and that can be a challenge for companies as well who are maybe not familiar with exactly how to approach it, especially if they're in environments that have more compliance type things where, access control can be pretty big and how do you deliberately think about these problems, I find to be, one of the problems that comes with a system like this.Walden [00:26:46]: The thing we found is So, MCPs, obviously it has been like this, really big explosion of, oh, you can go, integrate it with all these different things. But to actually get the integration right and the and get the right experience, oftentimes we found that we had to go build our own ad hoc things. I think Slack is a great example of this. You could give your agent a Slack MCP and okay, it can post messages back to you on Slack. But we actually use Devin like a coworker in Slack, and that's how it's been built from the ground up. But to do that, you actually need to, support webhooks that come back, right? And then Devin has to respond in a natural way and then hopefully don't spam your threads too much and annoy the people in your company. So you got to tune that experience just right. Especially when there's a lot of back and forths, we find that we actually have to go beyond the simple MCP integrations in these places.Swyx [00:27:39]: I just pulled up the MCP marketplace. I know this is a Fair amount of work. Is the answer to eventually take first party control of all the top MCPs? Is that theWalden [00:27:48]: I would love a world where you could have something that's more expressive than MCP. That, goes both ways, not just a set of tools, but a proper system that interacts back and lets it Have the right experience with all these interfaces.Swyx [00:28:03]: So there actually is sampling in the MCP spec, but nobody Uses it, right?Walden [00:28:07]: And so I think that's the other part is, actually we found that when the MCP spec starts to get too complicated, it starts to lose its original promise of Being like a simple one-step connect. Now then we have to go figure out how to support all these different variations of things and It starts to look a lot like just building the first party integrations in a lot of these cases now.Cole [00:28:29]: I think it matters, too, how critical it is to your company, right? If this is something that nearly every session is going through, it probably makes sense to own it so that you can make optimizations on top of it Versus just whatever is off the shelf.Swyx [00:28:43]: Awesome. Other than MCPs, what else, sorry, well, I don't know if that's Narrowing in too much on, integrations. But what else? What other elements of building OpenInspect or Devin that you guys really sink on?Memory and Knowledge: What Agents Should RememberCole [00:28:59]: I think, a problem that comes up very frequently is this idea of memories or knowledge base.Swyx [00:29:05]: Oh, boy. How do you solve it?Cole [00:29:08]: so not solved yet, is the short answer.Cole [00:29:11]: it's something, there's a open issue for it, someone asking about it.Swyx [00:29:16]: There's, I, D Wiki hasn't indexed anything about memory yet.Cole [00:29:20]: how I'm seeing it solved across my clients is primarily through skills. I find that skills can be a good gap within that or updating Claude MD, but I think memory as a whole is a pretty unsolved problem, and it is why I've been hesitant to add it. I think there is parts of memory and that can be addressed, but I think as a whole it's a very difficult retrieval problem.Swyx [00:29:44]: Oh my God. RAMP didn't write anything about memory? I see zero search results.Walden [00:29:50]: No. Memory can be quite tricky to get right because it's the retrieval, but also the generation of the memories that can be really tricky. You don't want it to just like Remember very specific details.Swyx [00:29:59]: Walk us through the Devin memory journey because I know there's been a journey.Walden [00:30:03]: the first version of memory that like stuck around for a while was A system we have called Knowledge. And the idea was we wanted it to pick up things over time and not need the user to be proactive about teaching Devin things. So, okay, any time you remind Devin, “Wait, no, that's not quite the way you're supposed to use Git”Like, we actually want Devin to say, “Hey, do you want me to actually just remember this for the future?” And for you to just basically quickly approve or reject and for it to build up over time. ‘Cause I find that, 95%, I think, or some crazy stat like that of the memories that Devin has are all through these auto-generated things. Very few people actually just want to sit down and write big docs on Here's how you're supposed to work with the technology, et cetera. The generation and the retrieval has been something that we've been trying to tune a lot over the years. Generation, you don't want it to remember something like, if you asked one time to like, “Oh, please open as a draft PR,” you don't want to be like, “Oh, everyone forever now should get their PRs as draft PRs.” But you do want some, conveyor. Maybe you want to say like, “Oh, Cole generally likes, things to be created as draft PRs.” Same with retrieval, if you have thousands of these memories, how do you actually make sure they're retrieved at the right time? And that can be quite tricky to do right without exploding the context with a bunch of useful yeah, useless information. Surprising amount of just, eval work to just make sure that, memory is, remains a reliable system as new models come and go.Cole [00:31:31]: Do you have anything that you could share on, memory pruning? And like the temporal aspect of memory?Swyx [00:31:36]: Deleting and forgetting?Walden [00:31:39]: The, today, the, So the things they could do is it could edit memories. And so if your memory used to say like, “Oh, Cole likes to open everything as like a draft PR,” then you can imagine, “No, don't do that.” And then it'll say, “Oh, do you want me to update the memory to be Cole now want everything as, open PRs?” I think that at the same time we don't know if this is going to be the final version of the system. Whatever we have here will probably, translate into the new system that we'll be coming up with. But I think one big difference between two years ago and today is these agents are really good at using anything that resembles a file system natively. And so part of us are, is thinking, “Oh, should we rebuild memories to feel more like a file system that we let the agent navigate on its own?” That's been an interesting exploration. Also similar ideas in the scale space.Swyx [00:32:35]: I am pulling up OpenClaude's memory thing right now. So memory, OpenClaude has like this like daily memory journal thing, right? And you can I mean, that is a file system you can grep through and is a source of truth. I don't know if it's the best. It's probably super noisy, but at least, if you lose something you can discover it or you can apply some, forgetting algorithm to, more ancient memories that don't get recalled again or something. I don't know.Walden [00:33:01]: One thing we've been trying to do to push the boundaries of how you use agents at your company is letting an agent basically have a very similar file, a memory.md or something, and just like be your permanent PM for a specific set of issues maybe. So we have like some Slack channels internally, maybe a Slack channel dedicated to, a specific product like DeepWiki maybe. And you can imagine that, or you want a Devin that never stops, it's just always awake, but it has this like memory dock that it can just maintain for itself about, okay, what are like the number one priorities of what we have to fix and prioritize? Who is responsible for some upcoming work? Maybe they'll even Devin will even tag you on some recurring basis. And so it's been an interesting move to see, okay, how can we actually use Devin for more than just engineering? Can we actually upstream above the engineering process and maybe it's just Devin creating tickets, which then maybe some humans do, but then maybe other Devins do.Swyx [00:34:00]: One of my more fun automations is go research competitors and just suggest stuff to me on a weekly basis. That's the automation. I can't find it right now, but basically it just like, “Look at competitors and suggest things.” “And here are three things that you've suggested that I don't want any more of,” and you just stick that in the prompts. But like I wish actually So for like when I, for example, when I reject a PR, I wish that it updated memory so that I can then just not have to go up, go back and update the scheduled, sync, but anyway, feature request.Walden [00:34:31]: what? We might change it soon. I guess OpenInspect, in the time you've been around, has there been anything you tried to implement but then you had to like undo and like do a different way?OpenInspect Architecture: Webhooks, Control Planes, and Agent StateCole [00:34:41]: Nothing yet, but something that is on my mind. The initial way that I built it was that each of the integrations lives as its own package. And so you have The Slack bot, which is what's handling the webhooks, and then is basically interacting with the control plane. As I'm seeing the system starting to be more integrated, specifically with the GitHub bot integration, I'm considering bringing that all into the central control plane because especially now I want to start, And a request that I'm getting is the ability to monitor, the actual, pull requests being merged, as well as just tracking ofSwyx [00:35:19]: What do I have open?Cole [00:35:21]: What do I have open? How many of these are getting merged? How many comments are showing up? To just understand the health of the system. And so in the case of a GitHub app, you only have one webhook. And so then it's a question of do I put that webhook in that GitHub bot package? That's weird. It doesn't really make sense to live there because that package is more for like the code reviewer. Or do I like centralize it? So that's something that's on my mind of, making that decision. I think the other one we touched on earlier is the harness in the box versus out of the box. I think long term the architecture will eventually come back out of the box. Some of the newer tools that I've added are calling back into the control plane so that you don't have the secrets in the sandbox. And so I think long term I probably will pull the actual, agent out of the box, but I think for now it's fine.Subagents and Multi-Agent Systems: When Parallelism Helps or HurtsSwyx [00:36:16]: Just, a quick question on pulling the agent out of the box. I'm One thing I'm very bullish on this year is agents calling other agents or spawning sub-agents or Whatever you want to call it. Does that make it harder or easier? I can't tell. Because if the harness is in the box, you can just spin up more boxes. If the harness is outside the box, then you're, it's less easy because you are, you have a unicorn pet of a, of a harness that's, living outside the box.Cole [00:36:45]: In theory it would be the same way, right? Whether, one agent has launched many, sub-sessions within it, OpenInspect, for example, can launch sub-sessions and actually create other environments and then monitor them. In the case where it is out of the box, that would basically just be an additional session that's running. And so that session is also running outside of the box. It's running in your worker plane, wherever you're running this. And then you really just have to think about how does your top level agent then interact with it. I do think it can be more complex, just ‘cause again, you have now a more difficult architecture. But I think if you figured it out once, it's probably fine.Swyx [00:37:26]: Well, then I'm just, throwing it open to you in terms of, I call this like meta Devin management. Which is like the, Devin's calling Devins or Devin scheduling Devins or querying trajectories or anything like that. What have you built or unshipped, anything?Cole [00:37:46]: I think one of the surprising things we've seen is that a lot of the ways that, these, separate agents work with each other, and you want them to, parallelize their work, has still mostly followed the same manager sub-agents regime. And a lot of people I think are excited about this world where you have swarms of agents that, talk with each other all over the place. We've actually given Devin an MCP so they can just go arbitrarily message other Devins And create new Devins, et cetera. But I guess, it somehow creates, a really chaotic world in that sense. And so we've still found that most practical use on a day-to-day basis has been one single Devin.Cole [00:38:33]: Figuring out how to segregate the work and get, have other Devins work on it in, a relatively isolated sense, each with their own boxes Not sharing machines, so there's, a very little room for conflict is the regime that you have to create today.Swyx [00:38:50]: I'll call out, the experiments from Cursor, right? This is Wilson Lin's work on Single agent to multi-agent, and you're obviously famously on the side of don't build multi-agent. But they went through the whole thing, only to arrive at, this Which is exactly what Devin has, I think.Cole [00:39:08]: I think there will be a revision to that post at some point AboutSwyx [00:39:12]: Tell us about itCole [00:39:12]: I think multi-agents were very much not at all possible a year ago. You do see more multi-agent experiments today, but you can argue, are they really multi-agents, or are they just just, tool calls,? There are people who, will create sub-agents to go look for XYZ file, XYZ implementation. Has really nice context management benefits because all of the tool calls and tokens that it spends then get collapsed back to just the answer for the main agent. There's a lot of benefits to doing this. We basically have Devin do this with Deep Bookie, make a call out to Deep Bookie, give you back the results, but that feels like a tool call,? It's not like these, two collaborators actually talking back with each, back and forth with each other. But I think the thing that gives me the most bullishness that multi-agents might actually be possible is actually what I said earlier about Devin will actually sometimes tell me I'm wrong and push back, and I think that demonstrates a level of maturity and communication today that makes a multi-agent world possible. One, can two agents who have seen different information come back to each other and actually figure out who is right, what is the correct implementation? They're not just, yes men. Claude, I guess is like, used to just say, what is it? “You're right,” or,Swyx [00:40:25]: “You're absolutely right.”Cole [00:40:26]: “You're absolutely right.” Yeah.Swyx [00:40:28]: The Have you seen, did you seeCole [00:40:29]: The age is overSwyx [00:40:30]: The Codex app troll in Topic? This is the Codex app. Inside of Settings, there's a little, there's a little Easter egg, right? So if you go to, the Themes or Appearance, right? There's all these, color codes, and the top is absolutely, and it's the Topic's colors. Which is such a troll. Anyway.Model Behavior: Pushback, Adversarial Prompts, and Agent SkepticismCole [00:40:53]: I love that Easter egg. Did you discover that yourself?Swyx [00:40:54]: No, it was, someone was, tweeting about it And I was like, I was like, “Is this true?” Because, sometimes people just tweet stuff to, get a rise out of you. But yeah, there you go, in Topic colors.Cole [00:41:06]: Yeah. So yeah, we're out of this regime where, it just says you're absolutely right, and they can have real conversations and real back and forths.Swyx [00:41:13]: You can prompt it as well to be more adversarial or whatever. Yeah. Okay. Yeah, that, I mean, to me, that is more intelligence, right? That is not just something that's, a dumb tool, it's actually pushing back on you I think. Yeah.Cole [00:41:24]: when you mentioned, of course, the blog posts. There was one blog they had where they fed a swarm of agents together and built a browser.Swyx [00:41:34]: That was I think that was the one.Cole [00:41:36]: You can have, likeSwyx [00:41:37]: I think it's the same oneCole [00:41:37]: Creation of it. We found a surprising success of, don't do a swarm or anything, just have one Devin, it does its own context management. Just let it keep running for a while and give it some crazy tasks. I think we asked it to, rebuild, a Windows OS system. And it managed to do it just like, going on for long enough. It'sSwyx [00:41:55]: Was this Andrew's thing?Cole [00:41:58]: there were lots of demos that we ended up not posting, ‘cause at some point we'd just be posting way too much a bunch of, Demos. But I love that because it shows that I think the multi-agent thing still has, a bit of exciting sexiness to it, which is maybe still beyond still, the actual delta it adds to the capabilities of these systems. But it's absolutely the future. I think we're heading in that direction and we can see the progress being made there already.Swyx [00:42:25]: If I were to, make one super minor pushback because I don't feel that confident about it yetCole [00:42:33]: Go for itSwyx [00:42:33]: But I've had Ryan Lopopolo from OpenAI on the pod And he's a super slop cannon, right? Oh my God, that's my coding agent being done. I downloaded this, Peon Ping. I don't know if you guys have heard this. It takes like-, sound packs from popular games like, Command and Conquer and Warcraft, and then it plays it whenever it's done. And so it's like, “Work,” or whatever, “At your command,” or something. Anyway, what I got from the Cursor code base and from Ryan's thing was that there's a slop cannon approach where you try to loosen the single agent's, bottleneck, and I feel like that is, probably an, a very important thing to try to figure out. I don't think anyone's, really solved it. Because then you just have more reviewer slop on top of the agent slop To try to wrangle it all. Ryan will probably very strongly object that I say that he hasn't solved it, but he thinks he's He thinks he's completely solved it. But I think it's still I think it's, very important, ‘cause, that is a bottleneck, right? I feel Devin is slow sometimes Because I'm like, well, yeah, this is very readable and very sensible, but also it is slower than it could be if I just, I want a button to just say, “Just ramp this up 1,000 next parallel, in parallel and just, see what happens,”? And I don't know if that's, feasible at some point in the future.Code Review, Entropy, and AI SlopWalden [00:43:55]: I And we've also run experiments internally where we've basically tried to build entire products, true products that we knew we would eventually ship, but for now, let's try to see if we can do it just by purely, vibe coding on top of each other, auto merge, no code review at all. And then there's this benchmark of how many weeks can you go onto this for Before you say, “We have the trashiest code base.”Walden [00:44:18]: “Let's actually rewrite it from scratch.”Swyx [00:44:19]: Start a new factory, yeah. What'd you find?Walden [00:44:21]: I think we found that the state-of-the-art in December was you can probably, run this for about two weeks. By the end of those two weeks, you'd find that, hey, you want to, change the color of a button. Well, it turns out this button is implemented in, 10 different places, and they, have All these different variations, and oh, you forgot one of them, and actually it's a slightly different color in one spot. And you're like, “Okay, this is too much to work with. Let's actually try to do code review at the same time.” And make sure that we're on top of our software, actually cleaning it up a bit And making sure it's done in a scalable way.Cole [00:44:54]: I think building on that, the idea of, you don't have to look at code, I think is generally a bad idea. And the meme that I have for thatWalden [00:45:03]: What timeline, all right, is Do you think that statement will be true on?Cole [00:45:06]: I think probably for a while it'll be true that you should continue to look at your code. A problem that I see a lot of teams run into that I work with who are embracing AI native, AI first coding, is The meme that I have is that your code base regresses to your worst engineer, because that engineer who is, very gung-ho about AI and is not auditing their code, their pattern starts cementing into the code, and now the AI is referencing their patterns. And so now their if/else block that, is 20 if/elses back and forth, the AI is seeing that as the pattern of how things are done and starts to then exponentially grow this slop. And I find to your point, a pretty good approach to that is having scheduled cleanup, whether by humans or through systems, that are looking for duplication. They then address that. You'll end up with like 12 helpers for how to format a date. And you need to address that, because otherwise it will continue to sprawl.Swyx [00:46:09]: Within balance, I think it's fine to have some duplication, and then sometimes To have garbage collection, right? Yeah. The What I've been, talking about with a lot of engineering leaders is that you want to be very strict about the boundaries between modules, and it's your job as an architect, as a CTO, whatever, to say like, “Okay, here's the hard contract between you guys and you guys. Whatever you do inside this black box is your business. You do whatever. But between these guys, let's be, really damn clear, and any movement must be signed off by a human or me,” or. Then, and like that's that. I don't know if you have any other modifications or advice.Walden [00:46:44]: Well, I guess generally on the topic of, where humans can be useful, I found that ‘cause, some of these, really deep infra problems, sometimes just having a human that just has, really deep expertise can make a big difference. I've actually seen this come into play when actually building agents. So we've had a few friends now, try building their own coding agents, and I think one same problem that I recurringly heard a lot of them run into was this problem of like, “Oh, Grep is really slow on our agents' machines.” And so a lot of them, I assume because they're using AI and they themselves don't have, super deep infra background knowledge, say, “Okay, we're going to go build our own custom Grep index. It's going to be really fast,” and use that as a way around this problem. When we ran into this problem About like, maybe like a year and a half ago when we were, in the early days of building Devin, we obviously didn't have AI then. We just asked our, how to, how to do this. You can just swap out a new Grep index, so.Infrastructure Details: Grep, File Systems, and SandboxesSwyx [00:47:45]: What do you mean you hand-coded Devin? What?Walden [00:47:48]: It's like, can you believe we hand-wrote this code? And we had, our infra people who are really amazing, they were looking into it and they're like, “Oh, what? We realized that actually the root cause of this problem is actually super simple, but like fine-grain detail,” which is that a lot of these virtual machines actually underlying them don't use real file systems. They use these, network file systems where things are actually cached over the network actually in S3. So when you're Grepping, you're actually making network calls Every time you're doing these things, and that's why Grep is extremely slow on these machines. And so again, goes back to, what is all of the crazy infra work that we had to do to actually get these machines working. If you try to do this yourself, there are tons of small details like this, and so we had to eventually go swap out that network file system. ButSwyx [00:48:35]: I think there's a write-up about it, right? Silas did one about the virtual file system.Walden [00:48:38]: Oh, that was a whole other thing. TheSwyx [00:48:39]: Oh, that's a different thingWalden [00:48:40]: The BlockDev file storage formatSwyx [00:48:42]: I'll bring it upWalden [00:48:42]: Which is, a file system format that we built so that the VMs could be spun up and down very quickly. Basically, the intuition behind this is-Imagine you have, a terabyte of disk, and your agent only, wrote, a hundred lines of code on top of that disk. How long does it, say, take to, save and re-bring up that disk? And most systems, because you're not optimizing for this case, it's just, on the order of a terabyte of work because you have to Save all of that and bring it back up. In our system, we try to build a file system that incrementally builds on top of each other. So every time you save and bring the machine back up, you're only doing work that is proportional to effectively the diff in the file system. And so this, shaves off a lot of time in the boot-up process of Devin. I think we This is actually now outdated. We have a newer system inside of Devin. But yeah, there's a lot of tiny details you have to get right here to actually get the day-to-day experience of Devin to be good.Swyx [00:49:39]: It's, not technically agents, but it is agent infra, and when you sell an agent as a company, you sell agent plus agent infra.Walden [00:49:46]: At least the way we do it be And the other The nice thing about having the agent infra being done together is, you We get to deploy Devin in whatever environment we want now. We don't need to wait for some underlying infra provider to also go and support VPC or on-prem or FedGovCloud, for instance. So we can actually go and figure out, okay, since we own the infrastructure, how can we get that set up for you?Cloud Providers: Modal, Daytona, and Enterprise SandboxesSwyx [00:50:12]: Whereas you're Cloudflare dependent.Cole [00:50:15]: so Cloudflare runs the control plane. The sandboxes, Modal is supported. A contributor just added Daytona. E2B is on the roadmap, and I think there's an abstraction in place that if any contributor wants to add a new provider, they can add that in.Walden [00:50:32]: Well, what are, How are the customers you work with Do they generally try to then go set up a contract with another one of these third-party providers? Do they try to do the VMs in-house?Cole [00:50:44]: most of them I see using Modal. I think Modal has a greatWalden [00:50:48]: Shout out Modal.Swyx [00:50:48]: Shout out Modal.Cole [00:50:50]: I think Modal has a great offering. It captures all of the sandbox pieces you need, snapshots being a pretty big piece of that, and given that they also offer GPUs, I think it's a pretty nice offering as a whole.Swyx [00:51:04]: no debate there.Walden [00:51:07]: Modal is great, especially, I think their container offering is, the most natural, and so especially if you are willing to, forego, the full VM requirements Modal is, a really vast place you can spin something up on.Swyx [00:51:20]: Is there a point So Modal's very Python, and I feel like most workload, has really shifted to JavaScript. I don't know if you guys Get the same feeling. So, okay, when I started Landspace and IE and all these things, I was like 50/50 Python and JS, right? That's roughly. I think that's wrong now. I think JS has won. I don't know if you guys Like, I Maybe I'm overstating it, and maybe for cognition, there's, C# and Java and what have you. But for, new greenfield apps, do you feel that Do you get that sense? Does it matter?Cole [00:51:52]: I think that most of the libraries that I see in this space are Python native first, especially in theCole [00:51:58]: Observability space. That said, I think that there is a pretty big appeal of having your entire system in one language. Especially when you have both your frontend and backend communicating, you can have one central type Which is very nice.Swyx [00:52:11]: That's my case against Modal, which is Then you have to run JS. You can run JS inside Modal. It's just, one extra step That, isn't native to the runtime. I don't know ifWalden [00:52:22]: I don't knowSwyx [00:52:23]: Reviews. Do you have numbers? I don't know.Walden [00:52:25]: the one thing I don't like about Python is whenever AI, whenever it writes Python, it always does, the weirdest patterns, andSwyx [00:52:32]: Oh, because it's, mixing two and three or what?Walden [00:52:34]: I think it's something mixing two and three, yeah. The I don't know if you see this. It always tries to do, has attribute on objects as likeCole [00:52:41]: Oh, my God.Walden [00:52:41]: But it's like But that you shouldn't be doing that. It should error if there wasSwyx [00:52:45]: Because it's training on library code?Cole [00:52:47]: I think it's more of, likeCole [00:52:48]: From what I've seen, it's more of, a reward hacking mechanism where it doesn't want to basicallyWalden [00:52:54]: It'll never error.Cole [00:52:54]: It doesn't want the code to fail. And so it Even when it knows it has the attribute, it'll call getattr on a, and for a lot of my clients who have moved towards more autonomous coding, we've put that in as a lint rule That if you do getattr, your pull request is going to fail.Slop Signatures: Comments, Backwards Compatibility, and TypesSwyx [00:53:12]: Ooh, this is a fun topic. Can you tell me more about this? What else is a sign of AI coding that you have to put guards in?Walden [00:53:21]: So we were talking just before this about Opus 4.7. One of the things this new model likes to do is it writes lots of comments. Not like, it'll, comment every line, but it'll write, paragraph, PRDs, on top of every function. But I will say, to its credit, these aren't slop, descriptions like they were before. “Oh, here's what this function does.” It's like, “Oh, here's actually the r

Pan Global Resources CEO Tim Moody discusses the company's growing copper and gold portfolio in Spain, led by the Escacena Project and its La Romana copper-tin-silver resource. Moody outlines the strategy to scale La Romana from a 36-million-tonne starter resource toward a larger VMS cluster, supported by newly won ground at Escacena South. A strategic investment from Alpayana boosts funding for a 20,000-meter drill program across multiple targets, while the Carmenes project in northern Spain adds early-stage gold upside.

