Podcasts about Dyno

Join Kyle, Nader, Vibhu, and swyx live at NVIDIA GTC next week!Now that AIE Europe tix are ~sold out, our attention turns to Miami and World's Fair!The definitive AI Accelerator chip company has more than 10xed this AI Summer:And is now a $4.4 trillion megacorp… that is somehow still moving like a startup. We are blessed to have a unique relationship with our first ever NVIDIA guests: Kyle Kranen who gave a great inference keynote at the first World's Fair and is one of the leading architects of NVIDIA Dynamo (a Datacenter scale inference framework supporting SGLang, TRT-LLM, vLLM), and Nader Khalil, a friend of swyx from our days in Celo in The Arena, who has been drawing developers at GTC since before they were even a glimmer in the eye of NVIDIA:Nader discusses how NVIDIA Brev has drastically reduced the barriers to entry for developers to get a top of the line GPU up and running, and Kyle explains NVIDIA Dynamo as a data center scale inference engine that optimizes serving by scaling out, leveraging techniques like prefill/decode disaggregation, scheduling, and Kubernetes-based orchestration, framed around cost, latency, and quality tradeoffs. We also dive into Jensen's “SOL” (Speed of Light) first-principles urgency concept, long-context limits and model/hardware co-design, internal model APIs (https://build.nvidia.com), and upcoming Dynamo and agent sessions at GTC.Full Video pod on YouTubeTimestamps00:00 Agent Security Basics00:39 Podcast Welcome and Guests07:19 Acquisition and DevEx Shift13:48 SOL Culture and Dynamo Setup27:38 Why Scale Out Wins29:02 Scale Up Limits Explained30:24 From Laptop to Multi Node33:07 Cost Quality Latency Tradeoffs38:42 Disaggregation Prefill vs Decode41:05 Kubernetes Scaling with Grove43:20 Context Length and Co Design57:34 Security Meets Agents58:01 Agent Permissions Model59:10 Build Nvidia Inference Gateway01:01:52 Hackathons And Autonomy Dreams01:10:26 Local GPUs And Scaling Inference01:15:31 Long Running Agents And SF ReflectionsTranscriptAgent Security BasicsNader: Agents can do three things. They can access your files, they can access the internet, and then now they can write custom code and execute it. You literally only let an agent do two of those three things. If you can access your files and you can write custom code, you don't want internet access because that's one to see full vulnerability, right?If you have access to internet and your file system, you should know the full scope of what that agent's capable of doing. Otherwise, now we can get injected or something that can happen. And so that's a lot of what we've been thinking about is like, you know, how do we both enable this because it's clearly the future.But then also, you know, what, what are these enforcement points that we can start to like protect?swyx: All right.Podcast Welcome and Guestsswyx: Welcome to the Lean Space podcast in the Chromo studio. Welcome to all the guests here. Uh, we are back with our guest host Viu. Welcome. Good to have you back. And our friends, uh, Netter and Kyle from Nvidia. Welcome.Kyle: Yeah, thanks for having us.swyx: Yeah, thank you. Actually, I don't even know your titles.Uh, I know you're like architect something of Dynamo.Kyle: Yeah. I, I'm one of the engineering leaders [00:01:00] and a architects of Dynamo.swyx: And you're director of something and developers, developer tech.Nader: Yeah.swyx: You're the developers, developers, developers guy at nvidia,Nader: open source agent marketing, brev,swyx: and likeNader: Devrel tools and stuff.swyx: Yeah. BeenNader: the focus.swyx: And we're, we're kind of recording this ahead of Nvidia, GTC, which is coming to town, uh, again, uh, or taking over town, uh, which, uh, which we'll all be at. Um, and we'll talk a little bit about your sessions and stuff. Yeah.Nader: We're super excited for it.GTC Booth Stunt Storiesswyx: One of my favorite memories for Nader, like you always do like marketing stunts and like while you were at Rev, you like had this surfboard that you like, went down to GTC with and like, NA Nvidia apparently, like did so much that they bought you.Like what, what was that like? What was that?Nader: Yeah. Yeah, we, we, um. Our logo was a chaka. We, we, uh, we were always just kind of like trying to keep true to who we were. I think, you know, some stuff, startups, you're like trying to pretend that you're a bigger, more mature company than you are. And it was actually Evan Conrad from SF Compute who was just like, you guys are like previousswyx: guest.Yeah.Nader: Amazing. Oh, really? Amazing. Yeah. He was just like, guys, you're two dudes in the room. Why are you [00:02:00] pretending that you're not? Uh, and so then we were like, okay, let's make the logo a shaka. We brought surfboards to our booth to GTC and the energy was great. Yeah. Some palm trees too. They,Kyle: they actually poked out over like the, the walls so you could, you could see the bread booth.Oh, that's so funny. AndNader: no one else,Kyle: just from very far away.Nader: Oh, so you remember it backKyle: then? Yeah I remember it pre-acquisition. I was like, oh, those guys look cool,Nader: dude. That makes sense. ‘cause uh, we, so we