 Interview with Gary Lohman, COO & VP Exploration, and Patrick J. Cruickshank, President & CEO of Thistle ResourcesRecording date: 20th May 2026Thistle Resources Inc., a recently listed explorer on the TSX Venture Exchange, is positioning itself at the crossroads of rising demand for gold and critical minerals through a diversified portfolio in Canada's Bathurst Mining Camp. The company controls five projects, with a strategic focus on three key assets: the Middle River Gold deposit, a large volcanogenic massive sulfide (VMS) target, and the high-grade Brunswick Antimony project. This multi-commodity approach reduces reliance on a single resource while offering multiple pathways for value creation.The flagship Middle River Gold project demonstrates strong scale potential. It hosts two distinct zones: a near-surface system extending to 130 meters depth with approximately 7 kilometers of mineralized folding—largely untested—and a deeper zone at 400 meters that exhibits one of the strongest geophysical conductive responses recorded in the region. Early drilling has confirmed consistent gold mineralization, while advanced surveys by two independent geophysical firms have significantly improved targeting confidence. The company is aiming to define a resource of up to 2 million ounces through systematic drilling.Equally compelling is the Brunswick Antimony project, որտեղ exceptionally high-grade mineralization occurs at surface, including antimony exceeding 10%, along with significant silver and gold values. Located near historic producing mines, the project benefits from existing infrastructure and growing geopolitical interest in securing non-Chinese sources of critical minerals. Antimony prices have surged in recent years, enhancing the project's economic potential even at modest scale.Operationally, Thistle benefits from a favorable jurisdiction with rapid permitting, strong infrastructure, and low drilling costs of roughly CAD 100 per meter. Fully funded for two years and equipped with active drill programs through 2026, the company is well positioned to advance its assets. With multiple catalysts ahead and exposure to both precious and critical minerals, Thistle represents a diversified exploration opportunity in a proven mining district.View Thistle Resources' company profile: https://www.cruxinvestor.com/companies/thistle-resourcesSign up for Crux Investor: https://cruxinvestor.com 

Take the 2026 AI Engineering Survey and get >$2k in credits and AIE WF tickets!On the product side, everyone is getting Computer - Perplexity, Manus, Cursor, and so on. Meanwhile on the research side, agentic evals like TerminalBench and GDPVal are also assuming computer (Harbor). On both ends, the consolidating LLM OS stack has become a standard toolkit, and Daytona is one of a small set of AI Infra companies that are booming because of it.“The end of localhost” has been Ivan Burazin's obsession for more than a decade.Something that is all too familiar…Long before agents became the default way people talked about software development, Ivan was already chasing the idea that development should not depend on a fragile local machine. CodeAnywhere, one of the first browser-based IDEs, was an early attempt at that future: move the development environment into the cloud, make setup reproducible, and free developers from the endless “works on my machine” tax.The thesis was directionally right, but the market wasn't ready yet.However, agents changed that. They do not care about a laptop, desk setup, or favorite editor. They need a computer they can access through an API: something stateful enough to keep working, fast enough to spin up instantly, flexible enough to resize, isolated enough to be safe, and composable enough to run the messy real-world workflows that real software engineering actually requires.Daytona isn't just selling “sandboxes” in the narrow code-execution sense. It is the latest version of Ivan's original localhost thesis.In this episode, Daytona's CEO joins swyx to explain why AI agents need more than code execution boxes: they need composable computers, stateful sandboxes, instant startup, dynamic resources, and infrastructure that can survive workloads going from zero to 100,000 CPUs.We go deep on the new agent compute market: Daytona's hard pivot from human dev environments to AI sandboxes, the New Year's Eve MVP that customers begged for, why Daytona runs on bare metal with its own scheduler, how one customer runs almost 850,000 sandboxes a day, and why RL/eval workloads went from 0% to roughly 50% of usage in just months. Ivan also explains why agents need Windows and macOS machines, why CLI may matter more than MCP, why Kubernetes is painful for this workload, and why the future AI cloud may look more like Stripe than AWS.We discuss:* How Daytona grew out of CodeAnywhere, Shift, and the “end of localhost” thesis* Why Daytona pivoted from human dev environments to AI sandboxes* Why agents need composable computers instead of disposable code execution boxes* The New Year's Eve MVP that customers chased API keys for* Why Daytona chose bare metal, stateful snapshots, and its own scheduler* How Daytona spins up one sandbox in ~60ms and 50,000 sandboxes in ~75 seconds* Why Daytona's biggest customer runs ~850,000 sandboxes a day* How RL/eval workloads create zero-to-100,000 CPU spikes* Why RL workloads went from 0% to roughly 50% of Daytona usage* Why customers compare Daytona against EKS/GKS and say they're “never going back”* Why every AI agent may need a computer, including Windows and macOS environments* The Apple licensing constraints that make macOS sandboxes hard* Why CLI gives agents more power than MCP* How open source helps agents integrate Daytona* Why agent-generated PRs may break today's CI/CD assumptions* Why AI SaaS companies reselling tokens may face a cold shower* Why the AI cloud may look more like Stripe than AWSIvan Burazin* LinkedIn: https://www.linkedin.com/in/ivanburazin* X: https://x.com/ivanburazinDaytona* Website: https://www.daytona.io* X: https://x.com/daytonaioTimestamps* 00:00:00 Hook* 00:01:12 Introduction* 00:03:15 CodeAnywhere, Shift, and the end of localhost* 00:05:58 What Daytona is: composable computers for AI agents* 00:08:07 The pivot from dev environments to AI sandboxes* 00:10:17 The New Year's Eve MVP and customers begging for API keys* 00:12:56 Bare metal, stateful sandboxes, and Daytona's scheduler* 00:17:28 60ms startup, 50,000 sandboxes, and 850K daily runs* 00:21:53 Spiky RL/eval workloads and the new agent infra problem* 00:28:12 RL workloads, Kubernetes pain, and dynamic resizing* 00:33:31 Why every AI agent needs a computer* 00:38:48 macOS sandboxes and Apple's licensing problem* 00:44:28 Why CLI may matter more than MCP* 00:48:11 Open source, GitHub stars, and agent integration* 00:53:11 Git, CI/CD, and agent collaboration bottlenecks* 00:58:15 Founder life and building a 25-person infra company* 01:02:44 AI SaaS, token resale, and API-first business models* 01:06:10 GPU sandboxes, data centers, and compute growth* 01:09:48 Why the AI cloud may look more like Stripe than AWS* 01:11:26 Closing thoughtsTranscriptIntroduction: Daytona, CodeAnywhere, and the End of LocalhostSwyx [00:00:02]: Okay, we're in the studio with Ivan Burazin, CEO of Daytona. Welcome.Ivan [00:00:07]: Thanks for having me, man.Swyx [00:00:08]: Ivan, you and I go back.Ivan [00:00:10]: Way back.Swyx [00:00:11]: How I don't even know how, you found, did you reach out or, for Shift.Ivan [00:00:17]: I reached out to you. The reason was you - we were just - we were thinking about I was one of the co-founders of CodeAnywhere, the first browser-based IDE, and so we were thinking a long time of, localhost should die. And you had this article.Swyx [00:00:29]: End of localhost.Ivan [00:00:30]: Then I reached out to you because of that, and then we talked, and I was actually at a different job and learning about I was the head of, developer experience, and you were quite well-versed in that, and I actually reached out to you, among other people, how do we go about that? What are the key things and whatnot at this point in time? And you were nice enough to take the call, and I remember I was late on your call with you.Swyx [00:00:51]: I don't remember.Ivan [00:00:52]: I remember because I was with my then I'm thinking of a girlfriend or wife at that point in time, I'm not sure. It's the same person, so that's great, and I was late ‘cause we were, in, Italy on, vacation, and then I was late for something. I felt so bad, and you were so nice to be, good about.Swyx [00:01:10]: The reason I'm nice is because I'm also late to other people, so it's like, who's, who's without sin here, yeah, so I have to, for those who don't know, InfoBip Shift, there's this whole thing that, you did in the past, and, and that was basically one of the inspirations for me starting AI Engineer, which is like, I have to thank you for giving me that push to be like, “Oh, you can, you can build and sell conferences?”Ivan [00:01:34]: I remember you asked you asked me at the beginning to give me advisory shares, and I was so focused on what we were doing, I said no, and I should've took the advisory shares. So I'm sorry, dude. But anyway.Swyx [00:01:43]: We're not, we're not venture backed.Ivan [00:01:44]: No, it doesn't matter.Swyx [00:01:45]: It's Yeah, anyway, so I think what's impressive about you is that CodeAnywhere is the thing that you've been trying to build, and, you kind of put it on hold and then came back after InfoBip. Just give us the story, do you - the story and the origin story, going into Daytona.From CodeAnywhere and Shift to DaytonaIvan [00:02:05]: Sure. Like, really way back, me and my co-founder have been together. I say this, I've said this multiple times, it's like we were married and divorced and married. Some people actually ask me is my co-founder my partner. they thought it literally. It's not literally, but we have done multiple companies together, and to your point, we had this shift where we went from the CodeAnywhere to the conference called Shift, and then back to, Daytona. We originally started stacking servers, doing like virtualization in the early 2000s and, routers and doing basically all these things, at a foundational level, and that was a services company which we sold to focus on what my co-founder actually invented, which was the very first browser-based IDE, right, I say the first. Before us was actually Heroku. They did it for a very short time until they became Heroku. But outside of them, we were the only one, and it was called.Swyx [00:02:55]: There was Cloud9.Ivan [00:02:57]: Cloud9 came out slightly after us. There was Replit, which came out when we stopped doing it, Replit came out, and they have been successful since then, which is great. There was Nitrous.io. There was quite a few that existed at the time, but it was like too early. But the interesting part is that we, at that point in time, because there was no VS Code, there was no Kubernetes, and Docker had just started when we Or I'm not sure if it was even public at that point in time. And so we had to build everything to the whole stack ourselves and that was the key learning that we brought into and that we've been using in Daytona today. So it was super early. There's about 3 million people used CodeAnywhere. It was slightly, it was angel-backed more than venture-backed. We ended up paying everyone back because it didn't have that sort of scale. But, three years ago, we started something similar with Daytona, which is not what we are today, but it was automating dev environments for human engineers, the basically the underlying stack of CodeAnywhere. And then we did a hard pivot last January to sandboxes. And so here we are.Swyx [00:04:01]: Historic pivot, yeah, and, it's one of those things where, I had independently invested in CodeAnywhere, but also in E2B, and then both of you pivoted into the same thing, and I'm like, “F**k.”Ivan [00:04:12]: You invested, you invested in Daytona. You invested in Daytona. But you were the first If we had not got your check, we wouldn't have done it.Swyx [00:04:18]: No way.Ivan [00:04:19]: No, it was like, “We have to get him on board first,” and you were that kicker that we, that got us off the ground.Swyx [00:04:23]: No, because you were putting me on your pitch deck, man. I was like, “Man, this is like a good trip if I don't invest.”Ivan [00:04:29]: That's because it was your quote. It's like we.Swyx [00:04:30]: Yeah. It's the end of localhost.Ivan [00:04:31]: Did a bunch of research about end of localhost and who was interested in that,.Swyx [00:04:34]: No, that's like, I put, I wrote that blog post, and every single company in that field reached out to me, and then every VC who was receiving those pitches then also had to call me and, talk it, talk through it with me.Ivan [00:04:47]: It's finally happening though.Swyx [00:04:48]: It was really super interesting.Ivan [00:04:48]: It's finally happening.Swyx [00:04:49]: It's finally happening.Ivan [00:04:49]: Yeah, it's finally.Swyx [00:04:49]: It's finally happening, with maybe sort of non-human users. Yeah, so what is Daytona today? Let's get like a quick description. I'm wearing the shirt.What Daytona Is Today: Composable Computers for AI AgentsIvan [00:04:58]: You're wearing the shirt. Yes,.Swyx [00:04:59]: It says, I think your branding is very good. Like, it's very consistent. It runs AI code. Like, it cannot be simpler.Ivan [00:05:05]: Exactly, but we're gonna probably have to change that.Swyx [00:05:07]: Oh, s**t.Ivan [00:05:07]: It's also a subset of what we do. Unfortunately, we really love this, Run AI Code is super simple. People interpret it different ways. I think we've given out 5,000, 6,000 of these shirts. People wear them with pride because it doesn't really market about us.Swyx [00:05:21]: Yeah, Daytona's on the back.Ivan [00:05:22]: It markets the back. It markets to the person itself, so I think we did a really good job on that one. But it is also a subset of what we do, because people, when they think about Run AI Code, they just think about these small, let's call it isolates, code execution boxes that, you send some code, you get an output. Whereas what Daytona is today is essentially composable computers for AI agents. It is, the market calls them sandboxes which can be misleading.Swyx [00:05:44]: All these things. All these things on.Ivan [00:05:45]: Yeah, exactly, ‘cause it can be misleading ‘cause people usually think about sandboxes as a demo or a test environment versus a production-grade environment. But what Daytona does, if you think of the laptop that you have in front of you or the computer that's over there, or, my wife is an architect, so she has like a Windows with a 3D graphics card inside to do 3D rendering. Like, as humans, we have different computers or different compositions of computers. And our belief is strongly that agents today and going forward will need all these different compositions of computers to do different types of tasks. And so we offer that basically through an API.Swyx [00:06:19]: Yeah, to give people - I'm trying to sort of front-load all the aha moments or the wow moments so that people can, stay engaged and click like and subscribe. the market is exploding, right? Like, you have been reporting 74% month-on-month growth, and it also, it's just been growing for a while. Like, it's been going like this. And every single - It's not just you guys. It's every single.Ivan [00:06:41]: Everyone, yeah.Swyx [00:06:42]: Sort of, compute provider. I don't know if you agree with me saying compute provider or not.Ivan [00:06:48]: It's fine.Swyx [00:06:48]: Yeah. So like organically PLG-driven growth, but also enterprise is doing super well, I think I wanna rewind to January of last year when you did the pivot. Like, so you obviously called this market early, and you were positioned for it, and you are now one of the market leaders. But what was the insight that made you do the pivot?The Pivot: From Human Dev Environments to Agent SandboxesIvan [00:07:06]: The insight that made us do this pivot is the quarter before that, so end of 2024, when we had - Basically, we did a demo with - I don't I think we discussed this as well, Devin was not public. You actually gave me access to Devin at that time. So Devin.Swyx [00:07:25]: I did?Ivan [00:07:26]: Yeah, you gave me access.Swyx [00:07:26]: I don't think I was supposed.Ivan [00:07:27]: Yeah, exactly.Swyx [00:07:28]: Yeah, I.Ivan [00:07:28]: So it doesn't matter. You.Swyx [00:07:29]: Yeah. I gave like three friends access.Ivan [00:07:31]: Yeah, or it was a call and you showed it to me. It doesn't matter. but OpenDevin was available, which is now called OpenHands. And so we're like, “Oh, this seems to be a thing. This is not public. Let's take our for human automation of dev environments and take, OpenDevin and launch that as a SaaS.” And we did that. Not very many people signed up and used it, but a lot of people reached out that were building agents, and they were like, “Hey, my agent needs a compute sandbox runtime,” whatever you wanna call it. I forgot what it was called at that point. And then we were like, “Oh, amazing. This is a new market. Here is our infrastructure. Here's our product, and go.” And what we found really fast, soon, was that people did not like what we had built. It didn't work. And I remember talking to people at the beginning when we're doing this, the sandbox we're building for agents. People were like, “Oh, why is it different? It's the same thing. We have like EC2, we have VMs, we have all these things.” But we saw that everyone we gave it to, it was like 20, 30 people, they all said, “No.” Like, “This is not what we need. This sort of breaks.” And basically, me and my co-founder not knowing a lot about - ‘cause we're infra people. We're not AI people. So I basically took it upon myself to like watch every single podcast that exists, including all of, all of these and all that, and sort of get up to date, read all the blogs, like get, understand what's going on.Swyx [00:08:45]: Do you wanna shout out who else was useful, just in case people are also looking.Ivan [00:08:49]: Generally we -, I looked at There's a few of podcast, different segments and different types. So there's you guys, No Priors, Bill Gurley's was great while.Swyx [00:09:04]: VG2, yeah.Ivan [00:09:05]: Yeah, while it was around. So there's a few. 20VC is interesting from a different dynamic, and some are different dynamic. But there was, also Red Points.Swyx [00:09:14]: We're not really about the compute market.Ivan [00:09:15]: It was also already - Sorry?Swyx [00:09:16]: You're, you want - You're looking at the agent infra market.Ivan [00:09:19]: I was looking at the agent market and the AI market in general and sort of understanding who are the players, what the perception, and how that goes. And like obviously you complement this with like going to conferences, going to events, going to meetups, reading white papers, like doing all the things that you have to do to understand what's happening. And so when we figured, when we sort of had an idea of what we had to build, literally over the New Year's Eve, literally on New Year's Eve, I half vibe coded the first MVP, first minimal viable product of what Daytona is today. And I went to sleep at like 3:00 AM or something like that. I was doing - I just put my like baby daughter and wife to sleep and, Happy New Year's, and go back to just, doing this. And I sent it to my co-founder, my CTO, and he saw it in the morning. He's like, “This is absolute garbage.” “Do not show this to anybody at all, but the idea is good.” And so he took two weeks, and he rebuilt it.Swyx [00:10:09]: Did it like look like that? Listen, I - It was rough idea.Ivan [00:10:12]: Oh, not even, not even close. Like it was it was way worse. But it was like a very - It was a simplistic view of what it should be. Like, it worked, but it was not ideal. And so he went, we went down the whole, which is his job as CTO, to go, and he came back with this version. We then called all the people that had said like, “This is garbage,” a quarter ago. And we set up these calls, and we gave it to - We just demoed it to everyone. And all the calls went long, every single one. They were 15-minute calls, and they all went to like 25, 30 minutes or whatnot. And everyone said, “We need, we want access.” There was no login, just an API key, ‘cause it was just a beta or an alpha. And they said, “Oh, we want access.” And we're like, “Sure, yeah. Okay, thank you very much.” But after like the next day, if we'd not send it, every single one, like every call that we did, everyone came back, “Where is my API key?” Like everyone wanted it. We're like, “S**t.” Like this is it. Like I've never felt So one, the understanding to your point was like most people thought it was the same infrastructure for humans and agents. We understood a quarter ago it's not. We just didn't know what was the right primitive. And then when we came, and we can talk about what that is, and we gave it to these people, I've never seen, I've never experienced - I've done multiple companies in my life. I've never experienced this, that people literally call you if you do not give them access. Like they want access right now. And so it's like, okay, they don't want this. the thing that they want doesn't seem to exist, or they have not found it, and they really want what we want. And then when we understood that we're onto something, and then when you think about the size of the market, like the market for human engineers and enterprise is a very large market, so think GitLab or whatnot. But the market for every single agent that will exist ever in the future is just like, what is that market? How big is that? And we're like, “We are all in on this.” And so that is where we made sort of the cut between the old product and the new one.Bare Metal, Stateful Sandboxes, and the Lambda + EC2 ModelSwyx [00:12:02]: Yeah. But it wasn't composable at the time?Ivan [00:12:05]: It was very - It was basically just a Linux box that you could change, that you could define number of CPUs, disk, and RAM. Like that is what you could do, but you couldn't have multiple operating systems, you couldn't resize it on the fly, you couldn't add a GPU, you couldn't do like all the things. It was just the, just the first sort of variation of that, yeah.Swyx [00:12:22]: Was it bare metal from the start?Ivan [00:12:24]: It was bare metal from the start. And so the interesting thing that we thought about right away, so our.Swyx [00:12:29]: Which, give people the background, what is the normal path?Ivan [00:12:32]: Yeah, so, basically most providers run this on top of VMs. And also.Swyx [00:12:37]: Firecracker.Ivan [00:12:38]: Yeah, they run on Firecracker and VM. And so we also fire - We can get - We have multiple isolation layers and we can do that. But the common way to do it is that they, one, that the state of the machine, or the hard disk is not part of the sandbox itself. And the other thing is they're not meant to last forever. So most of them are preemptible, like they can There's a time that they can live. And so our thought was when we were going into this is, agents will be like humans in the sense of you don't want your laptop to be shut down until you're done with work. Like, and you want to close the lid and open the lid, it's the same state. So you - Agents would want that, like the pause and come back. They want those two things. But also agents really want speed, right? Can they get it? So when we thought about it's like we need something insanely fast, how to make it fast, how to make it long-running, and stateful. And so those two things, it's like combining a Lambda and an EC2, right? Those two things together. And so we didn't have an idea how others did it, ‘cause we didn't know too that there was a market around this. It was more like, okay, this is what we need, what they need. And we looked at Kubernetes, it wasn't wasn't good enough for that. We looked at Nomad, it didn't enable that. And so our history in rewriting our own scheduler at CodeAnywhere is basically what my CTO came up with. Like, he's like, “Oh, the learnings from there,” and he brought it. And the funny thing is, our third co-founder, when he saw it, he's like, “Dude, what is this? This is like 2008.” Like, we went back in time, and he's like, “Exactly.” And so the reason why Daytona is like super fast, and you see this on benchmarks, is we essentially, we run on bare metal. We have our own scheduler, we use the underlying, disk, CPU, and RAM of the underlying machine, which means your IOPS are insanely fast because there's no, there's no network between an EBS or something like that. But also the snapshot, the point in time, the templates, are also preloaded on the bare metal machines. So when you fire off a sandbox from a template or a snapshot, you're essentially directed to the bare metal machine where that snapshot is based on that NVMe drive, and then it literally just turns on that machine, and it's local. There's no network latency, anything on there. And so that is sort of the specificities that we, when we're thinking from first principles, what a computer would look like for an agent, that is what we came up with, and that's what we created.Benchmarks, 60ms Startup, and 50,000 SandboxesSwyx [00:15:02]: Yeah. I should maybe, I don't know if you endorse this, but there's someone that does compute SDK, you guys do very well on there, with like the TTI, right? I. is this a, is this a is this a relevant benchmark for you guys? I don't know.Ivan [00:15:16]: I don't know, and it changes every day. So today RKL is.Swyx [00:15:18]: I don't know what RKL is. Never heard of it.Ivan [00:15:20]: Yeah. RK, yeah, so it is there.Swyx [00:15:22]: You are, at least a third of the next tier of performance, and then, there's a lot of other better-known names that are very slow to start.Ivan [00:15:31]: Yeah. We've been the number one by far for a long time, and now there's different, there's different definitions also of sandboxes, different isolation patterns, different other things. So RKL runs it literally on the S3, the data, so it's very different, and they spin up a sandbox, spin up a container for that, so it's a different type of thing. So the definition of a sandbox is something that we can all, we all need to get along with. But yeah, we're insanely fast on getting these things, up and running. And so you can see even there that it's a zero point 0.10 to 0.11, so.Swyx [00:16:03]: Close enough. Yeah. what else do you need, right?Ivan [00:16:05]: Yeah. So the benchmarks itself, so, in this, in I don't think the benchmarks equate to market ownership or revenue or anything like that. and I've seen this with multiple benchmarks, not just in sandboxes, but in general benchmarks around.Swyx [00:16:20]: It's table stakes. It's just like.Ivan [00:16:21]: Exactly. But it doesn't hurt.Swyx [00:16:22]: Just roughly check.Ivan [00:16:22]: Like you definitely have to be up there and you have to be competing so that people know that, oh, this is definitely one of the top. Because this is only one dimension of what customers look for. There's other things like how many can you spin up consecutively? There's a feature set, there's support, there's like all different things that people look at, but you definitely have to be there, on the benchmarks.Swyx [00:16:40]: How many people do people spin up consecutively?Ivan [00:16:43]: So we have.Swyx [00:16:43]: Or concurrently, is the Concurrency, right?Ivan [00:16:45]: There's three metrics that we look at. And so one is like time to spin up one, and so our time to spin up one is 60 milliseconds with network latency. So request, spin up, reply, 60, the whole thing, 60 milliseconds. That is one. But if you wanna spin up 50,000 at once, we are now at about 75 seconds. So it takes about 75 seconds to spin up concurrently 50,000. Some others, there's public data around this, like take 2,000 seconds, which is 30 minutes. Like there's different variations of that. And then there is the so it is speed of one, speed of like multiple, and then how many can you consistently have up and running. And so we basically have right now no limit to how much we can add because we basically own our own metal. But the biggest customer of ours does like about 850,000 every single day is sort of where they're, where they're just shy of a million every single day that they're running, we do have a request for half a million concurrent, which is literally half a million CPUs somewhere running. So that's an interesting.Swyx [00:17:44]: They pay by like vCPU seconds.Ivan [00:17:47]: By seconds, yeah.Swyx [00:17:47]: Or whatever. Yeah. Okay, and so and then, and the other thing is, the sleeping and the resuming, ‘cause it's all the stateful resumption of all these things, how, what kind of workload are people putting through this, right? Like how is it Do we measure by gigabytes in memory, gigabytes in storage? I don't In like network attached storage. I, what are the costly ones of, out of all these features?Workload Economics: CPU, RAM, Network, and StorageIvan [00:18:15]: The most expensive thing are CPU.Swyx [00:18:18]: Okay. Yeah, of course.Ivan [00:18:18]: The second one, yeah Then it's RAM, then it's disk. We actually don't charge.Swyx [00:18:22]: Which is snapshotting, right?Ivan [00:18:23]: No, it's actually the, snapshotting's part of it, but basically the size of your hard disk, of your machine. So do you have 10 gigabytes, do you have 20, do you have 50, do you have whatever? And then the transference of that. Right now, currently we don't charge for, network at all at Polychron.Swyx [00:18:37]: Oh, you gotta, yeah, you gotta fix.Ivan [00:18:38]: Yeah. It is very much a it's a larger and larger part of our bill, so we're working around, that part there. Obviously, that is the least, expensive, so the hard disk is the least expensive, so it's basically CPU, RAM, for us network, ‘cause we don't charge the customer, and then hard disk, is how it's split up. But there's also different types of workloads, so we basically split it up into two types of workloads in Daytona. One is what we call background agents or long-running agents. and the other is, basically RLs and evals, which I put sort of together. And so they have very different patterns of usage, and if you look at the usage of a background And I'll just name names of companies, not specifically.Background Agents vs. RL/Evals: Two Usage ShapesSwyx [00:19:21]: Yeah, open, all hands.Ivan [00:19:23]: Yeah. So like a background agent's a Cognition, a Lovable, a like all these things are Harvey. These are all long-running, background agents. And so if you look at their usage patterns, their usage patterns are similar to human, which is like follow the sun. Basically, the usage patterns of that is like noon is probably the highest, and the midnight is the lowest, and then weekends are lower. weekday is higher.Swyx [00:19:42]: Yeah, that's a fun question. How global is it? Is it very US-centric or?Ivan [00:19:46]: The US is a large part, but we have currently, we have Asia, Europe, and the US regions.Swyx [00:19:52]: So it's quite global.Ivan [00:19:53]: Yeah, it's quite global. We have it all over. It's interesting that our I talked to you a bit about this. Our number one city by user.Swyx [00:20:01]: Hmm.Ivan [00:20:02]: Is Singapore.Swyx [00:20:04]: Oh, wow. Amazing.Ivan [00:20:05]: Which is an interesting one, right? Not by revenue, just by just like by individual head count.Swyx [00:20:09]: Really?Ivan [00:20:09]: Just like an interesting thing.Swyx [00:20:10]: Singapore is, Singapore is weirdly high in the adoption charts of AI for the population. It's like an, seven, eight million population. And it's like keeps showing up.Ivan [00:20:20]: No, it's quite interesting. We were quite shocked, and I was like, “Oh, this is interesting.” And also one that's up there.Swyx [00:20:24]: There's a reason I'm doing AI using Singapore. it's because I'm from there.Ivan [00:20:27]: We're there. We're gonna, we're gonna be there as well. and it's interesting that Japan is in the top or like Tokyo's in the top, which is in all the tech cycles it has never been. It has never been, so it's quite interesting that they're.Swyx [00:20:39]: I think the Japanese just love AI. Yeah. It's that, and then it's Brazil. That's it.Ivan [00:20:44]: Brazil has always been in.Swyx [00:20:45]: I think.Ivan [00:20:46]: Even when I look, if you look at like GitHub's data and ask historically with CodeAnywhere, it was always like US, Western Europe, and then you'd have like India, Brazil, China, like that would be there. But like Singapore was not in, specifically Japan was never in sort of that top, that top.Swyx [00:21:01]: Yeah. Weird pockets.Ivan [00:21:01]: Weird. Yeah, so it's very global.Swyx [00:21:02]: Okay, so actually that, but that's helps you to distribute your load through, all time?Ivan [00:21:08]: The interesting thing is like we have those kind of loads, but if you look at the researcher loads, they're quite different. So what they are is like if you give them concurrency of 10,000 or 50,000 or 100,000 CPUs at ARMb, when they fire off a run, it's just 100%. And then it just runs, and then it stops. So it's very, the usage pattern is squares basically, right? And it's also not follow the sun, because people will fire it off at midnight before they go to sleep but then wake up and so it's very unpredictable, so you don't know where that is. So the shapes of the usage are quite different than we have had before. And also what's interesting is when it's sort of a follow the sun, even if you have a high growth company, you can sort of predict your usage patterns and have enough capacity for that, because it's sort of, it grows in a, in a way you can project. When you have companies doing sort of like evals and RL, they're super spiky. So they're gonna come in, it's like, “We're gonna use nothing, then can we have 100,000?” Right? And then go back down. And then 100,000, go back down. So it's very different, right? And.Swyx [00:22:09]: Do you want to lock them into commits so.Ivan [00:22:11]: Yeah, we do.Swyx [00:22:12]: Yeah, okay.Ivan [00:22:12]: We so we have to lock them into some sort of commits to have that capacity, because we have to have, basically we have to have the capacity for peak. Right? And so right now, Daytona's mean utilization is 15%, 1-5.Swyx [00:22:25]: Oh my God.Ivan [00:22:26]: So it's very low.Swyx [00:22:27]: Because it's very spiky.Ivan [00:22:27]: It's very spiky, but we get up to 90%. so we have these things. And so what we're, what we're looking at right now as a company is similar to Cloudflare where you can like geo move things around, but that works really well for basically the background agent where it's follow the sun. But this, it's not. Like it's a very different shape. Obviously with scale you figure these things out, but that's an interesting new problem that we have, as a compute provider in the agent space. And when we were doing the conference recently, and so we talked to like Nikita from Neon and.Swyx [00:22:57]: I should bring it up.Ivan [00:22:58]: Parag from Parallel and whatnot, everyone has the same problem. Whereas the usage is super spiky, and this is something that has not happened before, that you have these types of like it was always, it the amplitudes were not this high, right? So it's quite interesting use case and problem solve.Compute Conference and Spiky Agent InfrastructureSwyx [00:23:12]: Yeah, I don't know if we're gonna bring this up again, but let's just talk about the conference, you had like 1,000 something people at the Warriors game, at the Sorry, where is it? What's.Ivan [00:23:22]: Chase Center.Swyx [00:23:23]: Chase Center.Ivan [00:23:23]: Chase Center.Swyx [00:23:24]: I went. It was, it was very impressive. Obviously, you can, how to throw a conference, what did you learn? you put, you pulled together all these impressive names.Ivan [00:23:33]: What I.Swyx [00:23:34]: What were you looking for?Ivan [00:23:35]: My thesis behind the Compute Conference was let's bring together people that are building infrastructure for AI agents. Because when I think of what we're building, it is the agent is the primary user, what are the ergonomics and usage patterns of agents, and so we can do that. And what I found, this was a theory, it wasn't proven, is that we all have these problems, as I touched onto. And I was, as I was talking on stage, it was like we all have the same underlying infra problems, which is this spiky workloads, unpredictable workloads that we've never had before, in human, compute or human infrastructure. And it's, again, it's the same when I was talking to Parag or when I was talking.Swyx [00:24:20]: Lynn. Nikita.Ivan [00:24:21]: Lynn, Nikita. Lynn especially, I was talking to her the other day as well. Like the It is a very interesting type of problem to solve because I can touch on Cloudflare because there's a lot of like talk about that recently as to how they solve that, which is they have a bunch of geos, and basically, as users work in different places, and depending on your tier, they can move you around the geos. And so that how, that's how they get the higher utilization. But you can sort of predict these, and it's If it's something in You'll rarely get a spike that is 10 orders of magnitude. Like you'll get a like let's say one of your customers has some like an exponential curve. What is that to I'm using Cloudflare as an example. 10%, 20%, whatever it is. I don't, I don't have this data, I'm just assessing. It's surely not 10x, right? It's surely not something there. And so how do you go out and solve this problem? And we're all solving this in different ways. So we have.Swyx [00:25:11]: She also has the same thing.Ivan [00:25:12]: Yeah, I know specifically that like Neon had that issue as well. Like how are we solving these spiky loads and things like that ‘cause we talked about it. And so the interesting thing for me to actually internalize was, yes, everyone that's building for agents first is going through this, and we're all solving similar problems, which is quite.Swyx [00:25:28]: Let me let me double-click on this. Okay. So for example, Neon, I happen to know that they're very sort of S3 oriented, right? so they're just like fully bet on S3. And you get to benefit from S3's distribution and infrastructure. So I would imagine that Neon doesn't have to care, whereas Lynn maybe has to care a bit more because obviously she's doing GPU inference. And, for listeners, we did an episode with her, one and a half years ago. And you have to care. But like, right?Ivan [00:25:54]: Parag cares for sure, and Nikita.Swyx [00:25:58]: And Parag is C of, Parallel.Ivan [00:25:59]: Parallel, yeah.Swyx [00:26:00]: Former CTO of Twitter.Ivan [00:26:01]: Twitter, yeah.Swyx [00:26:02]: They are the search.Ivan [00:26:03]: Yeah, they're search, yeah.Swyx [00:26:03]: I You and I know but the listeners don't know.Ivan [00:26:08]: Yeah, we can put it down in the screen, and so ‘cause we, when we were talking.Swyx [00:26:11]: I'll put it up on the, on the screen.Ivan [00:26:12]: Yeah, right.Swyx [00:26:12]: People can look it up if they need.Ivan [00:26:14]: Look it up. And, yes, but they still have CPU and RAM, allocation that you have to have up and running. And so CPU and RAM, you have to allocate that and have that ready. And so there's basically two ways to do it. One is you either over-provision and you can handle the bursts, or two, you basically have, I don't know if this is a term, just-in-time compute, which is like as your load becomes, as your usage comes in, you can fire off requests for VMs or bare metals at other cloud providers and then get them up and running.Swyx [00:26:43]: This is if you go above 100%, right?Ivan [00:26:45]: Yeah, this is.Swyx [00:26:46]: Like your overflow.Ivan [00:26:46]: If your overflow, like spillage or whatever you do.Swyx [00:26:48]: You probably lose money on it, but it doesn't matter, right?Ivan [00:26:50]: It, not Well, you might, you might not That is a more cost-effective way to do it but it's a slower way to do it. Because basically what you have to do is you have to like queue your requests, spin up these just-in-time compute, get it all ready, provision it, and then get your workload there. And so if the time isn't important that much, that's fine, and you can do that. But if your customer, and especially for, let's say, the RL training runs, the reason why a lot of people come to us is because GPUs are more expensive than CPUs, right? So you want your GPU running at, what, 100% the entire time. And so when you're running runs on CPUs, when the when the CPU cycle is like down and spinning up the next one, you want that to be instantaneous so that your GPU doesn't go down, right? And if you then have to like go out and provision machines, you're essentially telling the GPU that it has to wait, and that's incurring our cost. So there's things that you have to try to solve for there.RL Workloads, Declarative Images, and Kubernetes ReplacementSwyx [00:27:43]: Yeah, let's talk about the different workload, right? You said that, what was it? A few months ago, you had zero RL workload and now it's 50%.Ivan [00:27:52]: It will be this one, 50%, yeah.Swyx [00:27:54]: Let's talk about how different it is, right? Like I imagine, for example, a lot less dynamic code generation of like arbitrary code. Like here, it's probably all the same code. You're just doing parallel runs or something, I don't know.Ivan [00:28:05]: Yeah. So you'll have multiple Depends on the like for each run, you'll have a snapshot. And they, for the most part, they actually do use our declarative image builder, which is like, “Oh, we, the agent wants these dependencies, these env vars.”Swyx [00:28:17]: These ones, yeah.Ivan [00:28:18]: Yeah, the declarative image builder, it.Swyx [00:28:20]: Which is a very modal like thing that they.Ivan [00:28:22]: Yeah. And so we build it on the fly and then we propagate that snapshot, and you can spin up as many sandboxes as you want against that snapshot. And then if you have to do changes, the model can, or like it could be also be automated. It's like, “Oh, now for the next run, we need to install these things or remove these things or whatever to get, a task done,” and then it goes off and runs that. So yes, that is something that it seems that they prefer. The number one reason I found, or should I say, let's take a step back. What we are competing against in that environment is essentially managed Kubernetes. So EKS, GKE, whatever. That is what the vast majority run on. And anyone that has tried Daytona versus GKE, EKS is like, “I'm never going back.” That has always been. There's a few reasons. One is the ergonomics. So if you have, if you're using Kubernetes to spin that up, you have to essentially manage the interface interactions with that. Daytona, although as a compute provider, it's more akin to a Twilio and Stripe from a consumption perspective than it is an AWS. Like you have an API, an SDK, it's quite like easy and seamless to get these things up and running, that's one. The other is the speed to which we spin up, which we mentioned earlier, which is much faster, and the scale to which we can go to. We haven't got into features, but an interesting feature is that it's very hard to OOM, or out of memory, our sandboxes, because we can dynamically on the fly.Swyx [00:29:48]: Resize.Ivan [00:29:49]: Resize, which is like impossible on almost any other thing. There are some technologies that enable you to do that, but it's like a very hard thing. And so we actually saw this when, the Terminal Revenge team is, brought us actually. So thank you, Alex and the team, that brought us into this whole space.Swyx [00:30:05]: It's just very rare that, a framework would just say, “Guys, just use Daytona.”Ivan [00:30:11]: Yeah, I think it says it somewhere. Yeah.Swyx [00:30:13]: Yeah. I was like, “What is this?”Ivan [00:30:15]: There's all, there's multiple there, but they also mention a few other places. and so Daytona specifically-We have, the, just jumping on themes here We, I don't know where it says Data Center.Swyx [00:30:27]: I, there.Ivan [00:30:27]: Doesn't matter.Swyx [00:30:28]: There's a very strong recommendation, which is, very unusual. Which is, it's.Ivan [00:30:33]: We do not pay them for this, just.Swyx [00:30:34]: I know, yeah. They just like you.Ivan [00:30:35]: Yeah, they like us. yeah, and also a thing, so, Data Center has multiple isolation sets underneath. The customer doesn't have to know what they are. But basically we have Docker, which is a container, that's hardened with Sysbox. So it's Docker's, isolation that is a security equivalent to a VM, but it's still a container. And that is the default, and they, especially in these training workloads, really like that as an interface to be able to use just a basic Docker container, and we enable Docker and Docker. Which for these RL runs, if you need to do a Docker compose or Kubernetes, you can spin up a K3S inside of these things, which unlocks a huge amount of workloads that you can do that you cannot do on other providers. So just on that part is much more interesting. And so we went that, through that. We showed them that we could do that, and they enjoyed that quite a bit. They being the general venture people.Swyx [00:31:28]: Those people, yeah.Ivan [00:31:29]: And Harbor people.Swyx [00:31:29]: Harbor people, do are they, are they a company yet?Ivan [00:31:33]: As far, I do not know.Customer Pull, Slack Connect, and the Computer Use BetSwyx [00:31:35]: Okay. All right. Yeah. It's like super obvious that like, there's a lot of excitement and success around these things, okay, so yeah, tell us more, right? Like, this is an exploding workload, Harbor adopted you, which helped speed things along. But what are you learning as this new workload comes online?Ivan [00:31:53]: There's a couple things that we learned, which we chat about in the beginning. We, and this has led our story, as we mentioned, we like talked to a lot of customers along the way, and we add more features and more tool sets as we talk to customers. And it's interesting that And I think it's that the ecosystem is so small and/or the models get smarter, where when we see one user come with a request, we know it goes on a roadmap if like three to five customers come with the same request in that week. It's like very bizarre. It happens so many times, which is.Swyx [00:32:27]: Because they're all friends.Ivan [00:32:28]: Sorry?Swyx [00:32:28]: They all, they're all friends. They're all in the same group chat.Ivan [00:32:30]: Yeah, probably, yeah. ‘Cause and they're like, “Oh, can you do this?” And I'm like, “Okay, this is interesting. We'll put it on a feature request.” And then the next one's like, “Oh, can you do this?” “Okay.” It's all the same, right? It's always the same. And so what we try to do, and I personally try to do, I try to be on as many call, quote-unquote “sales calls” I can. I'm in every Slack channel. We literally have about 1,000 Slack Connect channels, something like that. It's an interesting, there's so many interesting things you find out when you have all the Slack channels. You can also see where people, transfer between companies. You see leave Slack channel, enter Slack channel. It's an interesting thing. Also, just I digress, I feel that Slack Connect is literally LinkedIn what it should be. You have a list.Swyx [00:33:08]: LinkedIn charges you to, use your own connections, but Slack doesn't, right? Slack is like, do it for free. It's more lock-in. It's great.Ivan [00:33:15]: Yeah. It's amazing. Yeah. It's one of the reasons.Swyx [00:33:17]: You're gonna pay Slack for life.Ivan [00:33:18]: Exactly. You're there for life. So that's interesting. And so one of the things, the newer things we were talking about earlier is we made a big bet and put a lot of investment on computer use. that is not seen publicly the light of day. We haven't GA'd that yet, but we have.Swyx [00:33:32]: Is there a thing I can pull up?Ivan [00:33:33]: There is computer use there. It's right up a bit.Swyx [00:33:36]: Oh, yeah. Okay.Ivan [00:33:38]: What we have, what we talked about and what we've seen publicly is there's this theme now about, the human emulator where And Elon from XAI has talked about this publicly, and if you think about the models today, they're actually quite sophisticated and they can do a lot of work, but they still don't have access to all the tools. Like, I'm a strong believer that the most efficient way for an agent to work is essentially headless or through, terminal or whatnot. But if we, if we look at knowledge work in general, there's about 100 million knowledge workers in the US, about a billion in the world, and knowledge workers, and the salaries of them aggregate to 10 trillion in the US 50 trillion worldwide.Swyx [00:34:24]: Wow.Ivan [00:34:25]: Something like that. And if we look at, the five most important sectors of that, so like healthcare and government and financial services and whatnot, that's about 56% of that. So let's say it's about half of that. So in the US it's about 25 trillion, and most of them, most of that work is actually still locked into legacy apps inside of Windows, which is not going anywhere for a very long time. Like, people just won't invest in that. How much of it? our assumption is the following: if, in the RPA market, which is similar market, well, not the same 25% of, these white collar, workers', work is automated. If an agent is more sophisticated, can go through more runs, figure stuff out, let's say it's, 40%, right? And so if you take 40% of that, you get to essentially, $10 trillion a year.Swyx [00:35:17]: That's a TAM.Ivan [00:35:18]: That is a that is a TAM. So that's the TAM of the models, right? That's not our, essentially ours. But you get to that size, and to be able to do that, you essentially have to give agents these computers with the legacy. So computer use, either Mac or Windows or Linux. Linux we also obviously have and others have. But Windows specifically is something very new, and the only option right now is an EC2 with, Windows or on Azure. Both of them take anywhere from three to five minutes to spin up. We've created an actual sandbox, so it's a second instead of milliseconds, but you have, point in time snapshots, you have, forking, you have all the things that you have from a sandbox, but essentially enables you to hopefully unlock all this value. And so that's been our big push and bet, but we've sort of, kept our ear to the ground. What is sort of the next things in the market?RPA Returns: Why Agents Still Need ComputersSwyx [00:36:06]: Yeah, knowledge work, and building, and sort of RPA, the next wave of RPA. I got very excited about RPA kind of during COVID times. The UI path was IPO-ing. And it was, a very hot Isn't it, Eastern European?Ivan [00:36:20]: It is, Romanian.Swyx [00:36:21]: Romanian?Yeah, it might be the only Romanian, big unicorn okay, yeah. This I don't I don't, I don't have like a I think there's, I think there's a stage being set for the resurgence of RPA, ‘cause everyone understands that, yeah, no one wants to deal with these shitty apps and no one's gonna rewrite them. Like, you just have to do, a remote operation and programmatic operation of them.Ivan [00:36:45]: If you wanna unlock it, my own setup was basically the following. So I was doing a board deck recently, last month, whatever, and I'm like, “Okay, let's just, let's just do automated.” So, all our data's in, ClickHouse and PostHog and QuickBooks, where everyone else's is, and I'm basically, connected that all to, my Cloud code, like go off and go Cloud code whatever. Go off and, here's the integrations, go do that. It pulled out the first report, which was great. It connected to Brex and all these things, pulled it, which was great, and then I say, “Okay, now pull out this, and this,” and I kept getting, really well McKinsey-style design reports, but the data said partial data. all the missing data, partial data. Like, it can't access all the things, and I got so frustrated, and so I got, I got, my Mac Mini virtual sandbox with OpenClaw. I gave it its own account in our company, and then I went to all these services and created a read-only account, so literally like an intern in your company. And so I would say, “Now go and do this report,” and it would get the same, or like, “I can't via the MCP or the API or whatever. I can't get all the information.” I'm like, “Go log in.” And it will log into the website, then go in, export the data. It'll export the data and do the thing end to end. So even for things that have today APIs, not all of it is exposed, and I to get value, I get immense value right now, but it has to be a computer usage, unfortunately, and so I spend a bunch of tokens just on that, but I get the job done. And so if even a startup like ours, and using all the hottest tools, still needs a computer agent what hope does, Goldman have to have a headless, right?Swyx [00:38:22]: Yeah, what a - Why isn't Microsoft doing this?Ivan [00:38:27]: I'm pretty sure, Satya had a post yesterday.Swyx [00:38:29]: Oh, okay. I see.Ivan [00:38:29]: Which was like, “Every agent needs a computer.”Swyx [00:38:31]: I see, I see.Ivan [00:38:32]: So they have launched something recently.Swyx [00:38:34]: Yeah, they have Microsoft Power Automate, I'm sure, I'm sure, they're gonna have their version.macOS Sandboxes, Apple Constraints, and the Windows OpportunityIvan [00:38:39]: Version of that, yeah.Swyx [00:38:39]: You're gonna try to do yours, and it - I always know there's always demand for Mac, but I know it's, tricky to host, macOS sandboxes.Ivan [00:38:49]: We will have macOS sandboxes fairly soon. The problem with macOS, OS sandboxes is, I'm deep in this, I don't know how much interesting is.Swyx [00:38:55]: No, it's.Ivan [00:38:56]: MacOS has this problem.Swyx [00:38:57]: It's a licensing thing, right?Ivan [00:38:58]: Licensing thing. So one, you're allowed to run only two parallel VMs per machine, so that's one. Two, you can only license to a different user every 24 hours. So if you come in and theoretically, if I wanna charge you per second and I charge you one second, I have to have it idle for the rest of the day. I can't have anyone else doing that. So the pricing will be different in the sense that I will have to - we would have to charge for 24 hours, and that's not even, that's not even the most difficult thing. But the, thing above that is, from a security perspective, they enable you to do memory snapshot, pause, resume, but only on the same physical drive, physical machine. And so what you can do in, Windows world or Linux world is that I can move in the background, your snapshot from one to the other and manage load, right? Here, if you wanna do that, you essentially have to have your.Swyx [00:39:49]: Yeah, snapshots. Yeah.Ivan [00:39:50]: Your.Swyx [00:39:51]: It's like.Ivan [00:39:51]: Physical machine.Swyx [00:39:52]: You can't break it up.Ivan [00:39:53]: You can't, you can't move things around that, and all of that is, that part is, from a security standpoint, if it is written. Like, I understand the security aspect of that, but it disables you from doing these agentic, like really scalable agentic workloads.Swyx [00:40:08]: You need to do a vibe-coded, clean room implementation on macOS that you can then - That's like Clean OS or something. I don't know.Ivan [00:40:17]: So. We have.Swyx [00:40:18]: ‘cause like Linux was originally like a clean room rewrite of Unix.Ivan [00:40:21]: Okay. Yeah.Swyx [00:40:21]: Or something like that, right? Like same thing to macOS. Someone needs to do it.Ivan [00:40:25]: Someone will do that, and someone will have some long-running agents for a few days to figure this stuff out. But yeah. So definitely we - we're really close to offering something ‘cause people do want it, but the pricing will be different, and the feature set will be sort of stringent.Swyx [00:40:38]: Yeah, nobody's gonna use this. like, the labs, the labs will because they want to automate macOS.Ivan [00:40:42]: They have to do RL. They have to do RL again. But even if you The - So the point is with the RL part, if you, if you do RL on macOS, then the next iteration of the model comes out, it will be able to use these tools significantly. Then you actually need to run those, that somewhere. So you're gonna have to have that, later on. And from, if anyone at Apple is listening, I very much feel that they are shooting themselves in the foot of the scale of the revenue of compute or licensing they could get if they would just enable a concurrency model similar to what you can get on a Windows and a, and Linux.Swyx [00:41:17]: Yeah. Yeah. And I'm sure they've heard this before. They just don't care. Yeah, it's And maybe they will change their mind with the new CEO.Ivan [00:41:24]: Yeah. We'll see.Swyx [00:41:25]: We'll see.Ivan [00:41:25]: High hopes.Swyx [00:41:26]: High hopes.Ivan [00:41:26]: High hopes.Swyx [00:41:27]: Okay. But I, it's very clear the market opportunity is huge in Windows, and you can go for a long time on just Windows, but your customers are gonna want both. and I think, it is interesting to me that, this is the sort of God application of agents, right? Like, I don't It was - How big was OpenClaw for you guys? Like, was it, was there, a significant bump.OpenClaw, Agent Labs, and the B2B2C Sandbox MarketIvan [00:41:54]: Not for us because we.Swyx [00:41:54]: Because you already.Ivan [00:41:55]: We're kind of positioned differently. Whereas although it's completely PLG and we have individual developers that use it, most of the users that use Daytona are sort of a B2B2C. Sort of it's either B2B or B2B2C. So, in the researcher world, it's B2B, so you're selling to, labs and neo labs and things like that. But on the long-running agents, it's mostly, from a scale revenue perspective, it's mostly B2B2C, where you have a app layer agent that uses you at a big scale.Swyx [00:42:26]: Like a Manus. Yeah.Ivan [00:42:28]: Like a Manus Lovable type of thing.Swyx [00:42:31]: Yeah. I think that's the question of, well how, um-Uh, yeah, B2B to C is basically to me what I've been calling an agent lab, which is kind of like you're not in a model lab, but you're making a very good wrapper that is a platform that other people can sign up so they don't have to code those things. Yeah, it sound, it sounds like a much better market than the direct OpenClaw market.Ivan [00:42:56]: I've like - We I've done multiple things. So the CodeAnywhere's part of our career path R in the calendar, was very much an end user developer product. And so that is great. It You can get a lot of developer love, and I feel that we do as a company have a bunch of developer love. But it's a different type, where it's people building these things. Again, it's more akin to a Twilio because you don't really run - As a person, you wouldn't run Twilio. I don't know how many people remember. It was like ask your developer billboard and whatnot. And people really love Twilio, but they only used it inside of like, “Oh, I'm building this app or service for thing.” And so we're very much directly to that. And you also know that I used to work for a competitor for Twilio, so it's kind of ingrained, in my DNA.Swyx [00:43:35]: People don't know InfoBip is that big.Ivan [00:43:38]: Yeah, it's.Swyx [00:43:39]: Because.Ivan [00:43:40]: It's a billion euro.Swyx [00:43:40]: They're all American. They're like, “Whatever's in Europe doesn't matter to me.” But like it's the, it's the same size or bigger? Same size?Ivan [00:43:46]: It's about half the size.Swyx [00:43:47]: Half the size?Ivan [00:43:48]: Yeah, about half the size.Swyx [00:43:48]: It's like, yeah.Ivan [00:43:48]: Still huge. Multiple billions a year. Yes.Swyx [00:43:51]: That's crazy.Ivan [00:43:51]: Exactly, and so that - These are like really interesting and large revenue-generating, very sticky businesses. Whereas when you're selling to the - When your focus is the end developer, it is a very hard sell because they're very price sensitive, very price conscious, very around that. And there's very It's very hard to scale. Your cap is the number of people that are willing to spin up - First of all, wanna spin that up, and then spin up multiple of these. Whereas if you're in the enterprise one, like we know everyone's talking about like how many tokens they're spending, I'm spending. Like a lot of companies today are like, “If this is our company, spend as much as you can.” Like basically that is where we're going. And so if you think about that paradigm, where you're selling to companies that say, “Spend as much as you can to generate, productivity,” versus, “Oh, I'm a single person. I have this much budget, and I'm doing this thing because it's fun or it's helping me out or whatever.” Like it is a different, it's a different go-to-market, I think, strategy.MCP, CLIs, and Sandboxes as the Agent RuntimeSwyx [00:44:50]: Yeah, there's a lot of discussion. I'm just kind of going through like the mental list of things that are in your favor, which is, for example, MCP versus CLI. Like obviously you want CLI. It's been very good for you. I feel like it's maybe a drop in the bucket or maybe it's huge. I'm just checking whether it's like these are big trends.Ivan [00:45:10]: Those things you - work well in our favor, to your point just because every.Swyx [00:45:13]: They're kind of drop in the bucket, right?Ivan [00:45:15]: I think it's like sort of all the things come together. And so there's so many things that impact that. To your point, like OpenClaw wasn't huge for us, but like having the agent SDK, from Anthropic, so or Cloud Claude Code was very interesting. The reason why it was interesting is that a lot of, let's call them app I don't know what to call them, app layer agent companies, essentially they are like, “Oh, I can create this new app, this new agent. All I need, I just use Claude Code, and I throw it into a sandbox, and then I have my interface to the human to that.” And so that enabled so many more companies to actually offer this, and then they would pull on sandbox. So that was, that was interesting. And to your point, like MCP, versus the CLI, the MCP is an interface against an API, whereas the CLI is like you can actually go do things. Like this is it. The difference between integrations and actually running scripts or data or analysis against a thing. So being able to use a CLI very well enables the agent to do more things, and it's because that people will invoke a sandbox, they'll run it in the CLI, and but it'll do anal-analysis on that data and then give you an actual result versus just, pulling data from an API source.Swyx [00:46:29]: Yeah, it's a layer of indirection basically, it's the same thing as agentic search versus RAG, which where you're.Ivan [00:46:34]: Exactly, yeah.Swyx [00:46:34]: Just like you just win whenever people put more agents into their workflow. And so like it doesn't really matter, but I'm just kinda teasing out like what else have people heard about that like it's sort of, “Oh yeah, this is another sandbox use case. Oh yeah, that's another one.” Am I, am I missing any big ones?Ivan [00:46:51]: The thing, the thing that people, which is the computer use stuff, which I think is probably the most interesting one, is, and to your point, we've talked to so many people over the last year. It's like, “Oh, like why do you need a sandbox? Why do you need this? Why this?” And to your point, it's like, “Oh, I need sandbox for this. I need sandbox for that. I need sandbox-” It's like, “Oh, I need it for every single thing.” And so basically what I, what I - and it sounds like a broken record, it's like you use a laptop every single day, right? And you are n of one. It's just you. But now imagine how And by the way, the laptop, the computer PC market, the PC market is about equal to the cloud market in total. So it's about 150, 180 billion a year. Something like that. It's about roughly the three cloud hyperscalers is about equal to like Apple, HP, Lenovo, whatever, It's a little bit less, but it's sort of like that. And now imagine And that's just like, so how big is the addressable market? What, how many people are there in the world now? What's the last data?Swyx [00:47:45]: Let's call it eight billion.Ivan [00:47:46]: Eight billion. And so let's say you can have two computer, like you have one personal and one business, whatever. Like so it's double that, right? and so that's 16 billion, right? How many agents are gonna be running in two years, in 10 years, in 100 years? Like And for every single task, they will need one of these. And so how big is that? That market is essentially quote unquote “infinite”. You will get to the point, and Dylan Patel was at the conference talking about, from SemiAnalysis, that talks usually about GPUs, was also talking about how CPUs will now be a bottleneck because it will be the constraint. You won't be able to grow, or we won't be able to have enough of these because there won't be enough CPUs to basically do.Swyx [00:48:23]: Yeah. Well, I actually had a really good podcast with Doug Oliphant, who, which was his president at SemiAnalysis, where they've basically been like, yeah, it's been a GPU shortage first, but then it's cascaded down to memory and now to CPUs.Ivan [00:48:35]: CPU, yeah.Swyx [00:48:35]: It-What's next? So networking. So, networking actually has been in shortage for a while if you're looking at, just GPU networking. But, yeah, it's really crazy the amount of computer use that's going on, yeah, cool. I, other questions are, just the one very big part is the open sourceness which you didn't have to do, your competitors don't do, like it's not, a lot of people are worried about keeping their projects open source because some competitor can just slot fork it. I don't know if there's any reflections on just being an open source company.Open Source, Trust, and Enterprise ProcurementIvan [00:49:15]: Yeah. There's a bunch. So we the original product that we did was open source.Swyx [00:49:19]: Yeah. CodeAnywhere.Ivan [00:49:20]: So doing that was actually very good for us. There's basically a saying of, What's the saying? Like, companies that are, that are doing really well, measure themselves against, free cashflow, that are kinda okay, it's EBITDA, then, it's, it goes all the way down.Swyx [00:49:36]: The worst is like GitHub stars.Ivan [00:49:37]: GitHub stars. GitHub stars are the worst, yeah. So you go all the way down to GitHub stars. And so our original one was GitHub stars. That's what we talked about, we're at the point we're talking about revenue, so we're we've gone up the stack on that. And so we started.Swyx [00:49:47]: No, profit.Ivan [00:49:48]: Yeah. We haven't, we're, we'll get there. We'll get there. But basically at that point we did stars and GitHub and it was useful, and the original variation that we did, it we split the core into its own repo and it was Apache 2.0, so very, permissive. And then we basically would bundl