signed up really last minute, and so we had the last booth. It was all the way in the corner. And so I was, I was worried that no one was gonna come.So that's why we had like the palm trees. We really came in with the surfboards. We even had one of our investors bring her dog and then she was just like walking the dog around to try to like, bring energy towards our booth. Yeah.swyx: Steph.Kyle: Yeah. Yeah, she's the best,swyx: you know, as a conference organizer, I love that.Right? Like, it's like everyone who sponsors a conference comes, does their booth. They're like, we are changing the future of ai or something, some generic b******t and like, no, like actually try to stand out, make it fun, right? And people still remember it after three years.Nader: Yeah. Yeah. You know what's so funny?I'll, I'll send, I'll give you this clip if you wanna, if you wanna add it [00:03:00] in, but, uh, my wife was at the time fiance, she was in medical school and she came to help us. ‘cause it was like a big moment for us. And so we, we bought this cricket, it's like a vinyl, like a vinyl, uh, printer. ‘cause like, how else are we gonna label the surfboard?So, we got a surfboard, luckily was able to purchase that on the company card. We got a cricket and it was just like fine tuning for enterprises or something like that, that we put on the. On the surfboard and it's 1:00 AM the day before we go to GTC. She's helping me put these like vinyl stickers on.And she goes, you son of, she's like, if you pull this off, you son of a b***h. And so, uh, right. Pretty much after the acquisition, I stitched that with the mag music acquisition. I sent it to our family group chat. Ohswyx: Yeah. No, well, she, she made a good choice there. Was that like basically the origin story for Launchable is that we, it was, and maybe we should explain what Brev is andNader: Yeah.Yeah. Uh, I mean, brev is just, it's a developer tool that makes it really easy to get a GPU. So we connect a bunch of different GPU sources. So the basics of it is like, how quickly can we SSH you into a G, into a GPU and whenever we would talk to users, they wanted A GPU. They wanted an A 100. And if you go to like any cloud [00:04:00] provisioning page, usually it's like three pages of forms or in the forms somewhere there's a dropdown.And in the dropdown there's some weird code that you know to translate to an A 100. And I remember just thinking like. Every time someone says they want an A 100, like the piece of text that they're telling me that they want is like, stuffed away in the corner. Yeah. And so we were like, what if the biggest piece of text was what the user's asking for?And so when you go to Brev, it's just big GPU chips with the type that you want withswyx: beautiful animations that you worked on pre, like pre you can, like, now you can just prompt it. But back in the day. Yeah. Yeah. Those were handcraft, handcrafted artisanal code.Nader: Yeah. I was actually really proud of that because, uh, it was an, i I made it in Figma.Yeah. And then I found, I was like really struggling to figure out how to turn it from like Figma to react. So what it actually is, is just an SVG and I, I have all the styles and so when you change the chip, whether it's like active or not it changes the SVG code and that somehow like renders like, looks like it's animating, but it, we just had the transition slow, but it's just like the, a JavaScript function to change the like underlying SVG.Yeah. And that was how I ended up like figuring out how to move it from from Figma. But yeah, that's Art Artisan. [00:05:00]Kyle: Speaking of marketing stunts though, he actually used those SVGs. Or kind of use those SVGs to make these cards.Nader: Oh yeah. LikeKyle: a GPU gift card Yes. That he handed out everywhere. That was actually my first impression of thatNader: one.Yeah,swyx: yeah, yeah.Nader: Yeah.swyx: I think I still have one of them.Nader: They look great.Kyle: Yeah.Nader: I have a ton of them still actually in our garage, which just, they don't have labels. We should honestly like bring, bring them back. But, um, I found this old printing press here, actually just around the corner on Ven ness. And it's a third generation San Francisco shop.And so I come in an excited startup founder trying to like, and they just have this crazy old machinery and I'm in awe. ‘cause the the whole building is so physical. Like you're seeing these machines, they have like pedals to like move these saws and whatever. I don't know what this machinery is, but I saw all three generations.Like there's like the grandpa, the father and the son, and the son was like, around my age. Well,swyx: it's like a holy, holy trinity.Nader: It's funny because we, so I just took the same SVG and we just like printed it and it's foil printing, so they make a a, a mold. That's like an inverse of like the A 100 and then they put the foil on it [00:06:00] and then they press it into the paper.And I remember once we got them, he was like, Hey, don't forget about us. You know, I guess like early Apple and Cisco's first business cards were all made there. And so he was like, yeah, we, we get like the startup businesses but then as they