Is it a good time to buy bonds? On this episode of Market Sense, Fidelity portfolio manager Julian Potenza. who co-manages the Fidelity Total Bond Fund weighs in on the latest bond market trends amid a backdrop of geopolitical tensions and higher oil prices. He will also discuss what central bank policy could look like under new leadership at the Federal Reserve and what this all could mean for bond investors. Want to research rates? Head here to look up CUSIP numbers, bonds yields, and CDs. Read the full transcript View the slides Watch the video replay

Thistle Resources Inc. CEO Patrick Cruikshank joined Steve Darling from Proactive to provide additional details on the company's strategic focus on precious metals and critical minerals exploration within New Brunswick's historic Bathurst Mining Camp. The company is pursuing a multi-project exploration strategy with the objective of advancing five key assets, including Middle River Gold, Brunswick Antimony, Middle River VMS, Alba Forks Gold, and Celtic Highland Gold. Cruikshank highlighted the company's flagship projects, particularly the Middle River Gold and Brunswick Antimony properties, which are expected to play central roles in Thistle's long-term development plans. The Bathurst Mining Camp has long been recognized as one of Canada's most significant mining regions, known for hosting major mineral deposits and attracting exploration activity over several decades. Particular attention is being placed on the Brunswick Antimony Project, which sits adjacent to the world-famous Brunswick No. 12 Mine, historically one of the largest underground zinc mines globally and recognized as a major volcanogenic massive sulphide (VMS) deposit. The proximity to this established mining district provides important geological context and could enhance exploration potential. Cruikshank explained that drilling and historical work at the property have identified encouraging antimony mineralization. Results indicate the presence of antimony associated with sediment-hosted structures and high-grade mineralized zones. Certified trench assay data returned values of up to 10.3% antimony, along with 1,300 g/t silver and 2.32 g/t gold. The company noted that multiple styles of mineralization have been identified, including disseminations, crystal formations, and mineralized veins associated with silver-rich systems. Looking ahead, the next phase of exploration is expected to involve the company's proprietary UAV drone magnetic survey technology. The initiative is designed to identify and confirm additional mineralized structures before expanding trenching and follow-up exploration work. Cruikshank noted that the required trenching and UAV permits have already been secured, with geophysical survey work expected to begin in the near term. Antimony continues to attract increasing attention globally as a strategically important critical mineral. It is currently recognized as one of Canada's 37 critical minerals and plays an important role across multiple industries, including military applications, batteries, semiconductors, and advanced energy storage technologies. Growing supply concerns and demand for secure domestic critical mineral sources continue to elevate interest in antimony-focused exploration projects. #proactiveinvestors #thistleressources #tsxv #trcg #MiningIssuer #PublicMarkets #MiningFinance #JuniorMining #Exploration #CriticalMinerals #PreciousMetals #NewBrunswickMining #NovaScotiaMining #BathurstCamp #CapeBreton #ResourceDevelopment #AtlanticCanada #Antimony #CriticalMinerals #Mining #GoldExploration #Silver #ResourceInvesting #MineralExploration #BatteryTechnology #CanadianMining

In this episode, hosts Lois Houston and Nikita Abraham break down the differences between Infrastructure-as-a-Service, Platform-as-a-Service, and Software-as-a-Service. The conversation explores how each framework influences control, cost efficiency, expansion, reliability, and contingency planning.   Cloud Tech Jumpstart: https://mylearn.oracle.com/ou/course/cloud-tech-jumpstart/152992 Oracle University Learning Community: https://education.oracle.com/ou-community LinkedIn: https://www.linkedin.com/showcase/oracle-university/ X: https://x.com/Oracle_Edu   Special thanks to Arijit Ghosh, Anna Hulkower, Radhika Banka, and the OU Studio Team for helping us create this episode. --------------------------------------- Episode Transcript: 00:00 Hi there! We're hitting rewind for the next few weeks and bringing back some of our most popular episodes. So, sit back and enjoy these highlights from our archive. 00:12 Welcome to the Oracle University Podcast, the first stop on your cloud journey. During this series of informative podcasts, we'll bring you foundational training on the most popular Oracle technologies. Let's get started! 00:38 Nikita: Welcome to the Oracle University Podcast! I'm Nikita Abraham, Team Lead: Editorial Services with Oracle University, and with me is Lois Houston, Director of Innovation Programs. Lois: Hey there! Last week, we spoke about how hypervisors, virtual machines, and containers have transformed data centers. Today, we're moving on to something just as important—the main cloud models that drive modern cloud computing. Nikita: Orlando Gentil, Principal OCI Instructor at Oracle University, joins us once again for part four of our discussion on cloud data centers.  01:14 Lois: Hi Orlando! Glad to have you with us today. Can you walk us through the different types of cloud models?  Orlando: These are commonly categorized into three main service models: Infrastructure-as-a-Service, Platform-as-a-Service, and Software-as-a-Service. Let's use the idea of getting around town to understand cloud service models. IaaS is like renting a car. You don't own the car, but you control where it goes, how fast, and when to stop. In cloud terms, the provider gives you the infrastructure—virtual machines, storage, and networking—but you manage everything on top—the OS, middleware, runtime, and application. Thus, it's like using a shuttle service. You bring your bags—your code, pick your destination—your app requirements, but someone else drives and maintains the vehicle. You don't worry about the engine, fuel, or routing planning. That's the platform's job. Your focus stays on development and deployment, not on servers or patching. SaaS is like ordering a taxi. You say where you want to go and everything else is handled for you. It's the full-service experience. In the cloud, SaaS is software UXs over the web—Email, CRM, project management. No infrastructure, no updates, just productivity.  02:45 Nikita: Ok. How do the trade-offs between control and convenience differ across SaaS, PaaS, and IaaS? Orlando: With IaaS, much like renting a car, you gain high control. You are managing components like the operating system, runtime, your applications, and your data. In return, the provider expertly handles the underlying virtual machines, storage, and networking. This model gives you immense flexibility. Moving to PaaS, our shuttle service, you shift to a medium level of control but gain significantly higher convenience. Your primary focus remains on your application code and data. The provider now takes on the heavy lifting of managing the runtime environment, the operating system, the servers themselves, and even the scaling. Finally, SaaS, our taxi service, offers the highest convenience with the lowest control level. Here, your responsibility is essentially just using the application and managing your specific configurations or data within it. The cloud provider manages absolutely everything else—the entire infrastructure, the platform, and the application itself. 04:05 Nikita: One of the top concerns for cloud users is cost optimization. How can we manage this? Orlando: Each cloud service model offers distinct strategies to help you manage and reduce your spending effectively, as well as different factors that drives those costs. For Infrastructure-as-a-Service, where you have more control, optimization largely revolves around smart resource management. This means rightsizing your VMs, ensuring they are not overprovisioned, and actively turning off idle resources when not in use. Leveraging preemptible or spot instances for flexible workloads can also significantly cut costs. Your charges here are directly tied to your compute, storage, and network usage, so efficiency is key. Moving to Platform-as-a-Service, where the platform is managed for you, optimization shifts slightly. Strategies include choosing scalable platforms that can efficiently handle fluctuating demand, opting for consumption-based pricing where available, and diligently optimizing your runtime usage to minimize processing time. Costs in PaaS are typically based on your application usage, runtime hours, and storage consumed. Finally, for Software-as-a-Service where you can consume a ready-to-use application, cost optimization centers on licensing and usage. This involves consolidating tools to avoid redundant subscriptions, selecting usage-based plans if they align better with your needs, and crucially, eliminating any unused license. SaaS costs are generally based on subscription or per user fees. Understanding these nuances is essential for effective cloud financial management.  06:05 Lois: Ok. And what about scalability? How does each model handle the ability to grow and shrink with demand, without needing manual hardware changes? Orlando: How you achieve and manage that scalability varies significantly across our three service models. For Infrastructure-as-a-Service, you have the most direct control over scaling. You can implement manual or auto scaling by adding or removing virtual machines as needed, often leveraging load balancers to distribute traffic. In this model, you configure the scaling policies and parameters based on your specific workload. Moving to Platform-as-a-Service, the scaling becomes more automated and elastic. The platform automatically adjusts resources based on your application's demand, allowing it to seamlessly handle traffic spikes or dips. Here, the provider manages the underlying scaling behavior, freeing you from that operational burden. Finally, with Software-as-a-Service, scalability is largely abstracted and invisible to the user. The application scales automatically in the background, with the entire process fully managed by the provider. As a user, you simply benefit from the application's ability to handle millions of users without ever needing to worry about the infrastructure. Understanding these scaling differences is crucial for selecting the right model for your application's need.  07:45 Join the Oracle University Learning Community and tap into a vibrant network of over 1 million members, including Oracle experts and fellow learners. This dynamic community is the perfect place to grow your skills, connect with likeminded learners, and celebrate your successes. As a MyLearn subscriber, you have access to engage with your fellow learners and participate in activities in the community. Visit community.oracle.com/ou to check things out today!  08:18 Nikita: Welcome back! We've talked about cost optimization and scalability in cloud environments. But what about ensuring availability? How does that work?  Orlando: Availability refers to the ability of a system or service to remain accessible in operational, even in the face of failures or extremely high demand. The approach of achieving and managing availability, and crucially, your role versus the provider's, differs greatly across each model. With Infrastructure-as-a-Service, you have the most direct control over your availability strategy. You will be responsible for designing an architecture that includes redundant VMs, deploying load balancers, and potentially even multi-region setups for disaster recovery. Your specific roles involves designing this architecture and managing your failover process and data backups. The provider's role, in turn, is to deliver the underlying infrastructure with defined service level agreements, SLAs, and health monitoring. For Platform-as-a-Service, the platform itself offers a higher degree of built-in, high availability, and automated failover. While the provider maintains the runtime platform's availability, your role shifts. You need to ensure your application's logic is designed to gracefully handle retries and potential transient failures that might occur. Finally, with Software-as-a-Service, availability is almost entirely handled for you. The provider ensures fully abstracted redundancy and failover behind the scenes. Your role becomes largely minimal, often just involving a specific application's configurations. The provider is entirely responsible for the full application uptime and the underlying high availability infrastructure. Understanding these distinct roles in ensuring availability is essential for setting expectations and designing your cloud strategy efficiently. 10:32 Lois: Building on availability, let's talk Disaster Recovery. Orlando: DR is about ensuring your systems and data can be recovered and brought back online in the event of a significant failure, whether it's a hardware crash, a natural disaster, or even human error. Just like the other aspects, the strategy and responsibilities for DR vary significantly across the cloud service models. For Infrastructure-as-a Service, you have the most direct involvement in your DR strategy. You need to design and execute custom DR plans. This involves leveraging capabilities like multi-region backups, taking VM snapshots, and setting up failover clusters. A real-world example might be using Oracle Cloud compute to replicate your VMs to a secondary region with block volume backups to ensure business continuity. Essentially, you manage your entire DR process here. Moving to Platform-as-a-Service, disaster recovery becomes a shared responsibility. The platform itself offers built-in redundancy and provide APIs for backup and restore. Your role will be to configure the application-level recovery and ensure your data is backed up appropriately, while the provider handles the underlying infrastructure's DR capability. An example could be Azure app service, Oracle APEX applications, where your apps are redeployed from source control like Git after an incident. Finally, with Software-as-a-Service, disaster recovery is almost entirely vendor managed. The provider takes full responsibility, offering features like auto replication and continuous backup, often backed by specific Recovery Point Objective (RPO) and Recovery Time Objective (RTO) SLAs. A common example is how Microsoft 365 or Salesforce manage user data backups in restoration. It's all handled seamlessly by the provider without your direct intervention. Understanding these different approaches to DR is crucial for defining your own business continuity plans in the cloud. 12:59 Lois: Thank you, Orlando, for this insightful discussion. To recap, we spoke about the three main cloud models: IaaS, PaaS, and SaaS, and how each one offers a different mix of control and convenience, impacting cost, scalability, availability, and recovery.  Nikita: Yeah, hopefully this helps you pick the right cloud solution for your needs. If you want to learn more about the topics we discussed today, head over to mylearn.oracle.com and search for the Cloud Tech Jumpstart course. In our next episode, we'll take a close look at the essentials of networking. Until then, this is Nikita Abraham… Lois: And Lois Houston, signing off! 13:39 That's all for this episode of the Oracle University Podcast. If you enjoyed listening, please click Subscribe to get all the latest episodes. We'd also love it if you would take a moment to rate and review us on your podcast app. See you again on the next episode of the Oracle University Podcast.

Slide into our VMs to find out.

Slide into our VMs to find out.

Slide into our VMs to find out why.

Java 26 est là, GraalVM cartonne chez Trivago (43 à 12 réplicas !), OpenJDK interdit le code généré par LLM, Spring et Quarkus enchaînent les releases. Côté IA : ADK 1.0, A2A, Lyria 3 chante (mal ?), Yann LeCun lance Ami Labs et ses World Models. Mythos d'Anthropic fait trembler la sécu, Claude Code a leaké son source, et les git worktrees envahissent vos terminaux. Bonus : la mort annoncée de l'IDE, vagues de licenciement chez Oracle et Block, et nos voix toutes clonées. Bon week-ends de mai ! Enregistré le 7 mai 2026 Téléchargement de l'épisode LesCastCodeurs-Episode-340.mp3 ou en vidéo sur YouTube. News Langages Retour d'expérience d'une migration vers graalVM chez Trivago https://medium.com/graalvm/inside-trivagos-graalvm-migration-native-image-for-graphql-at-scale-912bca9df841 La passerelle GraphQL de Trivago (point d'entrée de tout le trafic vers 48 microservices) souffrait de pics de timeout au démarrage JVM Résultats spectaculaires après migration vers GraalVM Native Image : réduction des réplicas de 43 à 12, CPU de 15 à 5 cœurs, images Docker plus légères Obstacles techniques : incompatibilité Log4j → migration vers Logback, remplacement de Mockk par Testcontainers, compilation CI/CD très gourmande Netflix DGS et d'autres librairies manquaient de support GraalVM → l'équipe a contribué des correctifs upstream en open source Approche recommandée : commencer par les services les moins complexes, investir massivement dans les tests automatisés À la 14e migration, le processus était si rodé qu'il allait plus vite que la toute première tentative OpenJDK Interim Policy on Generative AI - https://openjdk.org/legal/ai OpenJDK adopte une politique intérimaire interdisant toute contribution incluant du contenu généré par des LLMs, modèles de diffusion ou systèmes deep-learning Le périmètre est large : code source, texte, images dans les dépôts Git, pull requests GitHub, emails, pages wiki et issues JBS Les contributeurs peuvent utiliser les outils d'IA de manière privée pour comprendre, déboguer et relire le code OpenJDK, mais ne peuvent pas contribuer le contenu généré Trois risques justifient cette politique : surcharge des relecteurs face au code plausible mais incorrect, risques de sûreté/sécurité pour une plateforme critique, et risques de propriété intellectuelle (l'OCA exige que les contributeurs possèdent les droits IP de leurs contributions) Même éditer partiellement du code AI-généré ne le rend pas acceptable à la contribution Oracle, sponsor corporatif d'OpenJDK, travaille sur une politique complète à soumettre au Governing Board GraalVM Native Image et la Closed-World Assumption en Java https://pvs-studio.com/en/blog/posts/java/1357/ Un bon article de rappel du contexte de closed world en Java GraalVM Native Image compile les applications Java en exécutables natifs statiques, sans JVM au runtime. La JVM fonctionne en monde ouvert : les classes sont chargées à la demande, les appels sont des références symboliques résolues dynamiquement. Native Image impose la "closed-world assumption" : tous les chemins d'exécution doivent être connus à la compilation. Les fonctionnalités dynamiques Java (réflexion, proxies, chargement de classes) créent des chemins cachés invisibles à l'analyse statique. C'est pourquoi Native Image exige des fichiers de configuration explicites pour la réflexion, les proxies, les ressources et la FFM API. L'article illustre le problème avec la Foreign Function & Memory API pour appeler printf natif : fonctionne sur JVM, échoue en Native Image sans config. Inclure tout le bytecode accessible serait inutilisable : binaire géant, compilation très lente, et la réflexion nécessite des métadonnées précises. La configuration n'est pas un défaut de conception mais une conséquence logique du passage du dynamique au statique. Java 26 : les nouveautés https://foojay.io/today/java-26-whats-new/ Java est le langage de la JVM, publié tous les 6 mois depuis Java 9 ; Java 26 est une version non-LTS avec 10 JEPs. JEP 500 : protection des champs final modifiés par réflexion profonde, avec des avertissements configurables. JEP 504 : suppression définitive de l'API Applet, plus supportée par les navigateurs. JEP 516 : le cache AOT (Project Leyden) fonctionne désormais avec n'importe quel garbage collector. JEP 517 : support HTTP/3 dans le client HTTP, HTTP/2 reste le défaut mais HTTP/3 est accessible à la demande. JEP 522 : amélioration du débit du GC G1 en réduisant la synchronisation entre threads applicatifs et threads GC. Nouveau support des UUIDv7 via UUID.ofEpochMillis(), naturellement triables et adaptés aux identifiants de bases de données. Process devient AutoCloseable, utilisable dans un try-with-resources. Aucune fonctionnalité en preview n'est graduée en standard ; Structured Concurrency en est à sa 6e preview. Librairies Guillaume a créé une petite librairie Java sans dépendance pour extraire le JSON d'une réponse d'un LLM un peu verbeux https://glaforge.dev/posts/2026/03/22/extracting-json-from-llm-chatter-with-jsonspotter/ Les LLM génèrent souvent du JSON, mais il est parfois entouré de bla-bla et/ou contient des erreurs (ex: commentaires, virgules finales) qui bloquent les parseurs JSON standards. Guillaume a créé une petite librairie légère sans dépendance pour localiser et extraire la structure la plus longue ressemblant à du JSON (même malformé) On peut ensuite passé cette chaîne à un parseur "lénient" (plus tolérant) comme Jackson pour ensuite avoir de bons vieux objets Java fortement typés Librairie dispo sur Maven Central ADK Java sort sa version 1.0 (Agent Development Kit par Google) https://developers.googleblog.com/announcing-adk-for-java-100-building-the-future-of-ai-agents-in-java/ ADK est un framework open source de Google pour créer des agents IA, initialement en Python, maintenant multi-langages (Python, Java, Go, Typescript). Nouvelles fonctionnalités majeures : Outils puissants : GoogleMapsTool, UrlContextTool, ContainerCodeExecutor, VertexAiCodeExecutor, abstraction ComputerUseTool. Architecture de plugins centralisée : Nouveau conteneur App pour gérer les Plugins à l'échelle de l'application (ex: LoggingPlugin, GlobalInstructionPlugin). Context engineering amélioré : Compaction d'événements pour gérer la taille des fenêtres de contexte (résumé et rétention). Human-in-the-Loop (HITL) : Supporte les workflows ToolConfirmation pour approbation humaine des actions d'agent. Services de session et de mémoire : Contrats clairs pour la gestion de l'état (InMemory, VertexAI, Firestore) et la mémoire à long terme. Support Agent2Agent (A2A) : Collaboration native entre agents distants de différents frameworks via le protocole A2A. Dans cet autre article, Guillaume partage comment il a développé l'application Comic Trip montrée dans la vidéo YouTube et qui utilise ADK 1.0 https://glaforge.dev/posts/2026/03/30/building-my-comic-trip-agent-with-adk-java-1-0/ Nouvelle version du SDK Java pour Agent2Agent Protocol, avec le support de la version 1.0 de la spécification https://medium.com/google-cloud/a2a-java-sdk-1-0-0-beta1-released-e83c414b34cc Alignement avec la version 1.0 de la spécification Nouveau groupId org.a2aproject.sdk et package org.a2aproject.sdk Protocoles de transport : support complet et équivalent pour JSON-RPC, gRPC et HTTP+JSON/REST. Gestion des erreurs : introduction de codes d'erreur et détails structurés pour une meilleure observabilité. Optimisation HTTP : ajout d'en-têtes de cache pour les métadonnées des agents (Agent Card). Flexibilité du client HTTP : support par défaut du JDK HttpClient, avec option Vert.x pour les environnements Quarkus. Nouvelles fonctionnalités techniques : méthode DataPart.fromJson() pour la création simplifiée d'objets depuis du JSON brut. Prochaines étapes (v1.0.0.GA) : support simultané des versions 1.0.0 et 0.3.0 du protocole pour assurer l'interopérabilité. JPA 4.0 Milestone 2 : nouvelles fonctionnalités pour Jakarta Persistence https://in.relation.to/2026/04/23/JPA-4-M2/ Jakarta Persistence (JPA) est la spécification standard Java pour le mapping objet-relationnel (ORM), implémentée notamment par Hibernate. JPA 4.0 M2 est la deuxième milestone de la prochaine version majeure de la spécification, annoncée par Gavin King. Construction de requêtes Criteria à partir de chaînes JPQL, offrant plus de flexibilité dans la composition dynamique des requêtes. Nouveaux types d'expressions spécialisés (TextExpression, NumericExpression) pour simplifier l'écriture des requêtes Criteria. Nouvelle interface FetchOption pour contrôler explicitement la stratégie de chargement des associations, dont un BatchSize intégré. Nouvelle annotation @EntityListener qui découple les classes entités de leurs listeners, supprimant les dépendances à la compilation. Les listeners peuvent cibler plusieurs types de callbacks et s'appliquer globalement à toute l'unité de persistance. Introduction de FlushModeType.EXPLICIT et QueryFlushMode pour un contrôle plus fin de la synchronisation avec la base de données. La méta-annotation @Discoverable permet de placer des annotations comme @NamedQuery sur n'importe quelle classe ou interface. Améliorations du DDL via @Index amélioré et clarifications de la spécification via la javadoc. Quarkus 3.35 : tree-shaking, PGO et AOT Semeru https://quarkus.io/blog/quarkus-3-35-released/ Quarkus est un framework Java cloud-natif optimisé pour GraalVM et HotSpot, conçu pour les microservices et les environnements conteneurisés. Nouveau JAR tree-shaking expérimental : analyse des dépendances à la compilation pour supprimer les classes inutilisées. Sur le CLI Quarkus, cela supprime plus de 6 000 classes et économise environ 18 Mo (39,5 %). Support du Profile-Guided Optimization (PGO) pour les builds natifs via quarkus.native.pgo.enabled=true. Le PGO est une fonctionnalité Oracle GraalVM, non disponible dans la Community Edition. Support de l'AOT IBM Semeru : le démarrage passe de ~380 ms à ~190 ms dans les premiers tests. Nouvelle extension quarkus-reactive-transactions : support de @Transactional pour les méthodes Hibernate Reactive retournant Uni. Configuration CORS dédiée pour l'interface de management, indépendante de l'interface HTTP principale. Les tests n'utilisent plus les System Properties pour la propagation de configuration, facilitant la parallélisation future. Le serializer jackson sans reflection n'est pas le default du aux retours de cas limites, encore du travail This Week in Spring - 21 avril 2026 https://spring.io/blog/2026/04/21/this-week-in-spring-april-21-2026 Spring Framework 6.2.18 et 7.0.7 corrigent trois failles de sécurité : DoS via fichiers multipart WebFlux, empoisonnement de cache de ressources statiques, et DoS sur Windows. Le support open source de Spring Framework 5.3.x et 6.1.x est terminé, la migration est recommandée. Spring Data 2026.0.0-RC1 introduit l'upsert (MERGE/INSERT ON CONFLICT) dans l'API Template de Spring Data Relational. Spring Data ajoute un RedisMessageSendingTemplate pour la cohérence avec les listeners Redis, et une optimisation de réinitialisation de caches en un seul appel. Spring AI introduit une Session API (série Agentic Patterns, partie 7) : architecture event-sourcée pour la mémoire des agents IA. La Session API supporte la compaction turn-safe, l'isolation de sous-agents en parallèle, et la persistence JDBC (PostgreSQL, MySQL, MariaDB, H2). Elle vise Spring AI 2.1 (novembre 2026) et remplacera à terme l'API ChatMemory. Spring Vault 4.1.0-RC1 et 4.0.2 sont disponibles. Netflix a présenté son usage de Java, Spring Boot et Spring AI dans une vidéo. This Week in Spring - 28 avril 2026 https://spring.io/blog/2026/04/28/this-week-in-spring-april-28-2026 Cette série hebdomadaire de Josh Long compile les nouveautés de l'écosystème Spring : articles, outils, podcasts et annonces de la communauté. Spring Boot 4 introduit un package natif de résilience org.springframework.resilience avec une nouvelle API de retry qui remplace les approches fragiles via Spring Retry ou Resilience4j. L'API retry native de Spring Boot 4 a des noms d'attributs et sémantiques différents des anciennes bibliothèques, rendant les tutoriels pré-2025 obsolètes et sources de bugs silencieux. Le SDK Spring AI pour Amazon Bedrock AgentCore est disponible en GA : il intègre les capacités AgentCore dans Spring AI via annotations et auto-configuration. Le SDK AgentCore gère automatiquement le contrat runtime AgentCore : endpoint /invocations, health check /ping, SSE avec backpressure. Il offre mémoire court terme (sliding window) et long terme (sémantique, préférences, résumé, épisodique), ainsi que des outils pour navigateur et exécution de code en sandbox. Un plugin Maven (Nullability Maven Plugin) simplifie l'intégration de JSpecify et NullAway pour enforcer la null-safety à la compilation dans les projets Java. Le plugin génère automatiquement les fichiers package-info.java par package et configure le compilateur pour traiter les violations de nullabilité comme des erreurs. Josh Long et Dr. Venkat Subramaniam ont co-présenté à Voxxed Days Amsterdam sur "Intelligent Kotlin", avec un épisode de podcast associé. Cloud Amazon S3 Files https://aws.amazon.com/about-aws/whats-new/2026/04/amazon-s3-files/ Amazon S3 Files est un nouveau service donnant un accès système de fichiers direct aux données stockées dans les buckets S3 Basé sur la technologie Amazon EFS, il supprime la barrière entre stockage objet et interface système de fichiers sans dupliquer les données Débit en lecture pouvant atteindre plusieurs téraoctets par seconde ; des milliers de ressources de calcul peuvent y accéder simultanément Les données restent accessibles via les deux interfaces : S3 API classique et système de fichiers standard, sans migration nécessaire Cas d'usage : agents IA pour la persistance de mémoire entre pipelines, équipes ML sans staging, simplification des data lakes Disponible dans 34 régions AWS Data et Intelligence Artificielle Comment générer de la musique et des clips audio en Java avec le modèle Lyria 3 https://glaforge.dev/posts/2026/03/25/generating-music-with-lyria-3-and-the-gemini-interactions-java-sdk/ Génération musicale avec Lyria 3 (DeepMind) et le SDK Java Gemini Interactions. Lyria 3 : modèle d'IA générative pour créer musique avec paroles ou pistes instrumentales. Utilisation via le SDK Java de l'API Gemini, nécessite une clé API Gemini. Deux versions de modèle Lyria 3 : lyria-3-clip-preview : Clips courts (30s), extraits. lyria-3-pro-preview : Chansons complètes (jusqu'à 3 min), structurées. Personnalisation via les prompts : Fournir ses propres paroles ou les faire générer. Contrôler la structure de la chanson ([Intro], [Verse], [Chorus], [Outro]). Générer des morceaux instrumentaux uniquement. Utiliser des images comme source d'inspiration (modèle multimodal). Sortie : Audio (MP3) et texte (paroles/structure) directement, sans décodage complexe. Facilite l'intégration de la génération musicale dans les applications Java. Les world model, la prochaine étape pour les IA https://www.lepoint.fr/sciences-nature/comment-le-commando-de-yann-le-cun-se-prepare-a-ringardiser-les-geants-mondiaux-de-lia-depuis-paris-OZVUWTDYBNE25C6WF44265ZQKE/ Yann LeCun a quitté Meta FAIR pour créer AMI Labs (Advanced Machine Intelligence) basée à Paris Sa thèse : les LLMs ne mèneront pas à l'intelligence générale, la vraie IA doit partir de la compréhension du monde physique AMI Labs a levé 1,03 milliard de dollars en seed (le plus grand seed round de l'histoire européenne) à 3,5 milliards de valorisation Les world models apprennent à prédire et comprendre la réalité physique plutôt qu'à prédire le prochain token d'une séquence Slogan d'AMI : "Real intelligence does not start in language. It starts in the world." Paris comme base stratégique pour challenger la Silicon Valley dans la prochaine rupture de l'IA Debezium 2026 : résultats du sondage communautaire https://debezium.io/blog/2026/04/27/debezium-2026-survey-results/ Debezium est un outil de Change Data Capture (CDC) open source qui capture les modifications de bases de données en temps réel pour les diffuser vers des systèmes comme Kafka. 98,6% des répondants utilisent Debezium activement ou prévoient de le faire dans l'année, avec 91,3% déjà en production. 63,8% des déploiements tournent sur Kubernetes, 60,9% utilisent Kafka Connect auto-géré, et 17,4% restent sur des VMs ou bare metal. Helm charts est l'approche dominante pour la gestion de configuration, souvent combiné avec GitOps, CI/CD, Ansible ou Terraform. PostgreSQL domine les connecteurs utilisés à 69,6%, suivi de MySQL (33,3%), SQL Server (29%) et Oracle (27,5%). Les volumes de changements capturés vont de 1-25 modifications par minute jusqu'à 1-2 millions par minute selon les environnements. Infinispan rejoint l'écosystème OGX comme fournisseur de stockage vectoriel https://infinispan.org/blog/2026/04/17/infinispan-joins-ogx-ecosystem OGX (anciennement Llama Stack) est un serveur API agentique open source pour construire des applications d'IA complètes. OGX compose des fournisseurs d'inférence, des stores vectoriels, des backends de sécurité, des runtimes d'outils et du stockage de fichiers en un seul serveur déployable. OGX se positionne comme une alternative à l'API OpenAI, déployable sur diverses infrastructures et modèles. OGX cible les workflows RAG (Retrieval-Augmented Generation) et les applications agentiques. Infinispan s'y intègre comme fournisseur de vector IO, apportant recherche vectorielle, par mots-clés et hybride. Je n'ai pas entendu parlé de ce renommage, vous le voyez dans vos deploiements ? Outillage cmux un nouveau terminal basé sur Ghostty spécialisé pour les coding agents https://cmux.com/ Application macOS native construite sur le moteur de rendu Ghostty (libghostty), offrant une accélération GPU pour une fluidité maximale Conçu spécifiquement pour le multitâche et les workflows assistés par IA, avec des onglets verticaux affichant la branche Git, le répertoire et les ports actifs Intègre des notifications qui illuminent les panneaux lorsqu'un agent IA (Claude Code, Codex, etc.) nécessite l'attention de l'utilisateur Propose un navigateur web intégré et scriptable qui peut être affiché en écran scindé à côté du terminal via une API Alternative moderne à tmux, ne nécessitant pas de fichiers de configuration complexes ou de préfixes de touches pour la gestion des vitres et des sessions Supporte nativement tous les agents de codage en ligne de commande et permet l'automatisation via une API socket et une interface CLI dédiée Git Worktree comme un chef https://www.metal3d.org/blog/2026/git-worktree-comme-un-chef/ Article par Patrice Ferlet Git Worktree: Travailler sur plusieurs branches simultanément via des répertoires distincts. Évite git stash ou clones multiples pour le changement de contexte rapide. Méthode "bare" (recommandée): Cloner le dépôt en mode bare (ex: .bare). Lier le dossier racine au dépôt bare via un fichier .git. Configurer le remote tracking pour voir toutes les branches distantes. Ajouter des worktrees pour chaque branche (git worktree add ). Avantages: Économie d'espace, source de vérité unique (un git fetch met tout à jour), hooks/configs partagés, sécurité. Conseils: Ne jamais faire de git checkout à l'intérieur d'un worktree. git fetch --all depuis n'importe quel worktree pour tout mettre à jour. git worktree add --detach pour tester des merges temporaires sans créer de branche. Supprimer: git worktree remove puis git worktree prune. Un script wtree est fourni pour automatiser l'initialisation du setup "bare". Améliore considérablement le workflow. L'IDE meurt et vite https://x.com/jdegoes/status/2036931874057314390?s=46&t=C18cckWlfukmsB_Fx0FfxQ Des leaders techniques prédisent la fin rapide de l'IDE traditionnel, remplacé par des interfaces conversationnelles agentiques Le changement de paradigme : le développeur n'écrit plus des lignes de code mais exprime son intention et supervise des agents autonomes Des outils comme Claude Code, Copilot et Cursor transforment déjà radicalement les workflows de développement quotidiens L'IDE centré sur l'éditeur de code perd sa raison d'être quand l'agent lit, modifie et structure le code de manière autonome La transition est comparable au passage du desktop au mobile : les pratiques établies depuis 30 ans remises en question en quelques mois Le source de Claude Code a leaké via probablement le codemap et un site decrit sont fonctionnement https://ccunpacked.dev/ Le 31 mars 2026, Anthropic a accidentellement inclus les sourcemaps dans un package npm de Claude Code, exposant ~512 000 lignes de TypeScript La fuite n'était pas un piratage mais une erreur humaine : un "*.map" oublié dans .npmignore Le site ccunpacked.dev a été lancé pour analyser et visualiser le code source décompressé Le code révèle un agent background permanent nommé "KAIROS", un mode furtif pour cacher les contributions des employés Anthropic à l'open source, et 44 feature flags cachés Une fonctionnalité inédite "Buddy" (animal de compagnie électronique dans le terminal) et un mode "dream" pour l'idéation continue ont été découverts Anthropic a confirmé : "Aucune donnée client sensible n'était impliquée. Erreur humaine dans le packaging de la release." Gemini CLI passe aux agents https://x.com/srithreepo/status/2039794081925382307?s=46&t=GLj1NFxZoCFCjw2oYpiJpw Gemini CLI, l'agent IA open source de Google pour le terminal, introduit des hooks dans sa boucle agentique Les hooks permettent d'exécuter des scripts automatiquement (scanners de sécurité, vérifications de conformité, logging) à chaque étape de l'agent Lancement de Gemini CLI GitHub Actions : un agent autonome pour les repositories qui peut exécuter des tâches de codage de routine Support des MCP servers pour étendre les capacités et des "Agent Skills" pour des workflows spécialisés Mode agent disponible dans VS Code et IntelliJ avec accès aux outils du système de fichiers et terminal Wispr, le speech to text en local sur macOS http://wispr.stormacq.com/ Wispr est une application macOS de dictée vocale entièrement locale, propulsée par Whisper (OpenAI) sur appareil, sans cloud ni tracking Sébastien Stormacq a développé Wispr en un jour et demi sans écrire une seule ligne de code, grâce à Kiro CLI (agent IA Amazon) Disponible en open source sur GitHub et via Homebrew Détection automatique de la langue, insertion du texte au curseur dans n'importe quelle application via un raccourci global En un mois : 19 releases incluant mode mains-libres, suppression des mots de remplissage, auto-envoi pour les chats, et un outil CLI Exemple concret de développement vibe coding produisant un outil de qualité production sans expertise Swift préalable Comment, Gordon, l'assistant spécialisé en Docker est né https://n9o.xyz/posts/202603-building-gordon/ Nuno Coração (n9o.xyz) détaille comment Gordon, l'assistant spécialisé Docker, a été construit sur docker-agent, le runtime d'agents IA open source de Docker écrit en Go Les agents sont définis en YAML déclaratif et distribués comme des artefacts OCI, sans mise à jour binaire nécessaire L'architecture initiale en essaim de 9 agents spécialisés a été abandonnée au profit d'un agent racine unique avec un prompt soigneusement conçu Le modèle utilisé est Claude Haiku 4.5, suffisant après optimisation des prompts Principe clé "show, then do" : toute action de l'agent nécessite une approbation explicite de l'utilisateur La description des outils impacte fortement la précision du LLM : ajouter des outils peut paradoxalement dégrader les performances existantes Le prompt est une spécification détaillée (identité, patterns d'accès fichiers, règles de sécurité) plutôt qu'une simple instruction IBM Bob https://bob.ibm.com/blog/announcing-ibm-bob-launch IBM Bob assistant IA d'IBM pour coder sur de vraies codebases (lancé avril 2026) 5 modes : Ask, Plan, Code, Advanced (MCP), Orchestrator Détecte la complexité du code en temps réel et propose des refactos Fait des revues de code automatiques sur tes branches/issues GitHub Permet d'écrire en langage naturel directement dans l'éditeur Fonctionne aussi en terminal/CLI et dans les pipelines CI/CD Sécurité : approbation manuelle, .bobignore, checkpoints, pas de training sur tes prompts How I use Claude - 50 tips pratiques https://www.youtube.com/watch?v=mZzhfPle9QU Staff Engineer Meta partage 50 tips après 6 mois d'utilisation intensive de Claude Code Basé sur ~12h/jour d'usage perso et professionnel Couvre tout : bases, workflows avancés, parallélisation Objectif : partager ce qu'il aurait voulu savoir dès le départ Méthodologies Quelqu'un rale sur la non soutenabilité des bases de code écritent avec des agents https://mariozechner.at/posts/2026-03-25-thoughts-on-slowing-the-fuck-down/ Mario Zechner estime que les agents IA font les mêmes erreurs répétitivement sans apprendre, accumulant la complexité à grande vitesse faute de bottlenecks humains Sans vision globale, les agents créent du cargo-cult : les "best practices" de l'industrie appliquées localement sans cohérence architecturale La croissance de la base de code dégrade la capacité des agents à retrouver le code existant → duplication et incohérences croissantes Il cite des pannes AWS et des initiatives qualité Microsoft comme signes préoccupants liés au code généré par IA Solution : réserver les agents aux tâches délimitées et évaluables, garder l'architecture, les APIs et les systèmes critiques écrits à la main Maintenir une revue de code rigoureuse et traiter les humains comme les gardiens finaux de la qualité On m'oblige à utiliser l'IA https://n.survol.fr/n/on-moblige-a-utiliser-lia Éric D. défend l'adoption obligatoire de l'IA comme décision stratégique légitime, comparable au choix du full remote ou de la stack technique Il distingue la décision stratégique (adoption IA) de la méthode d'accompagnement (qui reste collaborative et bienveillante) La compétence IA devient un critère de recrutement : chercher des candidats déjà curieux et explorateurs de ces outils L'alignement culturel sur les pratiques et outils est un prérequis à la cohésion d'équipe Le refus d'adopter certains outils stratégiques peut justifier de ne pas recruter un candidat autrement compétent Encore une metodo SPDD https://martinfowler.com/articles/structured-prompt-driven/ Problème : l'IA accélère le dev individuel mais amplifie ambiguïtés et incohérences à l'échelle d'une équipe. martinfowler SPDD : traiter les prompts comme des artefacts versionnés, révisables et réutilisables plutôt que des échanges jetables. martinfowler Canvas REASONS : 7 dimensions (Requirements, Entities, Approach, Structure, Operations, Norms, Safeguards) pour guider le LLM de l'intention à l'exécution. martinfowler Workflow en 6 étapes : exigences → analyse → contexte → prompt structuré → code → tests unitaires, chaque étape s'appuyant sur la précédente. martinfowler 3 compétences clés : abstraction d'abord, alignement de l'intention, revue itérative. martinfowler Limites : fort ROI sur du code métier complexe, peu adapté aux hotfixes urgents, scripts jetables ou travail créatif/visuel. m Sécurité Le projet Glasswing pour sécuriser les logiciels https://www.anthropic.com/glasswing Anthropic lance Glasswing, une initiative de cybersécurité utilisant Claude Mythos Preview pour identifier des vulnérabilités zero-day 12 partenaires fondateurs dont AWS, Apple, Cisco, CrowdStrike, Google, JPMorganChase, Linux Foundation, Microsoft et NVIDIA Anthropic investit 100 millions de dollars en crédits de modèle et 4 millions en dons aux organisations de sécurité open source Le modèle opère avec une autonomie substantielle, identifiant des milliers de vulnérabilités dans les OS, navigateurs et infrastructures critiques Plus de 40 organisations supplémentaires ont accès pour scanner et sécuriser leurs systèmes Objectif : donner l'avantage aux défenseurs avant que les techniques de hacking assistées par IA ne se généralisent chez les attaquants LinkedIn vous espionne https://frenchbreaches.com/blog/linkedin-est-accuse-de-fouiller-dans-votre-ordinateur-illegalement Scandale "BrowserGate" : LinkedIn injecte du JavaScript qui tente de détecter les extensions Chrome installées sur votre navigateur Le script analysé contient une liste codée en dur de 6 222 extensions Chrome avec identifiants et chemins de fichiers internes Croissance alarmante de la liste ciblée : 38 extensions en 2017 → 461 en 2024 → ~1 000 en mai 2025 → 6 222 début 2026 Les données collectées incluent aussi CPU, RAM, résolution d'écran, timezone et état batterie pour du fingerprinting Certaines extensions ciblées sont liées à la neurodivergence, aux pratiques religieuses ou aux opinions politiques → violation grave du RGPD LinkedIn défend que le scan vise uniquement à détecter les extensions qui pratiquent le scraping de données Post mortem de la supply chain attack sur la librairie NPM axios https://github.com/axios/axios/issues/10636 Le 31 mars 2026, deux versions malveillantes d'axios (1.14.1 et 0.30.4) ont été publiées via un compte mainteneur compromis Vecteur d'attaque : RAT installé via ingénierie sociale ciblée sur la machine personnelle du mainteneur principal La 2FA ne protège pas si la machine de l'utilisateur est compromise : l'attaquant contrôle tout et peut agir comme l'utilisateur Les packages malveillants injectaient plain-crypto-js@4.2.1, un cheval de Troie multi-plateforme (macOS, Windows, Linux) Détection communautaire en ~3 heures, suppression par npm, mesures correctives : rotation complète des credentials Changements préventifs : publication via OIDC, releases immuables, amélioration des pratiques GitHub Actions Passbolt un gestionnaire de mots de passe open source https://lesjoiesducode.fr/passbolt-gestionnaire-de-mots-de-passe-gratuit-open-source-que-votre-equipe-merite-vraiment Gestionnaire de mots de passe open source conçu pour le partage d'identifiants en équipe, utilisé par plus de 50 000 organisations Chiffrement individuel par utilisateur et par version de credential, pas de coffre-fort partagé — architecture zero-knowledge "Forward secrecy" : quand un membre quitte l'équipe, ses copies chiffrées sont automatiquement révoquées sans reset manuel Supporte TOTP, clés SSH, tokens API et champs personnalisés avec piste d'audit complète de tous les accès Édition communautaire entièrement gratuite avec utilisateurs illimités, auto-hébergeable ou cloud Chiffrement OpenPGP nécessitant passphrase + clé privée, avec tokens visuels anti-phishing Loi, société et organisation Anthropic fait un don d'1,5 millions de dollars à la fondation Apache https://news.apache.org/foundation/entry/the-apache-software-foundation-announces-1-5m-donation-from-anthropic Anthropic donne 1,5 million de dollars à l'ASF pour soutenir l'infrastructure, la sécurité et la communauté open source Vitaly Gudanets (CISO d'Anthropic) : "Soutenir l'ASF est un investissement direct dans la résilience et l'intégrité des systèmes dont dépend l'IA moderne" Les fonds financeront les systèmes de build, les processus de sécurité et les services aux projets Apache Ce don est le déclencheur de l'initiative IA responsable à 10 millions de dollars de l'ASF L'infrastructure Apache est invisible mais critique : des systèmes financiers aux plateformes de santé, elle sous-tend l'écosystème logiciel mondial L'ASF lance l'initiative IA responsable https://news.apache.org/foundation/entry/the-apache-software-foundation-launches-10m-responsible-ai-initiative-with-initial-1-75m-donation L'ASF lance une initiative pour une IA responsable dotée d'un budget de 10 millions de dollars sur 3 ans minimum Anthropic est le premier donateur avec 1,5 million de dollars ; Alpha-Omega contribue 250 000 dollars L'initiative fournit aux projets Apache un accès à des modèles IA pour l'expérimentation et la sécurité Elle soutient l'ensemble de la chaîne IA/ML : pipelines de données, infrastructure, frameworks de deep learning Des tracks de conférences, hackathons et bourses de voyage sont prévus pour élargir la communauté Les principes directeurs incluent la supervision humaine, l'intégrité des licences et la sécurité open source Oracle vire 30000 personnes https://rollingout.com/2026/03/31/oracle-slashes-30000-jobs-with-a-cold-6/ Oracle licencie 20 000 à 30 000 employés, 18% de ses effectifs mondiaux. Les salariés ont appris leur licenciement par un simple email à 6h du matin, sans aucun préavis. L'accès à tous les systèmes (Slack, Zoom, badges) a été coupé immédiatement après. But : libérer 8 à 10 milliards de dollars pour construire des centres de données IA. Oracle a déjà contracté 50 milliards de dettes en 2026 pour financer ses projets IA. Paradoxe : l'entreprise affiche un bénéfice record de 6,13 milliards, mais ses liquidités sont dans le rouge. L'action Oracle a perdu plus de la moitié de sa valeur depuis septembre 2025. Et si l'IA n'était qu'un prétexte pour licencier https://eventuallycoding.com/p/ia-licenciements-et-si-l-intelligence-artificielle-n-etait-qu-une-excuse Hugo Lassiège (eventuallycoding) estime que les entreprises utilisent l'IA comme narratif commode pour masquer des erreurs de gestion passées (Block a triplé ses effectifs post-COVID sans croissance des revenus correspondante) Moins de 1% des licenciements technologiques seraient réellement dus à des gains de productivité IA selon les analyses citées Mesurer la productivité des développeurs reste un problème non résolu, mais les entreprises affirment des gains d'efficacité sans preuves Des pressions économiques réelles (inflation, guerres commerciales, coûts énergétiques) sont masquées derrière le discours IA Les restructurations nécessaires sont présentées comme des transformations AI-driven positives pour rassurer les investisseurs Il y voit une fenêtre d'opportunité pour l'Europe pendant que les géants américains se restructurent GitHub Copilot va utiliser les interacitons pour entrainer ses modèles sauf si vous vous délistez https://github.blog/news-insights/company-news/updates-to-github-copilot-interaction-data-usage-policy/ À partir du 24 avril 2026, GitHub utilise par défaut les interactions des utilisateurs Copilot Free, Pro et Pro+ pour entraîner ses modèles Les données collectées incluent le code accepté ou modifié, les snippets envoyés, les noms de fichiers et structures de dépôts, et les retours utilisateurs Les utilisateurs Copilot Business, Enterprise et les dépôts d'entreprise sont exclus de cette collecte de données d'entraînement Opt-out disponible dans les paramètres GitHub > "Privacy" ; les préférences de désactivation préalables sont conservées automatiquement Objectif déclaré : améliorer la précision des modèles sur les langages et cas d'usage du monde réel Grosse percée de Claude Code dans les commits sur GitHub https://aifoc.us/damn-claude-thats-a-lot-of-commits/ Explosion de Claude Code : En six mois, Claude Code est passé de 0,7 % à 4,5 % de tous les commits publics sur GitHub, surpassant tous les autres outils d'IA combinés. Adoption massive des agents IA : Environ 5 % des commits publics sur GitHub sont désormais générés par des agents IA, un chiffre en croissance rapide depuis fin 2025. Domination des bots sur GitHub : Au-delà des commits, les outils d'IA sont omniprésents dans la gestion des pull requests et des problèmes (Copilot et CodeRabbit notamment). Limites méthodologiques : Les données ne concernent que les dépôts publics (les entreprises utilisent massivement des dépôts privés, invisibles ici). Le comptage dépend fortement de la visibilité des signatures (certains outils comme Claude marquent systématiquement leurs commits, d'autres non) L'API de recherche GitHub présente une fiabilité variable à cette échelle. Changement de paradigme : Le développement logiciel vit une transition majeure, comparable au passage du desktop au mobile. L'intégration des agents IA dans le cycle de production n'est plus une expérimentation, mais une réalité opérationnelle à grande échelle. Dysmaths une application pour aider à apprendre les mathématiques et la géométrie lorsque l'on souffre de dyspraxie, dysgraphie https://dysmaths.com/ Application web pour aider les élèves de collège et lycée souffrant de dysgraphie et dyspraxie à faire des maths et de la géométrie Outils de dessin à main levée, géométrie précise (compas, rapporteur, règle) et opérations structurées (fractions, racines, puissances, symboles mathématiques) Export PDF et PNG avec conservation fidèle de l'échelle pour l'impression et la soumission des exercices Options d'accessibilité : police OpenDyslexic, personnalisations d'interface, import d'images et de PDFs Répond à un besoin réel : les outils standards ne sont pas adaptés aux difficultés de coordination et d'organisation spatiale en mathématiques IA ou réalité ? Par Amistory https://www.youtube.com/watch?v=PPYdAhBBF2I L'IA génère des contenus (images, voix, vidéos) de plus en plus indétectables Les arnaques au clonage de voix et deepfakes sont en forte hausse Les faux contenus viraux manipulent l'opinion à grande échelle Le faux n'est plus un accident, c'est devenu un système organisé La société entre dans une ère de doute généralisé sur le réel Comment s'informer quand le réel lui-même peut être simulé ? Conférences La liste des conférences provenant de Developers Conferences Agenda/List par Aurélie Vache et contributeurs : 6-7 mai 2026 : Devoxx UK 2026 - London (UK) 12 mai 2026 : Lead Innovation Day - Leadership Edition - Paris (France) 12-13 mai 2026 : Lyon Craft - Lyon (France) 19 mai 2026 : La Product Conf Paris 2026 - Paris (France) 19-20 mai 2026 : Green Code Challenge - Paris (France) 21-22 mai 2026 : Flupa UX Days 2026 - Paris (France) 22 mai 2026 : AFUP Day 2026 Lille - Lille (France) 22 mai 2026 : AFUP Day 2026 Paris - Paris (France) 22 mai 2026 : AFUP Day 2026 Bordeaux - Bordeaux (France) 22 mai 2026 : AFUP Day 2026 Lyon - Lyon (France) 27 mai 2026 : aMP Day Strasbourg 2026 - Strasbourg (France) 28 mai 2026 : DevCon 27 : I.A. & Vibe Coding - Paris (France) 28 mai 2026 : Cloud Toulouse 2026 - Toulouse (France) 29 mai 2026 : NG Baguette Conf 2026 - Paris (France) 29 mai 2026 : Agile Tour Strasbourg 2026 - Strasbourg (France) 2-3 juin 2026 : Agile Tour Rennes 2026 - Rennes (France) 2-3 juin 2026 : OW2Con - Paris-Châtillon (France) 3 juin 2026 : IA–NA - La Rochelle (France) 4 juin 2026 : Workplace Intelligence Days - 1ère édition - Lyon (France) 5 juin 2026 : TechReady - Nantes (France) 5 juin 2026 : Fork it! - Rouen - Rouen (France) 6 juin 2026 : Polycloud - Montpellier (France) 9 juin 2026 : JFTL - Montrouge (France) 9 juin 2026 : C: - Caen (France) 9 juin 2026 : France API 2026 - Paris (France) 11-12 juin 2026 : DevQuest Niort - Niort (France) 11-12 juin 2026 : DevLille 2026 - Lille (France) 12 juin 2026 : Tech F'Est 2026 - Nancy (France) 15 juin 2026 : Jupyter Workshops: Demystifying MyST Markdown in Education - Orsay (France) 16 juin 2026 : Mobilis In Mobile 2026 - Nantes (France) 17-19 juin 2026 : Devoxx Poland - Krakow (Poland) 17-20 juin 2026 : VivaTech - Paris (France) 18 juin 2026 : Tech'Work - Lyon (France) 22-26 juin 2026 : Galaxy Community Conference - Clermont-Ferrand (France) 23-24 juin 2026 : MWCP 2026 - Paris (France) 24-25 juin 2026 : Agi'Lille 2026 - Lille (France) 24-26 juin 2026 : BreizhCamp 2026 - Rennes (France) 25-26 juin 2026 : Agile Tour Toulouse 2026 - Toulouse (France) 27 juin 2026 : Asynconf - Paris (France) 2 juillet 2026 : Azur Tech Summer 2026 - Valbonne (France) 2-3 juillet 2026 : Sunny Tech - Montpellier (France) 3 juillet 2026 : Agile Lyon 2026 - Lyon (France) 6-8 juillet 2026 : Riviera Dev - Sophia Antipolis (France) 28-30 août 2026 : State of the Map - Champs-sur-Marne (France) 4 septembre 2026 : JUG Summer Camp 2026 - La Rochelle (France) 10-11 septembre 2026 : Nantes Craft - Nantes (France) 17 septembre 2026 : dotAI - Paris (France) 17-18 septembre 2026 : API Platform Conference 2026 - Lille (France) 18 septembre 2026 : dotJS - Paris (France) 18 septembre 2026 : WordCamp Bretagne - Rennes (France) 22 septembre 2026 : Salon Data 2026 - Nantes (France) 22-23 septembre 2026 : Agile en Seine & IA 2026 - Paris (France) 24 septembre 2026 : OWASP AppSec Days France 2026 - Paris (France) 24 septembre 2026 : PlatformCon Paris - Paris (France) 24 septembre 2026 : React Native Connection 2026 - Paris (France) 24-26 septembre 2026 : Paris Web 2026 - Paris (France) 28-29 septembre 2026 : 4th Tech Summit on AI & Robotics - Paris (France) & Online 1 octobre 2026 : WAX 2026 - Marseille (France) 1-2 octobre 2026 : Volcamp - Clermont-Ferrand (France) 2 octobre 2026 : DevFest Perros-Guirec 2026 - Perros-Guirec (France) 5-9 octobre 2026 : Devoxx Belgium - Antwerp (Belgium) 12 octobre 2026 : Dev With AI - Paris (France) 27-29 octobre 2026 : Directions EMEA 2026 - Paris (France) 29-30 octobre 2026 : BDX I/O 2026 - Bordeaux (France) 30 octobre 2026 : Cloud Nord 2026 - Lille (France) 4-5 novembre 2026 : Devoxx Morocco - Casablanca (Morocco) 14-15 novembre 2026 : Capitole du Libre - Toulouse (France) 19 novembre 2026 : DevFest Toulouse 2026 - Toulouse (France) 27 novembre 2026 : DevFest Paris 2026 - Paris (France) 1-3 décembre 2026 : Apidays Paris - Paris (France) 4 décembre 2026 : DevFest Lyon 2026 - Lyon (France) 4 décembre 2026 : DevFest Dijon 2026 - Dijon (France) 9-10 décembre 2026 : OpenSource Expérience - Paris (France) 9-10 décembre 2026 : DevOps REX - Paris (France) 10 décembre 2026 : KCD Provence - Aix-en-Provence (France) 7-9 avril 2027 : Devoxx France 2027 - Paris (France) Nous contacter Pour réagir à cet épisode, venez discuter sur le groupe Google https://groups.google.com/group/lescastcodeurs Contactez-nous via X/twitter https://twitter.com/lescastcodeurs ou Bluesky https://bsky.app/profile/lescastcodeurs.com Faire un crowdcast ou une crowdquestion Soutenez Les Cast Codeurs sur Patreon https://www.patreon.com/LesCastCodeurs Tous les épisodes et toutes les infos sur https://lescastcodeurs.com/