mature, they kind of go somewhere else. And so I actually, I think we were talking with marketing about like using them for some, we should go back and make some cards.swyx: Yeah, yeah, yeah. You know, I remember, you know, as a very, very small breadth investor, I was like, why are we spending time like, doing these like stunts for GPUs? Like, you know, I think like as a, you know, typical like cloud hard hardware person, you go into an AWS you pick like T five X xl, whatever, and it's just like from a list and you look at the specs like, why animate this GP?And, and I, I do think like it just shows the level of care that goes throughout birth and Yeah. And now, and also the, and,Nader: and Nvidia. I think that's what the, the thing that struck me most when we first came in was like the amount of passion that everyone has. Like, I think, um, you know, you talk to, you talk to Kyle, you talk to, like, every VP that I've met at Nvidia goes so close to the metal.Like, I remember it was almost a year ago, and like my VP asked me, he's like, Hey, [00:07:00] what's cursor? And like, are you using it? And if so, why? Surprised at this, and he downloaded Cursor and he was asking me to help him like, use it. And I thought that was, uh, or like, just show him what he, you know, why we were using it.And so, the amount of care that I think everyone has and the passion, appreciate, passion and appreciation for the moment. Right. This is a very unique time. So it's really cool to see everyone really like, uh, appreciate that.swyx: Yeah.Acquisition and DevEx Shiftswyx: One thing I wanted to do before we move over to sort of like research topics and, uh, the, the stuff that Kyle's working on is just tell the story of the acquisition, right?Like, not many people have been, been through an acquisition with Nvidia. What's it like? Uh, what, yeah, just anything you'd like to say.Nader: It's a crazy experience. I think, uh, you know, we were the thing that was the most exciting for us was. Our goal was just to make it easier for developers.We wanted to find access to GPUs, make it easier to do that. And then all, oh, actually your question about launchable. So launchable was just make one click exper, like one click deploys for any software on top of the GPU. Mm-hmm. And so what we really liked about Nvidia was that it felt like we just got a lot more resources to do all of that.I think, uh, you [00:08:00] know, NVIDIA's goal is to make things as easy for developers as possible. So there was a really nice like synergy there. I think that, you know, when it comes to like an acquisition, I think the amount that the soul of the products align, I think is gonna be. Is going speak to the success of the acquisition.Yeah. And so it in many ways feels like we're home. This is a really great outcome for us. Like we you know, I love brev.nvidia.com. Like you should, you should use it's, it's theKyle: front page for GPUs.Nader: Yeah. Yeah. If you want GP views,Kyle: you go there, getswyx: it there, and it's like internally is growing very quickly.I, I don't remember You said some stats there.Nader: Yeah, yeah, yeah. It's, uh, I, I wish I had the exact numbers, but like internally, externally, it's been growing really quickly. We've been working with a bunch of partners with a bunch of different customers and ISVs, if you have a solution that you want someone that runs on the GPU and you want people to use it quickly, we can bundle it up, uh, in a launchable and make it a one click run.If you're doing things and you want just like a sandbox or something to run on, right. Like open claw. Huge moment. Super exciting. Our, uh, and we'll talk into it more, but. You know, internally, people wanna run this, and you, we know we have to be really careful from the security implications. Do we let this run on the corporate network?Security's guidance was, Hey, [00:09:00] run this on breath, it's in, you know, it's, it's, it's a vm, it's sitting in the cloud, it's off the corporate network. It's isolated. And so that's been our stance internally and externally about how to even run something like open call while we figure out how to run these things securely.But yeah,swyx: I think there's also like, you almost like we're the right team at the right time when Nvidia is starting to invest a lot more in developer experience or whatever you call it. Yeah. Uh, UX or I don't know what you call it, like software. Like obviously NVIDIA is always invested in software, but like, there's like, this is like a different audience.Yeah. It's aNader: widerKyle: developer base.swyx: Yeah. Right.Nader: Yeah. Yeah. You know, it's funny, it's like, it's not, uh,swyx: so like, what, what is it called internally? What, what is this that people should be aware that is going on there?Nader: Uh, what, like developer experienceswyx: or, yeah, yeah. Is it's called just developer experience or is there like a broader strategy hereNader: in Nvidia?Um, Nvidia always wants to make a good developer experience. The thing is and a lot of the technology is just really complicated. Like, it's not, it's uh, you know, I think, um. The thing that's been really growing or the AI's growing is having a huge moment, not [00:10:00] because like, let's say data scientists in 2018, were quiet then and are much louder now.The pie is com, right? There's a whole bunch of new audiences. My mom's wondering what she's doing. My sister's learned, like taught herself how to code. Like the, um, you know, I, I actually think just generally AI's a big equalizer and you're seeing a more like technologically literate society, I guess.Like everyone's, everyone's learning how to code. Uh, there isn't really an excuse for that. And so building a good UX means that you really understand who your end user is. And when your end user becomes such a wide, uh, variety of people, then you have to almost like reinvent the practice, right? Yeah. You haveKyle: to, and actually build more developer ux, right?Because the, there are tiers of developer base that were added. You know, the, the hackers that are building on top of open claw, right? For example, have never used gpu. They don't know what kuda is. They, they, they just want to run something.Nader: Yeah.Kyle: You need new UX that is not just. Hey, you know, how do you program something in Cuda and run it?And then, and then we built, you know, like when Deep Learning was getting big, we built, we built Torch and, and, but so recently the amount of like [00:11:00] layers that are added to that developer stack has just exploded because AI has become ubiquitous. Everyone's using it in different ways. Yeah. It'sNader: moving fast in every direction.Vertical, horizontal.Vibhu: Yeah. You guys, you even take it down to hardware, like the DGX Spark, you know, it's, it's basically the same system as just throwing it up on big GPU cluster.Nader: Yeah, yeah, yeah. It's amazing. Blackwell.swyx: Yeah. Uh, we saw the preview at the last year's GTC and that was one of the better performing, uh, videos so far, and video coverage so far.Awesome. This will beat it. Um,Nader: that wasswyx: actually, we have fingersNader: crossed. Yeah.DGX Spark and Remote AccessNader: Even when Grace Blackwell or when, um, uh, DGX Spark was first coming out getting to be involved in that from the beginning of the developer experience. And it just comes back to what youswyx: were involved.Nader: Yeah. St. St.swyx: Mars.Nader: Yeah. Yeah. I mean from, it was just like, I, I got an email, we just got thrown into the loop and suddenly yeah, I, it was actually really funny ‘cause I'm still pretty fresh from the acquisition and I'm, I'm getting an email from a bunch of the engineering VPs about like, the new hardware, GPU chip, like we're, or not chip, but just GPU system that we're putting out.And I'm like, okay, cool. Matters. Now involved with this for the ux, I'm like. What am I gonna do [00:12:00] here? So, I remember the first meeting, I was just like kind of quiet as I was hearing engineering VPs talk about what this box could be, what it could do, how we should use it. And I remember, uh, one of the first ideas that people were idea was like, oh, the first thing that it was like, I think a quote was like, the first thing someone's gonna wanna do with this is get two of them and run a Kubernetes cluster on top of them.And I was like, oh, I think I know why I'm here. I was like, the first thing we're doing is easy. SSH into the machine. And then, and you know, just kind of like scoping it down of like, once you can do that every, you, like the person who wants to run a Kubernetes cluster onto Sparks has a higher propensity for pain, then, then you know someone who buys it and wants to run open Claw right now, right?If you can make sure that that's as effortless as possible, then the rest becomes easy. So there's a tool called Nvidia Sync. It just makes the SSH connection really simple. So, you know, if you think about it like. If you have a Mac, uh, or a PC or whatever, if you have a laptop and you buy this GPU and you want to use it, you should be able to use it like it's A-A-G-P-U in the cloud, right?Um, but there's all this friction of like, how do you actually get into that? That's part of [00:13:00] Revs value proposition is just, you know, there's a CLI that wraps SSH and makes it simple. And so our goal is just get you into that machine really easily. And one thing we just launched at CES, it's in, it's still in like early access.We're ironing out some kinks, but it should be ready by GTC. You can register your spark on Brev. And so now if youswyx: like remote managed yeah, local hardware. Single pane of glass. Yeah. Yeah. Because Brev can already manage other clouds anyway, right?Vibhu: Yeah, yeah. And you use the spark on Brev as well, right?Nader: Yeah. But yeah, exactly. So, so you, you, so you, you set it up at home you can run the command on it, and then it gets it's essentially it'll appear in your Brev account, and then you can take your laptop to a Starbucks or to a cafe, and you'll continue to use your, you can continue use your spark just like any other cloud node on Brev.Yeah. Yeah. And it's just like a pre-provisioned centerswyx: in yourNader: home. Yeah, exactly.swyx: Yeah. Yeah.Vibhu: Tiny little data center.Nader: Tiny little, the size ofVibhu: your phone.SOL Culture and Dynamo Setupswyx: One more