Have you ever considered how a single server can support countless applications and workloads at once? In this episode, hosts Lois Houston and Nikita Abraham explore the sophisticated technologies that make this possible in modern cloud data centers. They discuss the roles of hypervisors, virtual machines, and containers, explaining how these innovations enable efficient resource sharing, robust security, and greater flexibility for organizations.   Cloud Tech Jumpstart: https://mylearn.oracle.com/ou/course/cloud-tech-jumpstart/152992 Oracle University Learning Community: https://education.oracle.com/ou-community LinkedIn: https://www.linkedin.com/showcase/oracle-university/ X: https://x.com/Oracle_Edu   Special thanks to Arijit Ghosh, Anna Hulkower, Radhika Banka, and the OU Studio Team for helping us create this episode.   ----------------------------------------------------   Episode Transcript:   00:00 Hi there! We're hitting rewind for the next few weeks and bringing back some of our most popular episodes. So, sit back and enjoy these highlights from our archive. 00:12 Welcome to the Oracle University Podcast, the first stop on your cloud journey. During this series of informative podcasts, we'll bring you foundational training on the most popular Oracle technologies. Let's get started! 00:38 Lois: Hello and welcome to the Oracle University Podcast! I'm Lois Houston, Director of Innovation Programs with Oracle University, and with me is Nikita Abraham, Team Lead: Editorial Services. Nikita: Hi everyone! For the last two weeks, we've been talking about different aspects of cloud data centers. In this episode, Orlando Gentil, Principal OCI Instructor at Oracle University, joins us once again to discuss how virtualization, through hypervisors, virtual machines, and containers, has transformed data centers. 01:11 Lois: That's right, Niki. We'll begin with a quick look at the history of virtualization and why it became so widely adopted. Orlando, what can you tell us about that?  Orlando: To truly grasp the power of virtualization, it's helpful to understand its journey from its humble beginnings with mainframes to its pivotal role in today's cloud computing landscape. It might surprise you, but virtualization isn't a new concept. Its roots go back to the 1960s with mainframes. In those early days, the primary goal was to isolate workloads on a single powerful mainframe, allowing different applications to run without interfering with each other. As we moved into the 1990s, the challenge shifted to underutilized physical servers. Organizations often had numerous dedicated servers, each running a single application, leading to significant waste of computing resources. This led to the emergence of virtualization as we know it today, primarily from the 1990s to the 2000s. The core idea here was to run multiple isolated operating systems on a single physical server. This innovation dramatically improved the resource utilization and laid the technical foundation for cloud computing, enabling the scalable and flexible environments we rely on today. 02:39 Nikita: Interesting. So, from an economic standpoint, what pushed traditional data centers to change and opened the door to virtualization? Orlando: In the past, running applications often meant running them on dedicated physical servers. This led to a few significant challenges. First, more hardware purchases. Every new application, every new project often required its own dedicated server. This meant constantly buying new physical hardware, which quickly escalated capital expenditure. Secondly, and hand-in-hand with more servers came higher power and cooling costs. Each physical server consumed power and generated heat, necessitating significant investment in electricity and cooling infrastructure. The more servers, the higher these operational expenses became. And finally, a major problem was unused capacity. Despite investing heavily in these physical servers, it was common for them to run well below their full capacity. Applications typically didn't need 100% of server's resources all the time. This meant we were wasting valuable compute power, memory, and storage, effectively wasting resources and diminishing the return of investment from those expensive hardware purchases. These economic pressures became a powerful incentive to find more efficient ways to utilize data center resources, setting the stage for technologies like virtualization. 04:18 Lois: I guess we can assume virtualization emerged as a financial game-changer. So, what kind of economic efficiencies did virtualization bring to the table? Orlando: From a CapEx or capital expenditure perspective, companies spent less on servers and data center expansion. From an OpEx or operational expenditure perspective, fewer machines meant lower electricity, cooling, and maintenance costs. It also sped up provisioning. Spinning a new VM took minutes, not days or weeks. That improved agility and reduced the operational workload on IT teams. It also created a more scalable, cost-efficient foundation which made virtualization not just a technical improvement, but a financial turning point for data centers. This economic efficiency is exactly what cloud providers like Oracle Cloud Infrastructure are built on, using virtualization to deliver scalable pay as you go infrastructure.  05:22 Nikita: Ok, Orlando. Let's get into the core components of virtualization. To start, what exactly is a hypervisor? Orlando: A hypervisor is a piece of software, firmware, or hardware that creates and runs virtual machines, also known as VMs. Its core function is to allow multiple virtual machines to run concurrently on a single physical host server. It acts as virtualization layer, abstracting the physical hardware resources like CPU, memory, and storage, and allocating them to each virtual machine as needed, ensuring they can operate independently and securely. 06:02 Lois: And are there types of hypervisors? Orlando: There are two primary types of hypervisors. The type 1 hypervisors, often called bare metal hypervisors, run directly on the host server's hardware. This means they interact directly with the physical resources offering high performance and security. Examples include VMware ESXi, Oracle VM Server, and KVM on Linux. They are commonly used in enterprise data centers and cloud environments. In contrast, type 2 hypervisors, also known as hosted hypervisors, run on top of an existing operating system like Windows or macOS. They act as an application within that operating system. Popular examples include VirtualBox, VMware Workstation, and Parallels. These are typically used for personal computing or development purposes, where you might run multiple operating systems on your laptop or desktop. 07:08 Nikita: We've spoken about the foundation provided by hypervisors. So, can we now talk about the virtual entities they manage: virtual machines? What exactly is a virtual machine and what are its fundamental characteristics? Orlando: A virtual machine is essentially a software-based virtual computer system that runs on a physical host computer. The magic happens with the hypervisor. The hypervisor's job is to create and manage these virtual environments, abstracting the physical hardware so that multiple VMs can share the same underlying resources without interfering with each other. Each VM operates like a completely independent computer with its own operating system and applications.  07:53 Lois: What are the benefits of this? Orlando: Each VM is isolated from the others. If one VM crashes or encounters an issue, it doesn't affect the other VMs running on the same physical host. This greatly enhances stability and security. A powerful feature is the ability to run different operating systems side-by-side on the very same physical host. You could have a Windows VM, a Linux VM, and even other specialized OS, all operating simultaneously. Consolidate workloads directly addresses the unused capacity problem. Instead of one application per physical server, you can now run multiple workloads, each in its own VM on a single powerful physical server. This dramatically improves hardware utilization, reducing the need of constant new hardware purchases and lowering power and cooling costs. And by consolidating workloads, virtualization makes it possible for cloud providers to dynamically create and manage vast pools of computing resources. This allows users to quickly provision and scale virtual servers on demand, tapping into these shared pools of CPU, memory, and storage as needed, rather than being tied to a single physical machine. 09:25 Do you want to boost your data management skills for free? The Oracle Data Platform Foundations Associate Learning Path covers everything from Autonomous Database to modern data architectures like lakehouse and mesh—and prepares you for the certification. Get started today by visiting mylearn.oracle.com. 09:50 Nikita: Welcome back! Orlando, let's move on to containers. Many see them as a lighter, more agile way to build and run applications. What's your take? Orlando: A container packages an application in all its dependencies, like libraries and other binaries, into a single, lightweight executable unit. Unlike a VM, a container shares the host operating system's kernel, running on top of the container runtime process. This architectural difference provides several key advantages. Containers are incredibly portable. They can be taken virtually anywhere, from a developer's laptop to a cloud environment, and run consistently, eliminating it works on my machine issues. Because containers share the host OS kernel, they don't need to bundle a full operating system themselves. This results in significantly smaller footprints and less administration overhead compared to VMs. They are faster to start. Without the need to boot a full operating system, containers can start up in seconds, or even milliseconds, providing rapid deployment and scaling capabilities. 11:08 Nikita: Ok. Throughout our conversation, you've spoken about the various advantages of virtualization but let's consolidate them now.  Orlando: From a security standpoint, virtualization offers several crucial benefits. Each VM operates in its own isolated sandbox. This means if one VM experiences a security breach, the impact is generally contained to that single virtual machine, significantly limiting the spread of potential threats across your infrastructure. Containers also provide some isolation. Virtualization allows for rapid recovery. This is invaluable for disaster recovery or undoing changes after a security incident. You can implement separate firewalls, access rules, and network configuration for each VM. This granular control reduces the overall exposure and attack surface across your virtualized environments, making it harder for malicious actors to move laterally. Beyond security, virtualization also brings significant advantages in terms of operational and agility benefits for IT management. Virtualization dramatically improves operational efficiency and agility. Things are faster. With virtualization, you can provision new servers or containers in minutes rather than days or weeks. This speed allows for quicker deployment of applications and services. It becomes much simpler to deploy consistent environment using templates and preconfigured VM images or containers. This reduces errors and ensures uniformity across your infrastructure. It's more scalable. Virtualization makes your infrastructure far more scalable. You can reshape VMs and containers to meet changing demands, ensuring your resources align precisely with your needs. These operational benefits directly contribute to the power of cloud computing, especially when we consider virtualization's role in enabling cloud and scalability. Virtualization is the very backbone of modern cloud computing, fundamentally enabling its scalability. It allows multiple virtual machines to run on a single physical server, maximizing hardware utilization, which is essential for cloud providers. This capability is core of infrastructure as a service offerings, where users can provision virtualized compute resources on demand. Virtualization makes services globally scalable. Resources can be easily deployed and managed across different geographic regions to meet worldwide demand. Finally, it provides elasticity, meaning resources can be automatically scaled up or down in response to fluctuating workloads, ensuring optimal performance and cost efficiency. 14:18 Lois: That's amazing. Thank you, Orlando, for joining us once again.  Nikita: Yeah, and remember, if you want to learn more about the topics we covered today, go to mylearn.oracle.com and search for the Cloud Tech Jumpstart course.  Lois: Well, that's all we have for today. Until next time, this is Lois Houston… Nikita: And Nikita Abraham, signing off! 14:37 That's all for this episode of the Oracle University Podcast. If you enjoyed listening, please click Subscribe to get all the latest episodes. We'd also love it if you would take a moment to rate and review us on your podcast app. See you again on the next episode of the Oracle University Podcast.

When markets move fast, nimble investors often see opportunity, not just noise. On this episode of Market Sense, Fidelity portfolio manager Adam Kramer reveals where recent volatility has created unusual potential opportunity among income-paying investments. Whether you're focused on generating income or managing risk, Adam explains how to spot unique mispricings when there's market dislocation. Plus, we dig into the headlines around the leadership transition at the Federal Reserve and what it could mean for markets going forward. Interested in researching mutual funds? Choose your criteria and get fund picks from Fidelity and independent experts. Read the full transcript View the slides Watch the video replay

Slide into our VMs to hear all about it.

We Slide into our VMs and give it a shot.

Slide into our VMs.

This guy would never! Slide into our VMs.

Is the housing market finally ready to rebound? On this episode of Market Sense, Fidelity leaders break down what's driving mortgage rates, pricing and inventory across the country. Plus, we'll dig into some viewer questions about adjustable-rate mortgage loans and rental properties all in 20 minutes. Buying or selling a home? From negotiation to closing, learn about all the steps along the way. Click here to get started. Read the full transcript View the slides Watch the video replay

Slide into our VMs.

We Slide into our VMs.

Slide into our VMs. They are off the chain today.

IMPACT Silver is weighing a restart of its Capire Mine with some help from new technology, says CEO Fred Davidson in an interview with Mining Stock Daily. The company is currently evaluating the use of XRT sensor-based sorting to improve margins at the VMS deposit by electronically separating ore from waste during bulk mining. While Capire remains on care and maintenance, the company maintains active production at the Zacualpan Mining Complex, supported by the recent discovery and extraction of the high-grade Kena vein. At the Plomosas Mine, management has suspended mining to optimize the underground design and is pursuing toll milling contracts with third-party miners to generate near-term cash flow.

Please visit answersincme.com/NYR860 to participate, download slides and supporting materials, complete the post test, and get a certificate. Presented by Jill Liss, MD, MSCP; Denise Black, MD, FRCSC; and Danielle Covarrubias. In this activity, experts in women's health, joined by a patient advocate, discuss the burden of menopause-related vasomotor symptoms (VMS) and novel management strategies. Upon completion of this activity, participants should be better able to: Identify the impact and burden of VMS as a consequence of menopause; Outline the clinical rationale for novel therapeutic approaches to manage menopause-related VMS; Evaluate the efficacy and safety of novel neurokinin-targeted therapies for treating menopause-related VMS; and Implement patient-centered clinical approaches to improve outcomes for patients experiencing menopause-related VMS.

Slide into our VMs.

In this episode of the Pure Report, we sit down with longtime colleague Robert Quimbey, Consulting Field Solution Architect, known to many as "Q." Q shares with us how his role has evolved from a back-end problem solver focusing on Microsoft integrations to a customer-facing strategist dedicated to understanding the entire solution set for customers, not just fixing siloed problems. Drawing on his deep history with Microsoft technologies, including his time on the Exchange team, Q discusses Everpure's strategic moves to simplify the modern data center. Our conversation dives into two major capability developments: ActiveCluster for File and Azure Local. ActiveCluster for File is designed to provide high availability for file services, inheriting the core benefits of the original Everpure ActiveCluster— with ease of setup and no extra licensing costs—while solving hard problems in the file space. Q explains how ActiveCluster for File implements file storage at a cousin layer to block storage, avoiding the performance and scalability issues common in competing solutions. The new capability includes continuous availability to ensure persistent sessions for VMs on SMB shares, even during non-disruptive upgrades, and is launching right as the NAS market is projected to nearly double, driven largely by AI-related unstructured data growth. Next, we explore Azure Local, formerly Azure Stack HCI, a project Q has championed for years. This initiative is key to customers looking to modernize their virtualization strategy. The new integration, which is near GA, allows customers to connect virtual machines and containers directly to FlashArray via Fibre Channel (FC), avoiding the complexities of HCI storage. Ultimately, the focus remains on the power of the core Purity foundation to deliver agility, predictable costs (like Evergreen//One), and superior performance for all hybrid-cloud workloads. To learn more, visit: https://blog.purestorage.com/products/microsoft-azure-local-and-flash-array/ and https://blog.purestorage.com/products/introducing-activecluster-for-file/ Check out the new Everpure digital customer community to join the conversation with peers and Pure experts: https://purecommunity.purestorage.com/ 00:00 Intro and Q's Career Journey 07:17 Key Development Projects 09:59 Stat of the Episode on NAS Storage 12:51 ActiveCluster for File Discussion 27:45 Protocols and Arrays Supported 34:19 Intro to Azure Local 53:04 Hot Takes Segment

...and cries a bit. Slide into our VMs.

It's very suspicious, Slide into our VMs.

Slide into our VMs.

Slide into our VMs.

Early bird discounts for the San Francisco World's Fair, the biggest AIE gathering of the year, end today - prices will go up by ~$500 tonight so do please lock in ASAP!From near-universal AI tool adoption inside Shopify to internal systems for ML experimentation, auto-research, customer simulation, and ultra-low-latency search, Mikhail Parakhin joins us for a deep dive into what it actually looks like when a 20-year-old, $200B software company goes all-in on AI. We cover why Shopify has become much more vocal about its internal stack, what changed after the December model-quality inflection, and why the real bottleneck in AI coding is no longer generation, but review, CI/CD, and deployment stability.We also go inside Tangle, Tangent, SimGym, which are three major AI initiatives that Shopify is doing to make experimentation reproducible, optimization automatic, customer behavior simulatable, and search and catalog intelligence faster and cheaper at scale. Along the way, Mikhail explains UCP, Liquid AI, and why token budgets are directionally right but often measured badly, why AI-written code can still increase bugs in production, what makes Shopify's customer simulation defensible, and what he learned from the Sydney era at Bing.We discuss:* Mikhail's path from running a major Microsoft business unit spanning Windows, Edge, Bing, and ads to becoming CTO of Shopify* Why Shopify is talking more publicly about AI now, and why staying at the frontier has become necessary for the company* Shopify's internal AI adoption curve, the December inflection, and why CLI-style tools are rising faster than traditional IDE-based tools* Why Jensen Huang is directionally right on token budgets, but raw token count is still the wrong way to evaluate engineering output* Why the real unlock is not more agents in parallel, but better critique loops, stronger models, and spending more on review than generation* Why AI coding can still lead to more bugs in production even if models write cleaner code on average than humans* Why Shopify built its own PR review flow, and why Mikhail thinks most off-the-shelf review tools miss the point* How PR volume, test failures, and deployment rollback are becoming the real bottlenecks in the agent era* Why Git, pull requests, and CI/CD may need a new metaphor once code is written at machine speed* What Tangle is, and how Shopify uses it to make ML and data workflows reproducible, collaborative, and production-ready from the start* Why Tangle is different from Airflow, and why content-addressed caching creates network effects across teams* What Tangent is, and how Shopify is using auto-research loops to optimize search, themes, prompt compression, storage, and more* Why Tangent is becoming a democratizing tool for PMs and domain experts, not just ML engineers* Why AutoML finally feels real in the LLM era, and where auto-research still falls short today* Why Tangle, Tangent, and SimGym become much more powerful when combined into one system* What SimGym is, why simulated customers only work if you have real historical behavior, and why Shopify's data gives it a moat* How SimGym evolved from comparing A/B variants to telling merchants what to change on a single live storefront to raise conversions* Why customer simulation is so expensive, from multimodal models to browser farms to serving and distillation costs* How Shopify models merchant and buyer trajectories, runs counterfactuals, and thinks about interventions like discounts, campaigns, and notifications* Why category-level behavior is so different across commerce, and why ideas like Chinese Restaurant Processes are showing up again in practice* Shopify's new UCP and catalog work, including runtime product search, bulk lookups, and identity linking* Why Shopify is using Liquid AI, and why Mikhail sees it as the first genuinely competitive non-transformer architecture he has used in practice* Where Liquid already works inside Shopify today, from low-latency query understanding to large-scale catalog and Sidekick Pulse workloads* Whether Liquid could become frontier-scale with enough compute, and why Shopify remains pragmatic and merit-based about model choice* Who Shopify is hiring right now across ML, data science, and distributed databases* The Sydney story at Bing, why its personality was not an accident, and what Mikhail learned from deliberately shaping AI character early onMikhail Parakhin* LinkedIn: https://www.linkedin.com/in/mikhail-parakhin/* X: https://x.com/MParakhinTimestamps00:00:00 Introduction: Mikhail Parakhin, Microsoft, and Shopify00:01:16 Why Shopify Is Talking More About AI00:02:29 Internal AI Adoption at Shopify and the December Inflection00:06:54 Token Budgets, Jensen Huang, and Why Usage Metrics Can Mislead00:10:55 Why Shopify Built Its Own AI PR Review System00:12:38 AI Coding, More Bugs, and the Real Deployment Bottleneck00:14:11 Why Git, PRs, and CI/CD May Need to Change for Agents00:18:24 Tangle: Shopify's Reproducible ML and Data Workflow Engine00:21:19 Why Tangle Is Different from Airflow00:26:14 Tangent: Auto Research for Optimization and Experimentation00:30:07 How Tangent Democratizes Experimentation Beyond ML Engineers00:33:06 The Limits of Auto Research00:36:36 Why Tangle, Tangent, and SimGym Compound Together00:37:20 SimGym: Simulating Customers with Shopify's Historical Data00:42:47 The Infra Behind SimGym00:46:00 Why SimGym Gets Better with Real Customer History00:47:30 Counterfactuals, HSTU, and Modeling Merchant Trajectories00:51:55 CRPs, Clustering, and Category-Level Customer Behavior00:53:30 UCP, Shopify Catalog, and Identity Linking00:55:07 Liquid AI: Why Shopify Uses Non-Transformer Models00:59:13 Real Shopify Use Cases for Liquid01:03:00 Can Liquid Scale into a Frontier Model?01:09:49 Hiring at Shopify: ML, Data Science, and Databases01:10:43 Sydney at Bing: Personality Shaping and AI Character01:13:32 Closing ThoughtsTranscript[00:00:00] swyx: Okay. We're here in the studio, a remote studio, with Mikhail Parakhin, CTO of Shopify. Welcome.[00:00:08] Mikhail Parakhin: Thank you. Welcome.[00:00:10] swyx: I don't even know if I should introduce you as CTO of Shopify. I feel like you have many identities. Uh, you led sort of the, the Bing ML team, I guess, uh, uh, or ads team. I, I don't know, I don't know, uh, you know, it's, uh, people va-variously refer you as like CEO or, or, uh, I don't know what that, that, that said previous role at Microsoft was.[00:00:29] Mikhail Parakhin: Uh, that was... Yeah, my previous role w- at Microsoft was the-- I actually was the CEO of one of Microsoft's business units, which included, as I, you know, as we discussed, all the things that people like to laugh about, uh, including Windows and Edge and Bing and ads and everything.[00:00:47] swyx: Yeah, yeah. What a, what a, what a wild time.You've obviously, uh, done a lot since you landed at Shopify. Uh, one of the reasons I reached out was because you started promoting more sort of internal tooling, uh, primarily Tangle, but also a lot of people have seen and adopted Tobi's QMD, uh, and obviously, I think, uh, Shopify has always been sort of leading in terms of, uh, engineering.I think more-- it's just more recent that you guys have been more vocal about your sort of AI adoption. Is that, is that true?[00:01:16] Mikhail Parakhin: Well, I think AI tools in general are fairly recent development, uh, and we've-- Shopify, you know, at this stage of its development, we're developing AI in-in-house and other, uh, building tools that use AI and, you know, interfacing with the wider AI community, uh, you know, are on the sort of the, uh, runaway trajectory.So it just did by sort of natural byproduct. We, we talk about it more also. We just, uh, just even yesterday, Andrej Karpathy was famous in tweeting about, oh, are there some, uh, ways, uh, that, that you can organize your agents to store the data and then, uh, look up the data so that you don't have to research or, or lose context every- Yestime. And a little bit tongue in cheek, I tweeted that, “Hey, we've, we've done it much earlier, and we even have different approaches, Tobi and I.” Tobi, of course, is a big fan of QMD, and I'm more of a SQL, SQLite fan. But, uh, yeah, very similar things that we've already done here. The point is, yeah, we're very dynamic, you know, explosively growing company, and we have to be at the forefront of AI adoption, obviously.[00:02:29] swyx: Yeah. Yeah. Um, you, your team kindly prepared some slides actually that we were gonna bring up on to, uh, the screen. I think I can, I can screen share, and then we can kind of go through some of the shocking stats that maybe, maybe put some numbers to what exactly is going on. So here we have, uh- An internal AI tool adoption chart.What are we looking at here? What ?[00:02:54] Mikhail Parakhin: Yeah, this is very interesting statistics. Uh, this is number of daily active workers, you know, think of, uh, DAO, basically the active users of-[00:03:05] swyx: Yeah ...[00:03:05] Mikhail Parakhin: AI tool as a percentage of all the people in the company, right? And then- Yeah ... different AI tools. And, uh, you could see two things here is that one is the green is total.Uh, green is just total. So you could see that it approaches really % by now. It's hard not to do your job now without interacting deeply, at least with one tool. You could see another interesting thing is just as many people commented in December was the phase transition when suddenly models gotten good enough that, that everything took off and started growing.Uh, it, it was many people noticed that the thing is that small improvements accumulated into this big change in Sep- December roughly timeframe.[00:03:52] swyx: Yeah.[00:03:52] Mikhail Parakhin: The other thing I would claim you could see is that, uh, CLI-based tools and tools that don't require you to look at the code becoming more popular, and you could see, yeah, various versions of, uh, Cloud Code and Codex and Pi and internal development tools taking off.Uh, exactly, yeah, uh, and blue is our River, just internal agent for coding, where tools, uh, that require IDEs such as, uh, GitHub, Copilot or Cursor, they're not exactly shrinking, but they're not growing as fast. Like, uh, red, red line is, is the IDE kind of tools. So you could see that they're, they're not experiencing as, as fast of a growth.[00:04:37] swyx: As I understand it, basically, every employee has their choice, right? Of choose whatever tool you use, and then you're just kind of doing a, a daily sur-survey or something.[00:04:47] Mikhail Parakhin: Exactly. And, uh, we- Yeah ... the, the push is to get your job done, you can use any tool, and we effectively fund unlimited tokens for everybody.Uh, we, we do, we do try to control the models that, uh, people use, but from the bottom, not from top. Like we basically say, “Hey, please don't use anything less than Opus four point six.”[00:05:09] swyx: Oh .[00:05:10] Mikhail Parakhin: Some people, some people end up using GPT five point four extra high. Some people use Opus four point six. Um, uh, you know, uh, there are some, uh, there are plus and minuses in going for full one million context window versus not.But, uh, we try to discourage people from using anything less than that.[00:05:28] swyx: Yeah, yeah. Got it, got it. Uh, I mean, uh, that's, you know... The, the next chart here, it really kind of shows the expansion and the sort of December twenty twenty-five inflection, right? That, uh, people are using a lot of tokens. I think it's also really interesting that no one was kind of abusing it in twenty twenty-five.Like it was- Had comparatively, uh, to this year, there was almost no growth. I mean, it's still like, you know, probably, probably gave fifty percent.[00:05:56] Mikhail Parakhin: Yeah. This is just a different scale. It's still exponential- Yeah, yeah ...growth at just a different- ...rate of expansion. Uh, there was inflection point, and Sean, I would claim the, the super interesting part here is that you could see that the distribution becoming more and more skewed.Yes. The top percentiles grow faster. So that means- Yeah ...the people in the top ten percentile, they, their consumption grows faster than seventy-five and so forth. So, uh, the distribution skews more and more towards the highest users, which is... I don't know what it tells me. It's like it feels not ideal, to be honest.Or maybe it's okay. We'll see.[00:06:36] swyx: Why does it feel not ideal? Is, is it because of, um, quantity over quality, or what's the concern?[00:06:42] Mikhail Parakhin: Because take it to the limit. That means, you know, if, if this rate of separation continued- Ah, yes ...a year, there will be one person consuming all the tokens. So it's just, it's kinda strange.[00:06:54] swyx: Yeah, I mean, um, uh, I, I think internal like teaching and all that, uh, will, will help sort of distribute things more widely. But in, in the early days, of course, the people who are sort of more AI-pilled will obviously find more ways to use it than the people who are less AI-pilled. Maybe let's, let's call it that.I'll just, I'll just kinda quickly, uh, pause from the, the... You know, we will go back to the rest of the slides, but I just wanna, um, review, you know, there are a lot of CTOs of, of large companies like yourself where they're all considering some kind of token budget, right? Like I think it's something, something that Jensen Huang has been talking about, where like if your 200K engineer is not using 100K of tokens every year, like they're, they're underutilizing coding agents.Of course, Jensen Huang would say that, but like it seems a very quantity over quality approach and like some, some people are basically saying like, well, is this comparable to judging engineer quality by lines of code, right? Which we also know is like kind of flawed, but better than nothing. So I, I don't know if you have like a sort of management take here on, on how to view this kind of, uh, metrics.[00:08:02] Mikhail Parakhin: Well, I mean, you're, you're baiting me. I, I like... This is my favorite topic. Uh, if you let me, I'll probably talk for two hours on just this. I have a lot of things to say. Like I do think Jensen gotten a lot of bad press saying, “Oh, of course you're, you know, this, uh, the- ...the cake seller says you don't need enough cakes.”You know? Like, of course. Uh, but, uh, I actually, uh, think that's undeserved. I think he, he's actually right. Uh, I do think- He,[00:08:33] swyx: he's directionally correct.[00:08:35] Mikhail Parakhin: Yeah. Yeah. He's directionally correct for sure. Uh-[00:08:37] swyx: Who knows what the right number is? Yeah.[00:08:39] Mikhail Parakhin: The thing that I do Uh, want to say, and this is something that we learned through trial and error and very important is like two things.One is that it's not about just consuming tokens. Uh, you can consume tokens and, and in fact, the anti-pattern is running multiple agents, too many agents in parallel that don't communicate with each other. That's almost useless, uh, compared to just fewer agents and burns tokens very efficiently. Uh, setting up the right critique loop, especially with the high quality models, where one agent does something, the other one, ideally with a different model, critiques it, uh, suggests ways to improve it, the agent redoes it with this critique and, and so it takes much longer.So people don't like it because latency goes up. You know, they, they have to wait until this debate is happening. But, uh, the quality of the code is much higher. And another thing, just since you mentioned like, look, uh, uh, yeah, the overall budget is just like, uh, lines of codes. Lines of codes are exploding for everybody right now, or partially because AI is really mover balls, but partially just because AI can write a lot more code, you know, doesn't get tired.And so you have to have to have a very strong narrow waist during PR review. Otherwise, just the number of bugs will go through the roof. It's, uh, it's this unexpected consequence of the just volume trumping everything. I would claim by now good model writes code on average with fewer bugs than, than the average human.But since they write so much more of it, like more of it will make it into production. So you have to- You still[00:10:26] swyx: have[00:10:26] Mikhail Parakhin: more bugs. Yeah. Have to have a very rigorous PR reviews, also automated of course. But, uh, yeah, that to spend a lot budget there. Like this, this for me, for me, actually, the important metric is the ratio of budget spent during code generation versus, uh, spent, uh, expensive tokens like GPT, uh, five point four Pro or, uh, uh, Deep Think from Gemini, you know, checking on PR reviews.[00:10:55] swyx: Yeah, totally. Uh, I noticed in your chart you didn't have any review tools. Do you just use like, like let's say a Claude code to review tools? Or do you have another set of review tools like the Greptiles, the Code Rabbits, uh, Devin Reviews has a review tool. I don't know if you've had those specialist review tools.[00:11:13] Mikhail Parakhin: You are a little bit jumping on my store tool right now because the graphs I was only showing public tools. Uh, uh, the-- I haven't found a good PR review tool that, that does what I think should be done. And, uh, partially my, my thinking is because it's so... It just goes against both what people feel like emotionally they prefer and, uh, some of the, uh, you know, frankly Even business models that, that the companies run.At peer review tool, uh, time, you want to run the largest models. That means, I don't know, Codex or, or, uh, Cloud Code is not gonna cut it. You need to have pro-level models if you really want to, uh, stand the tide of bots from going into production. And you need us to spend a lot of time, the models taking turns, but you don't want, like, a big swarm of, uh, of, uh, agents.So in fact, you end up in a different dual-dualistic world where you generate not that many tokens. You, in fact, generate few tokens, but it takes f-a long time because these are expensive models taking turns rather than many, many agents trying to do many things in parallel. So that's, that's why I feel like I haven't found good tools, so we are using our own for peer review for now.[00:12:33] swyx: Yeah. Yeah. I mean, uh, I think a lot of companies are building their own, uh, especially to their needs, right?[00:12:38] Mikhail Parakhin: Mm-hmm.[00:12:38] swyx: Um, I, uh, you also have a chart here going back to the slides on, uh, PR merge growth, where we're now at thirty percent, uh, month on month rather than ten percent. Uh, and also the, the estimated complexity is going up.You know, this is productivity, right? ‘Cause y- presumably there's more stuff going into the code base and more, more features getting worked on. I'm curious about the backlog, right? Like the, the, the-- I actually don't mind a pro-level model taking an hour or two hours to review my PR, because I've dealt with humans who take a week to review my PR, right?And I keep pinging them on Slack, “Hey, hey, review my PR.” So, you know, I think there's some trade-off here where, like, it still doesn't make sense.[00:13:18] Mikhail Parakhin: Exactly. That, that's exactly m-my point. Uh, that on one hand, you can tolerate longer latencies at, uh, PR. On the other hand, like right now, the real problem is not in spending time waiting for PR.It's real problem is since there's so much more code than- Yeah ... uh, probability of at least some tests failing going up, and then you, like, keep de-failing, then you have to find the offending PR, evict it, retest it without that PR, and so deployment cycle becomes much longer. Uh, so it actually, in terms of the overall time to deploy, it's total time savings if you spend more time on a longer model, like thinking for an hour, because then, then you, you don't have to spend all that time during testing and rolling, you know, rolling back the deployment.[00:14:03] swyx: Yeah, totally. That's still worth it. You know, you don't look at the individual, look at the aggregate, and look at the, the, the change in the aggregate system.[00:14:11] Mikhail Parakhin: Exactly.[00:14:11] swyx: I'm kind of curious if, like, there's this PR mentality and, like, c-- the, the, the CICD paradigm will be changed eventually. Some people are like, obviously a lot of people want new GitHub, but I even wonder if, like, Git is the problem, right?Like, is that the bottleneck? Is the concept of a PR a bottleneck? Do you guys use stack diffs? I don't know if, uh, that's a, like, a merge queue stack diff type of thing.[00:14:34] Mikhail Parakhin: We, we use, we use Stacks, we u- we use Graphite. We worked with, uh, Graphite a lot. Uh, so we use Stack, uh, PRs. I think, uh, like that's clearly the overall CICD in general, and the interaction with the code repository right now is the, clearly the sort of the, the main issue and the bottleneck for us, uh, and highest top of mind.I would say we probably need a different metaphor or different whole design of how to process it in new agentic world. I haven't seen anything dramatically better yet. I, I think everybody right now is just trying to keep their head above the water ‘cause, ‘cause there, there's so many PRs and then everybody's CICD pipelines start creaking, the, the times are increasing, the number of bugs slipping by increasing, and you have to, have to clap on down.And so we are a little bit in this situation when we need to first stabilize that story and then start thinking, hey, what, what it could be a completely different and new world, which I haven't... I know some people working on it. I haven't seen something, like anything super compelling yet, but clearly the old thing were designed for humans will need to be morphed into something new.[00:15:53] swyx: One of the thing that I, I think about is kind of like the merge conflict is basically a global mutex on the whole system, right? And in, in hu- in human organizations, we do have something like that. It's the company standup. But like, other than that, it's like it's actually fitting for us to be somewhat decentralized, somewhat plugged into one stream of information source, but somewhat lossy.Like it's okay, you know, that, that not every delivery is like atomic consistency. Like we're not dealing with a database sometimes.[00:16:27] Mikhail Parakhin: This is a very good point, uh, because since humans don't write code too fast, you know that global mutex is not too bad. Once you-[00:16:36] swyx: Yes ...[00:16:37] Mikhail Parakhin: start writing code at the speed of machine, it becomes the, you know, the bottleneck.Then what do you do? Maybe, and I can't believe I'm saying this because I, I'm long-- lifelong opponent of, uh, microservices, and I always thought that was, like, a really bad idea. And now that you're saying it, like, maybe in new guys like microservices will make a comeback, you know, because then you, you can ship things independently in tiny things and, and the managing all that complexity automatically will be much easier.I don't know. Like, we'll s-- we'll have to see.[00:17:10] swyx: Yeah. I mean, I don't know what the Microsoft or, or Shopify thing is, but I, I read this paper from Google where they have a monorepo that deploys into microservices, right? And then, uh, the other concept that I think about a lot is the Chaos Monkey concept from, from Netflix.Being able to create, like, this robust system where, um, uh, you know, you, you have the service discovery, you have the, uh, the independent, independent microservices discovery and, and, uh, you know, probably going to be a fair amount of duplication. That's how an organic system sort of scales, uh, that, that you have that...I don't know how you call it. Slack? Robustness? Depend-- uh, d-duplication. I, I, I forget the-- I, I'm-- And this-- those-- these are not exactly the terms- Hmm ... I'm looking for, but I c-can't really think of the words. Okay. I was gonna go into Tangent and Tangle. Uh, so, uh, we, we sort of discussed the overall stats that, uh, Shopify has.Uh, but, you know, I, I think some, some pretty cool stuff that you guys are working on is your ML experimentation, uh, and your, your sort of auto tr-research training pipeline. Presumably you're much closer to this one because it's, it's a sort of personal hobby of yours. How, how would you explain them in, together?I thought we have a slide that, like, uh, has the s- the system diagram.[00:18:24] Mikhail Parakhin: Yeah. Tangle first and then Tangent as a-[00:18:27] swyx: Yeah ...[00:18:28] Mikhail Parakhin: as a thing on top of Tangle. And, uh, Tangle is the third generation, I claim, of, uh, systems of, uh, running any data processing, but a bit with a skew for ML experiments, but not necessarily. Any sort of data processing tasks where you need to iterate, share, and you have scale so that you want maximum efficiency.You know how, like, normally you would work, you would-- Imagine you're a data scientist or an ML practitioner, you would get Jupiter notebooks or, or maybe you would get, uh, you know, Pyth- your Python scripts, and you would manage the data, and you produce those TSV files, and you put them in some JFS or something.Then you would notice that, oh, it has this, uh, weird missing values. You go and write another script that, uh, goes and replaces them with, uh-[00:19:20] swyx: Ah ...[00:19:21] Mikhail Parakhin: dash S. And then, then you, then you run some, some, uh, “Oh, I need to filter bots.” And so you run some light GBM model that, uh, removes the bots. And then, then you like-- And then you, you kind of like get into shape, and then you start experimenting, and you run multiple experiments, and then you're like, “Oh my God,” like, “this experiment is worse.”You undo, and you cannot get to previous result. And like, “Ah, what did I do?” Like that. Again, then, then you finally like get everything working. Then you like start throwing it over the fence to production. You, you replicate it, those things don't work, and then sometimes you like don't notice that you forgot some feature naming and the, the features don't match.But then, like imagine you, you did everything, and then six months later you're like, have to repeat it because now there's more data, or you wanted to do another pass, and you're like, “What, what did I do?” Or like, or like, “This script crashes now,” or the, “the path has changed.” And then, then you're trying to, like you spend another month just doing ar- digital archeology on your own, you know, history, right?Now multiply that by many, many teams. Now imagine you got an intern that you wanna ramp up. Now you have to show that intern, “Oh, you know, look, here's the folder, there's the scripts, you know, ask your cloud agent to do, and then, uh, to, to figure it out.” And then cloud agent does something, and then you're, “Ah, yeah, right, right, it was the wrong folder.I forgot to tell you, I actually have this other thing I forgot myself.” And, and that's, that's the, like, the daily life we all, uh, all know it, uh, if, if you're a data scientist, machine practitioner, ma- machine learning practitioner or, uh, or even like any data managing, uh, person.[00:21:00] swyx: Yeah. So I, I used to do this, uh, f- uh, on the quant finance side, uh, in, in my hedge fund.So we did this before Airflow, and then, uh, obviously Airflow came along and, uh, then more recently Dagster, uh, I would say is like, in my mind, what I would use for that shape of problem, uh, where you had to materialize assets and create a pipeline.[00:21:19] Mikhail Parakhin: And that's, that's very good segue because... So Airflow is great, but Airflow is more about you, you have something and you wanna repeatedly run it in production on schedule.It's less about you as a team developing things and being able to share, and you grabbing the standard pipeline and saying, “Hey, I wanna change this tiny little component in the huge sea of data processing, and I don't wanna-- I wanna run ten experiments on this, and I wanna do hyperparameter optimization.”All that is very hard to do with Airflow. It's very easy to do with Tango. Tango is m- more about, it's everything about group of people Running experiments, it might be agents too nowadays. Uh, running experiments cheaply, collaborating, sharing results. Uh, you don't need to understand fully. You, you grab-- you clone somebody else's experiment or somebody else's pipeline, uh, run, uh, change small piece, run it, be, like, get it to production state, and then ship in one click.So then the... You don't have to port it into any other system to, to run in production. You can just run the same experiment. It's, it's fully production ready. And, and it's, uh, it has lots of... Again, as I said, it's third generation system. The original one was, I would claim there was Ether and then, uh, at least in my career, Ether was the first, first, uh, that pioneered this type of approach.And then there was, uh, Nirvana, which, uh, uh, at Yandex, which did kind of sec-second take on this. And now this one aggregates the, the learnings from all of those and, and Airflow as well to, to get to the state where you try it, it, it feels kind of magical. Uh, ‘cause now everything is based on content, uh, hashes.So even if the version changed, but if the output didn't change, nothing is being rerun. It's very efficient. If you... Multiple people start experiment that needs the same sort of data preprocessing, it's not repeated multiple times. It's automatically done only once. If you start ten experiments that all require, you know, some, some data preparation first as the first step, and you don't have to coordinate for that.Like, you don't have to know that other people are starting it. You now, it's very easy compos-, uh, composability, any language you can u- uh, you wanna use, and it's very visual. So you can see immediately, you can edit it easily, you can assemble small things with just even mouse clicks if you want to, and, uh, share, clone.And everybody knows also it's fully kind of static in the sense that we rerun it second time, it will exactly have the same results. Like, you will never have to do digital archeology. So full versioning and everything is also there.[00:24:06] swyx: Uh, so, so people can, uh... It's open source. Go to the GitHub repo and, and, uh, check it out.Uh, and it is also a really good, uh, blog post about it. I think all these is, like, really appealing. The, the, the, the thing that I think sells me the most about it is that, um, sort of development to production transition, right? Which I think, um, a lot of people haven't really solved that, uh, strictly, right?Like, we develop really, really well in, in Python notebooks, but then, you know, that's obviously not a sort of production ready process. I think that, like, any way in which that is solved, I think is, is very appealing. Then the other thing that you mentioned, which also raised my eyebrows, was content-based caching, which you mentioned is, is, um, you know, is ve-very much, uh, um, a sort of efficiency measure about, uh, you know, just like recalculation only on, on sort of content addressing Which I think makes sense.Uh, it surprised me that the savings could be this much, but maybe I just haven't worked at your scale where there's so much duplication, uh, that people just rerun because they change a single ID upstream.[00:25:10] Mikhail Parakhin: It does, yeah. But it's not only you rerun. The, the main savings are coming from the fact that you ran it, you got your job done, and you moved on.Then- Yeah ... somebody else in some department you don't know existed runs the same task, but on a newer version.[00:25:27] swyx: Yeah.[00:25:27] Mikhail Parakhin: Like right now, you can't, in, in most of the organizations, you can't even find out about it so that you can't even measure that you're spending that time twice, right? Here- Yeah ... if everybody's on Tango, that's detected automatically and detected that the output is the same.And then for that person, all it looks like is like experiment just suddenly moved, jumped forward, right? Uh, uh- Yeah ... so that's because, because the, there's network effect of multiple people helping each other.[00:25:51] swyx: Yeah. This is one of those things where it's designed to be a platform from the beginning rather than an individual developer's tool from the beginning, right?And, and everything's gonna streams down from there. That is the sort of Tango, uh, orchestrator, and it's, it manages jobs. We've seen a few versions of this, and this is obviously, uh, uh, the sort of, uh, unique approaches that you guys have, have, uh, figured out. And then there's Tangent.[00:26:14] Mikhail Parakhin: Yeah. And Tangent is basically an automatic auto research loop that can help and kind of do your work for you.Uh- ... you know, uh, effectively, effectively, Andrej Karpathy recently popularized it with auto research. Yes. Remember he said like he was, uh, speed running this, uh... Yeah, uh, you know the story. The, here we're basically bringing the same capability into Tango so that, uh, the, uh, Tangent can analyze it. It's just an agent that can run multiple experiments, figure out what can be changed, and keep on rerunning it, keep on modifying until, uh, maximizing some goal, some loss function, whatever you need to, to achieve.And in general, I would say if you're not using auto research-like approach in whatever you do, like literally whatever you do, then you're missing out. We saw at Shopify that taking like a wildfire, anything where you can put measurements can be done dramatically better. Our-[00:27:19] swyx: Mm-hmm ...[00:27:20] Mikhail Parakhin: uh, speed of, uh, templatization HTML, uh, completely new UX tem- uh, templatization of, uh, reducing latency for liquid themes.Uh, we-- Our, uh, search, uh, recently we moved from It's hard even, uh, quote from eight hundred QPS to forty-two hundred QPS with the same quality just by pure optimizations and not a research loop that kept running and changing code in our index serve on the same number of machines, just increasing the throughput.We, we managed to improve the quality of gisting and machine learning process. Uh, you know, gisting is the prompt compression technique that[00:27:59] swyx: allows for[00:28:00] Mikhail Parakhin: lower latency and, and lower and, uh, actually higher quality slightly. So like literally whatever different walks of life, and it doesn't have to be AI related.Uh, we, we had a reduction in, uh, storage because the agents would go and find data sets that clearly are derivative, uh, and then you don't need to store things twice. You know, we, we, we found somewhat embarrassingly that it was one of the largest tables was hashing random IDs into another random ID, and we literally- Oofput only one. So it was translating, yeah, two random IDs hashed[00:28:36] swyx: into[00:28:37] Mikhail Parakhin: each. So, so[00:28:37] swyx: it has access to the code as well, so it can, it can check the, like what, what the hell is it doing?[00:28:42] Mikhail Parakhin: So there, there cou- it could be run in two levels. You, uh, you know, at the superficial level, it could just use ex-existing components and, uh, reshuffle them.Uh, you know, like you can grab- Yeah ... uh, XGBoost, and you can grab some, some Py- PyTorch module, and then can grab some, you know, grab another tools and, and combine them. At a deeper level, since Tangle is all sort of CLI based underneath you, every, every component is a wrapped really CLI, uh, call and a YAML file, it can analyze code and create new components and, and, uh, keep on iterating as well.So, so you can, you can both have quick modifications of existing t- uh, pipelines with the, with components that are already there pre-baked, or you can create new components, uh, and-[00:29:29] swyx: Yeah ...[00:29:29] Mikhail Parakhin: keep iterating on those. So auto research is, again, this is probably the, the thing I was excited the most in the last two months happening, and we see it taking like, like totally like a wildfire.Just, uh, everybody, every day, every... well, every day, every minute, I would, uh, have somebody Slack message saying, “Oh, look how much better I made it.” And, uh, it's all throughout the research.[00:29:53] swyx: Is this democratized in some way in, in the sense that like is it your ML, uh, engineers and researchers doing this, or is it your regular PMs and software engineers also have the ability to auto-- to use Tangent?[00:30:07] Mikhail Parakhin: This is an awesome question. Like, Tango in general and Tangent in particular are extremely democratizing. Like they- Yeah ... they are the main tools for- ‘Cause I don't[00:30:15] swyx: need the details.[00:30:16] Mikhail Parakhin: Yeah. Exactly. Initially used by ML and AI engineers, but then literally, as you said, PMs are like the highest user right now is one of PMs on our org, uh, Sartak and he was, he was number one by, by usage of, of this ‘cause they're just, uh, energetic and knowledgeable, and now it, it unlocks a lot of capability where you don't have to co-change code manually.[00:30:39] swyx: I mean, I mean, because it kind of cuts out the ML, ML engineer from the process because the, the, the PMs have the domain knowledge and the ability to think about, uh, from first principles about, okay, what, what results do I want? And they can-- they even have the access to the data that, that needs to go in.So it's like in some ways, like this is the magic black box that we've always wanted for, for training and, and for, uh, I guess, uh, uh, hill climbing, whatever.[00:31:04] Mikhail Parakhin: It's basically cloud code for your AI development- ... uh, situation, right? Like now, now you don't have to know exactly how algorithms work. You can just, uh, bring your domain knowledge and expertise and product knowledge and iterate within Tangent until you've gotten the results that you need.[00:31:21] swyx: In my previous roles, every time that someone has pitched AutoML, you know, I've always been like, “Uh, this is not, this is not gonna work. It's, you know, it's, it's always gonna be a flop.” Somehow it's working now. I mean, presumably the answer is now we have LLMs and it's good enough, right? It's, it's an emergent property that we can do auto research, but like, it doesn't feel that satisfying that how come we didn't do this before, right?Like we just did like parameter search and like, I don't know. That's maybe that's it.[00:31:48] Mikhail Parakhin: Yeah. Bayesian optimization and hyperparameter optimization was, was the one that, or facet of AutoML that was used very actively, which incidentally also built into, uh, Tango. But, you know, I know Patrice Simard very well, and, uh, he was such a, uh, such a proponent of AutoML, and he put, like literally spent careers trying to democratize it.Without LLMs, it just turned out to be very hard. Like it, you, you would have flexibility within certain narrow domain, but it was hard to wider scale, and now with LLMs suddenly it's like magic wand, and so suddenly everybody- ... is an AutoML expert.[00:32:28] swyx: Yeah, I, I think it's multiple things, right? Like I'm, I'm just gonna bring up the, the, the chart again, right?Like LLMs can do the monitoring very well. That is the very potentially unbounded, super unstructured. It can do the analysis very well, it can do the... Uh, and basically it is much more intelligence poured into every single step. Uh, there's maybe nothing structurally changed about AutoML, but this is just m-more intelligent and more unstructured.[00:32:53] Mikhail Parakhin: Exactly.[00:32:54] swyx: Any flaws that you've run into? Like everyone is like drinking the Kool-Aid, oh my God, time savings, uh, you know, performance improvements. Like what, what, uh, issues have you have, uh, come up?[00:33:06] Mikhail Parakhin: This is really cool. It's not a solution to all the world's problems for sure. The limitations are usually the ones I-- And this is where we get into a bit of a subjective territory.Uh, I can only share what I've, I've seen so far, and I'm sure the situation, uh, is changing, and, you know, maybe after I say it, like many people will reach out and say, “Hey, what about this?” And you don't know that, and then, then we'll be probably right. But what I've seen is auto research is very good at doing kind of obvious things that you don't have bandwidth to do or you didn't notice or maybe you're not aware of like the-- some standard practices.It is not good at doing something completely out of distribution, something that, you know, you have to think for, for multiple days, uh, and, and do something like none of this. So, so it's, uh, I, uh, set an experiment once, uh, on, on my sort of, uh, hobby thing, and I let it run for, uh, ended up, uh, several weeks run, uh, you know, it's like full production kind of scale, so it, you know, slow runs and, and it ex-- it performed in the end, uh, over four hundred experiments, and only one was successful.I'm like, “Okay, that's, that's good.” But-[00:34:18] swyx: But it saved time.[00:34:19] Mikhail Parakhin: Yeah, I saved time. Like it, it was the, that thing. Yeah, if I, if I were doing four hundred experiments myself, my betting average, as I said, would have been much higher, I'm sure. But also, first of all, it would take me like three years to do four hundred experiments.And, uh, I didn't have to do them. Like the machines were just, uh, the price of electricity did that. So, and I got one improvement, uh, that in, uh, my, my-- Honestly, when I was starting that experiment, my thinking was to go and show that, “Hey, Andre, maybe you just don't know how to optimize.” And I was super smart because in, in my pro-problem, it was optimized for many years, and it was like fully improved.Uh, and I didn't expect it, you know, auto research to find anything at all. Yet it did. So instead of making fun of Andre, I ended up, uh, a big, big supporter. Yeah, that's exactly the tweet. Yes.[00:35:10] swyx: You and Toby really, really go back and forth on-online a lot, which is really funny. Uh, think of it as, as an eval for the optimalness of the code it's running on.Uh, it's almost like it reminds me of like a Kolmogorov complexity thing, but, uh, I guess it's-- there's some optimal thing that you're trying to sort of reduce down to, I guess. Um, and so, so you, you, you know, you should congratulate yourself that you had, uh, you know, uh, ninety-nine percent, uh, optimality.[00:35:36] Mikhail Parakhin: Exactly, yeah. I think Andre really deserves a lot of credit for popularizing this approach. This is, uh, this is incredibly, I think, powerful and cool and You know, the, uh, even him, him just mentioning it led to a lot of gains in a lot of places in the industry, so we should be thankful.[00:35:56] swyx: Yeah. I think he also has a just...I don't know what it is. Like, um, you know, it, it is a simple self-contained project that people can take and apply to other things, which is, is, is one thing, but also just the name. Just like somehow no one, no one managed to call their thing auto research. It's just naming things is very important. I think that that is mostly, uh, our coverage of Tango and, and, uh, Tangents.I think obviously, you know, there's a lot of, uh, ML infra at, at Shopify that people can, uh, dive into. We're about to go into SimGym, but before I do that, any, any other sort of broader comments around this whole effort? Like where is it, where is it leading to?[00:36:36] Mikhail Parakhin: As a segue to SimGym, like all those things start composing strongly.And, uh, you could see a huge unlock when you can look at each one of the tools and, and you see, oh, they're extremely useful. Uh, Tango is useful by itself. Auto Research is useful by itself. SimGym is useful by itself. If you combine all three, you create like synergetic effect. I think that's why we wanted to even, uh, cover them today is because this is something that if you go back even, you know, five years ago, would've been unthinkable.Uh, replicating that, uh, would, would be either incredibly costly or impossible, right? With probably thousands of people are required.[00:37:20] swyx: Well, we have serverless human, uh, serverless intelligence, right? Like, uh, so yes, you do have thousands of hu-- of, of intelligences, not just, not humans. And that's, that's close enough, right?Even if they're not AGI, they're, they're close enough to do the, the task that you need them to do. And, and, you know, that's, there's plenty for, for a lot of routine work, knowledge work. Okay, let's get into SimGym. Um, this is one of those things I, I was surprised to see actually it's apparently your, uh, one of your most popular launches, and I think something that, uh, I think Sim AI, I think Yunjun Park, who did the Smallville thing, there's a very small cottage industry of people trying to do like the simulate customer thing.I think a lot of people maybe don't super trust this yet because they're like, well, obviously they would just do what you prompt them to do, right? But maybe just think, uh, tell us about the sort of inspiration or origin story.[00:38:10] Mikhail Parakhin: That's exactly actually the thing I wanted to cover, because if you don't have the historical data, all you can do is prompt a-agents in a vacuum, and they will do exactly what you prompt them to do.In fact, when I first proposed it, and this is a bit of, um, my brainchild initially, if I, I can boast, even Toby said like, “But wouldn't they, they just repeat what, what you tell them?” And, uh, but I'm like, “Yes, except Shopify has decades of history of how people made changes and what there is, uh, there, what it resulted in terms of sales.”So now what we can do is we can-- we have this... It's not, it's a noisy data. There's a small, usually websites, uh, you know, like things, things are never in isolation. It's almost never AB experiment. It's always AA experiment when there's has two meanings, but basically, you know, in different time you run two different things.But if you aggregate in general, uh, like everything together, and you apply, uh, denoising and collaborative filtering like approach, you can extract a very clear signal. And then you can optimize your agents. And that's why it took so long. It took almost a year of that optimization of just us sitting and fiddling, and, and we had this internal goals of correlation of hitting-- internal goal was to hit zero point seven correlation with, uh, add to cart events, for example.Like that, that if we run real AB test experiment, that it should, it should go and, and rep-uh, replicate, uh, same sort of success that, that humans had or lack thereof. And it, it took forever, and I don't think that's easily replicatable because, uh, like who else would have that data? You have to have this historic, you know, decades, uh, worth of data.And now, now the, like the other thing you need is in-infrastructure and the scale, right? Because, uh, w- again, what we found, uh, stat sig results, you need to run a lot of simulations, a lot of agents, and, and it's-- Those are expensive things. Like you're, you're making actions in the browser because you want a real friction.You want to, to be able to get the image like of what humans will see because you wanna, uh, detect effects like, “Hey, if I make my images larger, will I have more sales or l- uh, fewer sales?” And like usually people's intuition here, by the way, is that I increase my images, I will have more because they look nicer.You know, designers all look sparse and big images. Like usually your sales tank, right? But, but, uh, you know, from HTML, all the characters look the same only the, the size tag looks different, right? So it's very hard. So you have to take visual information, you have to run this in simulated browser environment on the big farm and, and of course, you have to have, uh, like very, very expensive model, good model with multi-model model.So all this it's-- is what's taken so long and, uh, to share my personal fail a little bit there, Sean, is like, you know, we always had this bias to-- for like large company bias. You know, we always, uh, whenever you-- we do, we're like, “Hey, we'll run an experiment,” right? We make, make a change, and we will run an experiment and then, uh, see, uh, see which one's better or like, “No, this is worse,” and most of them are worse, so you discard it and keep iterating, hill climbing.And we're like, “Oh, like smaller merchants, they cannot get stat sig results. They cannot really run experiments simply because, you know, in a week there would be not enough data for them.” So we thought from this perspective. What we didn't realize is that most people don't have A and B, they just have one thing, and they need suggestions of What A and B should be.So, uh, we first build this, hey, we run simulation on two separate teams and, and, uh, say, “Hey, which one is better?” We then morphed it into, and very recently just released it, when you have just your site, your theme, we run over it and we say, “Hey, here's what predicted values of, of, uh, uh, conversions are, and here's how we think you should modify it to increase your conversions.”And then circling back to what you started with, the proof is in the pudding. Like, if we are not correlating with reality, like, people will not be using it. And, uh, thankfully, we see literally every day more users than the previous day. So, so right now, uh, right now- It's working. Yeah. I'm-- Right now my problem is how to pay for it all because the so our major thing is how to optimize the LLMs, do distillation, how to run the headless browsers, uh, and handful browsers, uh, uh, cheaper so that we can accommodate the increase in traffic.[00:42:47] swyx: Yeah. I, I understand that you, uh, you published a lot of technical detail at GTC, so I was just gonna bring it up a little bit. I think s- was this in, in con-conjunction with some kind of GTC presentation? Or something like that, right?[00:42:59] Mikhail Parakhin: Well, we, yeah, we, we did it in several place, but yeah, we had the engineering- Yeahblog, uh, as well. Yeah.[00:43:05] swyx: Yeah. So you're running, uh, GPT OSS. Uh,[00:43:08] Mikhail Parakhin: the, this is an older version. You know, now we run multimodal model. But yeah- Yeah ... GPT OSS, we still run GPT OSS as well for[00:43:15] swyx: And then you have the VMs, and you also have browser-based. I really like this one where it you said, “It violates almost every assumption that standard LLM serving is designed for.”And then you had like, basically orders of magnitude differences between everything.[00:43:29] Mikhail Parakhin: Exactly. Which is, which, uh, which was, you know, a bit of a challenge to implement, like when, like even simple things. Uh, be- since it violates all the assumptions, for example, multi-instance GPUs, like MIGs don't work as well.But we needed, uh, to get MIG to work because, ‘cause otherwise it's way too expensive. And so we had to deal with the, yeah, with, uh, lots of infrastructure and, and, uh, work with, uh, uh, Fireworks and CentML, uh, you know, to help with optimizations and browser-based, as you mentioned. Yeah, like, takes a village.[00:44:04] swyx: Okay. So there's a lot of like, I guess, experimentation in the infrastructure so far, and you've published more or less what you have here. I guess I'm, I'm less familiar with CentML. I, I don't do, uh, that much work in this, this part of the stack. But why was it the sort of preferred instance platform?[00:44:22] Mikhail Parakhin: There are really three probably top companies. There used to be, uh, uh- Three top companies, uh, at least I was aware of that did, uh, LM optimization. You know, together Fireworks and Santa ML, not necessarily in that order. Santa ML recently got acquired by NVIDIA. Uh, what they did is if you have a model and you want to optimize it to a specific prof-- uh, profile of usage, uh, they would go and do it.And, uh, we work with, with those companies, uh, this was work particularly in with Santa ML and NVIDIA to get them the best possible results out of it. And, and sometimes you, you have to retune depending on, like sometimes you want the maximum throughput, sometimes you want minimal latency, sometimes you want like the cheapest, right?And, yeah, or some combination. And so yeah, these are people who would come and help you.[00:45:14] swyx: I see. I see. Yeah, yeah. I'm familiar with these people for the LLM, you know, autoregressive stack. But the other interesting category of these optimizers is also the diffusion people, whereas like Fel and, you know, uh, Pruna recently has come up a lot as well, which I think is like really underappreciated, uh, at least by myself, because I, I thought, oh, all the workload would be LLMs, but actually there's a lot of diffusion as well.[00:45:38] Mikhail Parakhin: Exactly.[00:45:38] swyx: There's a lot here, so I, I, I... it's, it's, uh, it's, it's, it's hard to cover. But I, I do think like people underappreciate the importance of customer simulation, basically. I think this is something that I'm candidly still getting to terms with. Uh, you know, uh, you also-- your team also like prepared this, like, really nice diagram.Uh, I, I assume this is AI generated.[00:46:00] Mikhail Parakhin: Yeah, it looks-[00:46:01] swyx: Maybe it's not.[00:46:01] Mikhail Parakhin: Yeah, it looks, uh, Gemini-ish. Yeah, but, uh, uh, honestly, I, I don't know where, where the hell they generated. It looks, look, uh, looks like it's, uh, Google. But the interesting part, John, that, that, uh, we haven't covered, but I, I wanted to mention is if your store had previous customers, rather than it's a new store, you're like new merchant just launching things, it helps tremendously in just correlation and forecast.Yeah, we take your previous, uh, customer's behavior, and we create agents that replicate those specific distribution of, of customers that you get, and then we a- we apply those to your changes, and then that, that raised raw, you know, the re-- uh, just correlation with the add to cart events or to-- with conversion or whatever it, it, it may be, uh, quite dramatically.So, uh, replicating humans in general seems like an interesting, cool challenge.[00:46:58] swyx: As a shareholder, I think this is the-- like if people are Shopify shareholders, they should really deeply understand this because this is basically the moat. The, the more you use Shopify, the more it will just automatically improve, right?Like you're, you're doing the job for them.[00:47:13] Mikhail Parakhin: Yeah, that's what we started with. Like, uh- ... uh, otherwise, if you're just a startup, I wouldn't do it if, uh, you know, if it was my startup because Without the data, it, yeah, as, as you said, it's, it's exactly the case that, uh, whatever you say in prompt, that's, that's what the agents will be doing.[00:47:30] swyx: The statistician in me wants to like really satisfy the sort of, um, statistical intuition, I guess. Um, to me it's kind of, uh, the, the word that comes to mind is, um, ergodicity. Uh, so let's say a, a customer takes this path, customer takes this path, customer takes this path, right? Um, the... In my mind, the way I explain it is like, okay, here, here's the ninety-five percentile, here's the five percentile, and here's the median, right?Um, but to me, what SimGym is potentially doing is that it can, uh, modify... It can sort of model the sort of in-between sort of journeys as well, that, that maybe are dependent on the previous states. This may be like a very RL-type conclusion where like basically the summary statistics, if you only did naive AB testing, you only have the, the statistics at, at, at a certain point, and you only judge based on the sort of overall summary statistics.But here you can actually model trajectories. Does that make sense? Or-[00:48:31] Mikhail Parakhin: That makes total sense because like, well, that, that makes even more sense that maybe even you realize bec- because-[00:48:38] swyx: Okay. Please,[00:48:38] Mikhail Parakhin: please. Yes ... we do-- Yeah. The, so internally, uh, we have this system, we talked about it briefly once at NeurIPS.We have a huge HSTU-based system that models the whole companies, uh, and their possible paths. And like- Yeah ... what you are, what you are showing, like actually at any point of time, you can either model the user's behavior or you mo- can also think about, uh, the whole merchant as a company, as the entity that acts in the world.You can model that as well. And then you can do, can do counterfactuals. In your graph, like in your blue graph, uh, if you're... Imagine in the center there, uh, somewhere in the middle, you would have an intervention. I give that person a coupon, or I don't know, I send a personal thank you card, or give a discount in some- somewhere.And then you can, uh, then you can do forward rollouts from that counterfactual. So what would have happened with that intervention or without the intervention? And you can even ch- change where that intervention, uh, in time can happen, right? Like some- where, where in this journey. So we, we do this at the Shopify scale for our merchants, and then if we notice that something that they can be fixing, like there's a strong counterfactual, like we have Shopify policy, they basically get a notification like, “Hey, we think your...something is wrong with your-” I don't know, Canadian sales. Like, uh, it looks like it's misconfigured. Here's what you need to do. Or do you think like, uh, you have to set up this campaign with these parameters? And we do that at the buyer level to literally offer discounts or cashback or, or things to buyers.So this is-- I'm getting very excited. Like this is my sort of area of, uh, interest, I guess, and, and hobby. But being able to m-model something complex as human beings or companies and model counterfactuals on it, where you can have interventions in the future and optimize when to make intervention, what kind inter-- uh, what kind of intervention to make.It's such an unlock that previously was completely impossible. Like the-- it was, it was always dreamed of, but never... Like how would you even simulate it without LLMs or HTUs? I think very, very exciting times.[00:50:59] swyx: I just wanted to, uh, to maybe illustrate this. I, I'm not the best illustrator, but I, I am a conceptual statistics guy.And y-you know, you cannot just do this. Like this is a dimensionality AB test doesn't do, right? Like, uh, because it doesn't have the, the, the change over time, uh, stochastic nature, uh, and it doesn't have the sort of contextual like... Here's all the context to this point. Um, okay, cool. Um, that's SimGym.You're, you're gonna burn a lot of tokens on this thing. But you're, you're one of the, the only scale platforms in the world that can, uh, that can do this across a huge variety of workloads, right? I'm even curious on a sort of human, uh, research level of like, well, do, does retail behave d-differently from like clothing sales?D-does that behave differently from electronic sales? I, I don't know. I don't know what else you guys... The Kardashian shoppers, do they differ from like people who buy, uh, I don't know, cars and, uh, whatever.[00:51:55] Mikhail Parakhin: Well, very different, and different sensitivities and different modes of, uh, shopping and, and different levels of what's important.Now, to-totally, you can do aggregations at, uh, at a store level. You can do aggregations at a different, uh, category level. I don't know if, uh, you know, for our statisticians among us, I couldn't believe, but we-- recently we're looking at it, and we had to bring back, uh, CRPs, you know, Chinese restaurant process.It's a, like, way of aggregating and, like, naturally grow clustering. So across... Specifically to answer questions that, uh, like you were just posing on how, how if, if buyers behave different categories. And I'm like, “I haven't seen CRP since two thousand and one.” It's[00:52:37] swyx: so What? It's so- What is... No, I haven't, I haven't seen this.No. This is not in my training. Uh,[00:52:44] Mikhail Parakhin: but, but yeah, it, uh, uh, it actually, like the, the-- there was a very popular kind of theory, popular neurips HTML circles in early two thousands, uh, kind of nice. And now, now it has practical applications, uh- Yeah ... that we were resurrecting.[00:53:03] swyx: Yeah, amazing. Uh, I, I can see, I can see how this is like a, uh, a fun job for you where you get to apply all these things.Um, yeah, yeah, so super cool. Super cool. So, okay, so, so anyone who, who knows what CRPs are and has always wanted to use them at work, uh, they should, they should definitely join Shopify. Okay, so w-we have a lot and but I, I'm, I'm being mindful of the time. I, I do wanted to, to sort of cover some other things.Um, I-I'll give you a choice, UCP or Liquid?[00:53:30] Mikhail Parakhin: Liquid. I think, I think on UCP, you know, like UCP is very important for us and, and it just we are-- UCP, we have a structured, uh, discussions, and you can read about them, and we have, uh, blog posts, and we have a big release this week, in fact, like with our catalog.Oh,[00:53:46] swyx: okay.[00:53:46] Mikhail Parakhin: Uh, yeah,[00:53:46] swyx: but- Le-I mean, we, we can, we can discuss the, the, the release briefly because we'll release this after the-- after it's already announced so whatever. There's a catalog that you guys are doing?[00:53:55] Mikhail Parakhin: Yeah. So we are, we are- Okay ... we are bringing in capabilities of a whole, uh, Shopify catalog.Basically, you now you can search for products, you can do lookups by specific ID, you can do bulk lookups when you need to bring m-multiple products. You don't need to know in ad-in advance what you're trying to show or to sell or check out. Like, you can now, you can now have this decided at, at runtime, and this big area for investment for us for both non-personalized and personalized searches, trying to provide basically a win-window into whole universe of products that are being sold everywhere in the world.And Shopify is really not exactly, but almost like a super set of any-anything being sold. Now we are bringing it into UCP and, uh, and, uh, identity linking is another big thing for us, uh, so that you, you can use, uh, like Google or whatever, whatever identity you have, uh, they're minimizing friction.[00:54:56] swyx: Yeah. So[00:54:57] Mikhail Parakhin: yeah, big release for us.But Liquid AI of course we never talk about, and the problem might be more, more aligned with what we d-discussed previously on this chat.[00:55:07] swyx: Sure. The main thing that everyone understands about Liquid is that it is inspired by Worm, and I still don't know why. I'm curious on your explanation. I think you, you, uh, you can make things very approachable.And also I think like what is the potential of like the, the level of efficiency that you get out of Liquid?[00:55:23] Mikhail Parakhin: You- we all familiar with transformer architectures. And, uh, for the longest time, there was a competing architecture, it's called the state space models. So, so Sams, uh, you know, Chris, Chris Reyes, one of the pioneers and, and lots of startups, uh, trying to make those realities.They have, uh, significant benefits being main being, uh, being much faster and, uh, lower footprint and not quadratic in length, you know, sort of, uh, linear in, in, uh, in your context length. But with state space models- They never quite made it. Like they're used-- They have, uh, certain niches when they thrive, their hybrid architectures are useful, but they never quite made it.And liquid neural networks are, you can think of them as a next step, like, uh, sort of, uh, state-space model square. It's non-transformer architecture that's more complicated than sta-state space and really difficult to code if you-- if I'm being honest. But it's, um, very efficient. It's, uh, subline-- sub, uh, quadratic in, in length of your context.Uh, it's very compact way to represent things, and that's a liquid AI company. They... Their goal is to productize it, and very often you have this need, uh, when you need to have long context and small model, and you want to have low latency. Like in general, it's basically on par with transformers, and if you do hybrids with transformers, it's, it's even better.That's why we at Shopify, when we tried multiple and we constantly try multiple models, multiple companies, we found that for small, particularly with low latency applications, when you have low latency and/or if you need longer context lengths, liquid was the best. And so we still use the whole zoo and always like obviously test and use everything, uh, every open source model and, you know, it feels l

Slide into our VMs for a trip down memory lane.

Slide into our VMs to hear all about them.

Was there a full moon last night? Slide into our VMs.

In this episode we welcome Naveen Neelakantam, Chief Architect of Everpure's Digital Experience Business Unit. Naveen dives into the origin and evolution of Everpure's Digital Experience (DX), detailing how DX revolutionized storage management by moving beyond reactive support. The foundation of this lies in the phone home telemetry data collected from storage arrays, which first enabled the Cloud Assist capability. This data powers the ability to proactively identify and prevent issues, non-disruptively upgrade systems, and ensure a first-class support experience for every customer. Naveen explains how the intelligence gathered through telemetry propelled innovations like Pure1 and Evergreen//One. Pure1, the cloud-based platform, uses machine learning to offer predictive recommendations—such as projecting capacity needs to avoid unexpected overages. This predictive power is central to Evergreen//One, the consumption-based storage-as-a-service offering. By managing the physical appliance using telemetry, Everpure allows customers to consume logical storage connected to SLAs, simplifying the procurement process and eliminating the complexity of managing hardware specifics. This subscription model provides predictability and isolates customers from pricing pressures on components. Our discussion shifts to the future of storage and the transformative power of Artificial Intelligence. Naveen details AI Co-pilot, an agentic AI interface that helps users triangulate performance issues and orchestrate complex operations, such as migrating VMs, through conversational language using the Model Context Protocol (MCP). This move to active management is further realized through Pure1 Edge, allowing fleet-level data management and cloud-based upgrades. We then touche on Everpure Protect, a crucial cloud-based Disaster Recovery as a Service (DRaaS) solution. Ultimately, Naveen advises IT leaders to embrace AI as a powerful tool—like the domestication of the horse—that will make people more effective and accelerate innovation. To learn more, visit: https://www.purestorage.com/products/monitoring-fleet-management.html Check out the new Everpure digital customer community to join the conversation with peers and Pure experts: https://purecommunity.purestorage.com/ 00:00 Intro and Welcome 01:45 Naveen's Career Journey 09:29 Origin of Digital Experience 12:45 Proactive Recommendations 16:05 Cloud Management and Subscriptions 18:12 Stat of the Episode on Storage Capacity Growth 21:30 AI Co-Pilot and Automation 32:14 Telemetry 37:01 Pure1 and Subscription Management 39:51 Everpure Protect DRaaS 45:44 Hot Takes Segment

Slide into our VMs and consider this…

A surprisingly heated debate. Slide into our VMs.

Vizsla Copper announced a US$13.7 million for its Palmer project. Craig Parry, Executive Chairman and CEO, spoke to Mining Stock Daily to discuss the board-approved 2026 exploration and development budget for this VMS project in Southeast Alaska. Parry also talked about the company's Poplar project and recently announced drill holes. TH26-151 intersected the longest interval of continuous porphyry-related copper-molybdenum mineralization drilled to date at the Thira Discovery located at Poplar. 

Slide into our VMs.

Daniel Mahncke and Shawn O'Malley take a deep dive into four companies operating in the shadow of one of the greatest compounders of the last two decades — Constellation Software. Some investors believe that Topicus, Lumine, Sygnity, and Asseco Poland represent the best way to own the CSI model today, while others argue that the spinoffs lack the institutional depth and deal flow of the mother ship. Join Daniel and Shawn as they assess which of these mini-Constellations has the most compelling setup, and whether any of them deserve a spot in the portfolio. IN THIS EPISODE, YOU'LL LEARN: 00:00:00 - Intro 00:01:12 - Why smaller VMS companies are interesting 00:09:23 - How the law of large numbers shifts CSU's focus 00:11:04 - About Topicus and why it's the closest copy of CSU 00:14:57 - Why VMS is so attractive for acquirers 00:31:13 - Lumine and its focus on the media and communication vertical 00:44:16 - Sygnity and its new chapter 01:03:51 - Asseco Poland and why it might be a the next Topicus 01:11:40 - Whether Shawn and Daniel add a Mini Constellation to the portfolio *Disclaimer: Slight timestamp discrepancies may occur due to podcast platform differences. BOOKS AND RESOURCES The Investors Podcast Network is excited to debut a new community known as The Intrinsic Value Community for investors to learn, share ideas, network, and join calls with experts: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Sign up for the waitlist(!)⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Sign up for ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠The Intrinsic Value Newsletter.⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Learn how to ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠join us⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ in Omaha for the 2026 Berkshire Hathaway shareholder meeting. Track ⁠⁠⁠⁠⁠⁠The Intrinsic Value Portfolio⁠⁠⁠⁠⁠⁠. Shawn & Daniel use ⁠⁠⁠⁠Fiscal.ai⁠⁠⁠⁠ for every company they research — use their ⁠⁠⁠⁠referral link⁠⁠⁠⁠ to get started with a 15% discount! Outsiders' Corner Asseco Writeup. Outsider's Corner Asseco Writeup No.2. Alankrit Capital Sygnity Writeup. Seeking Winners Lumine Writeup. Check out our previous Intrinsic Value breakdowns: ⁠⁠⁠⁠Transdigm⁠⁠⁠⁠, ⁠⁠⁠⁠Salesforce⁠⁠⁠⁠, ⁠⁠⁠⁠Berkshire Hathaway⁠⁠⁠⁠, ⁠⁠⁠⁠FICO⁠⁠⁠⁠, ⁠⁠⁠⁠PayPal,⁠⁠⁠⁠ ⁠⁠⁠⁠Uber⁠⁠⁠⁠, ⁠⁠⁠⁠Nike⁠⁠⁠⁠, ⁠⁠⁠⁠Amazon⁠⁠⁠⁠, ⁠⁠⁠⁠Airbnb⁠⁠⁠⁠, ⁠⁠⁠⁠Alphabet⁠⁠⁠⁠. Related ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠books⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ mentioned in the podcast. Ad-free episodes on our ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Premium Feed⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠. NEW TO THE SHOW? Follow our official social media accounts: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠X (Twitter)⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠LinkedIn⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Facebook⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠. Browse through all our episodes (complete with transcripts) ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠. Try Shawn's favorite tool for picking stock winners and managing our portfolios: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠TIP Finance⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠. Enjoy exclusive perks from our ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠favorite Apps and Services⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠. Learn how to better start, manage, and grow your business with the ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠best business podcasts⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠.⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ References to any third-party products, services, or advertisers do not constitute endorsements, and The Investor's Podcast Network is not responsible for any claims made by them. Learn more about your ad choices. Visit megaphone.fm/adchoices Support our show by becoming a premium member! https://theinvestorspodcastnetwork.supportingcast.fm

Slide into our VMs.

#344: Kubernetes is boring now. That's the whole point. KubeCon EU 2026 in Amsterdam -- likely the biggest KubeCon ever at more than 13,000 attendees -- made one thing extremely clear: the container orchestrator is done being interesting on its own. Every keynote, every new sandbox project, every vendor announcement pointed the same direction. AI. Inference. Agents. NVIDIA donated a DRA driver for GPUs to CNCF. Google open-sourced their cluster autoscaler and shipped a DRA driver for TPUs. Red Hat brought LLM-D for disaggregated inference. NVIDIA contributed the KAI Scheduler for AI workloads. The Gateway API now has an inference extension in beta -- model routing baked directly into the Kubernetes networking layer. And here's the thing Whitney pointed out that should make everyone pause: you can't even run inference workloads in containers. They can escape. You need micro VMs. So the container orchestrator is orchestrating things that aren't containers. The platform engineering conversation shifted too. The bottleneck isn't technology anymore -- it's culture. Getting teams to work together differently. And if your company can't trust its own employees to make decisions, good luck trusting agents. Viktor's take on the determinism objection was blunt: agents aren't deterministic, but neither are you. You just think you are. One thread that kept surfacing: agents as first-class platform users. Not agents doing agent things -- agents as the users your platform serves. Viktor sees it in real time -- pull requests created by agents, reviewed by his Claude, responses written by the submitter's agent. Humans aren't even in the conversation anymore. The new CNCF sandbox projects tell the story too. LLM-D, KAI Scheduler, Higress (AI-native gateway). And then Velero -- the Kubernetes backup tool that everyone assumed was already CNCF -- finally donated by Broadcom. Which raises a fair question: is CNCF becoming a dumping ground for projects companies don't want to maintain? Probably some of both. Viktor compared the current state to the first five years of Kubernetes -- everyone focused on low-level components, trying to figure out how to combine 57 different tools. The next wave will be higher-level platforms that bundle all of it. And somewhere underneath it all, the mainframe keeps running. Viktor's bet: it'll outlive AI.   YouTube channel: https://youtube.com/devopsparadox   Review the podcast on Apple Podcasts: https://www.devopsparadox.com/review-podcast/   Slack: https://www.devopsparadox.com/slack/   Connect with us at: https://www.devopsparadox.com/contact

The US government is drumming up fear about foreign routers, a pretty serious supply chain attack might be state-sponsored, and the safety of filesystems inside VMs. Plugs Support us on patreon and get an ad-free RSS feed with some early episodes The Real Cost of Technology Dependence: Building Independence with Open-Source Storage News/discussion US bans any new consumer-grade routers not made in America National Security Determination on the Threat Posed by Routers Produced by Foreign Countries (pdf) 1K+ cloud environments infected following Trivy supply chain attack Self-propagating malware poisons open source software and wipes Iran-based machines Free consulting We were asked about the safety of filesystems inside VMs. Automox Turnkey Results Endpoint management tailored to your specific environment. Know the plan. Trust the result. Learn more at www.automox.com See our contact page for ways to get in touch.