thing before we move on to Kyle. Just have so many Jensen stories and I just love, love mining Jensen stories. Uh, my favorite so far is SOL. Uh, what is, yeah, what is S-O-L-S-O-LNader: is actually, i, I think [00:14:00] of all the lessons I've learned, that one's definitely my favorite.Kyle: It'll always stick with you.Nader: Yeah. Yeah. I, you know, in your startup, everything's existential, right? Like we've, we've run out of money. We were like, on the risk of, of losing payroll, we've had to contract our team because we l ran outta money. And so like, um, because of that you're really always forcing yourself to I to like understand the root cause of everything.If you get a date, if you get a timeline, you know exactly why that date or timeline is there. You're, you're pushing every boundary and like, you're not just say, you're not just accepting like a, a no. Just because. And so as you start to introduce more layers, as you start to become a much larger organization, SOL is is essentially like what is the physics, right?The speed of light moves at a certain speed. So if flight's moving some slower, then you know something's in the way. So before trying to like layer reality back in of like, why can't this be delivered at some date? Let's just understand the physics. What is the theoretical limit to like, uh, how fast this can go?And then start to tell me why. ‘cause otherwise people will start telling you why something can't be done. But actually I think any great leader's goal is just to create urgency. Yeah. [00:15:00] There's an infiniteKyle: create compelling events, right?Nader: Yeah.Kyle: Yeah. So l is a term video is used to instigate a compelling event.You say this is done. How do we get there? What is the minimum? As much as necessary, as little as possible thing that it takes for us to get exactly here and. It helps you just break through a bunch of noise.swyx: Yeah.Kyle: Instantly.swyx: One thing I'm unclear about is, can only Jensen use the SOL card? Like, oh, no, no, no.Not everyone get the b******t out because obviously it's Jensen, but like, can someone else be like, no, likeKyle: frontline engineers use it.Nader: Yeah. Every, I think it's not so much about like, get the b******t out. It's like, it's like, give me the root understanding, right? Like, if you tell me something takes three weeks, it like, well, what's the first principles?Yeah, the first principles. It's like, what's the, what? Like why is it three weeks? What is the actual yeah. What's the actual limit of why this is gonna take three weeks? If you're gonna, if you, if let's say you wanted to buy a new computer and someone told you it's gonna be here in five days, what's the SOL?Well, like the SOL is like, I could walk into a Best Buy and pick it up for you. Right? So then anything that's like beyond that is, and is that practical? Is that how we're gonna, you know, let's say give everyone in the [00:16:00] company a laptop, like obviously not. So then like that's the SOL and then it's like, okay, well if we have to get more than 10, suddenly there might be some, right?And so now we can kind of piece the reality back.swyx: So, so this is the. Paul Graham do things that don't scale. Yeah. And this is also the, what people would now call behi agency. Yeah.Kyle: It's actually really interesting because there's a, there's a second hardware angle to SOL that like doesn't come up for all the org sol is used like culturally at aswyx: media for everything.I'm also mining for like, I think that can be annoying sometimes. And like someone keeps going IOO you and you're like, guys, like we have to be stable. We have to, we to f*****g plan. Yeah.Kyle: It's an interesting balance.Nader: Yeah. I encounter that with like, actually just with, with Alec, right? ‘cause we, we have a new conference so we need to launch, we have, we have goals of what we wanna launch by, uh, by the conference and like, yeah.At the end of the day, where isswyx: this GTC?Nader: Um, well this is like, so we, I mean we did it for CES, we did for GT CDC before that we're doing it for GTC San Jose. So I mean, like every, you know, we have a new moment. Um, and we want to launch something. Yeah. And we want to do so at SOL and that does mean that some, there's some level of prioritization that needs [00:17:00] to happen.And so it, it is difficult, right? I think, um, you have to be careful with what you're pushing. You know, stability is important and that should be factored into S-O-L-S-O-L isn't just like, build everything and let it break, you know, that, that's part of the conversation. So as you're laying, layering in all the details, one of them might be, Hey, we could build this, but then it's not gonna be stable for X, y, z reasons.And so that was like, one of our conversations for CES was, you know, hey, like we, we can get this into early access registering your spark with brev. But there are a lot of things that we need to do in order to feel really comfortable from a security perspective, right? There's a lot of networking involved before we deliver that to users.So it's like, okay. Let's get this to a point where we can at least let people experiment with it. We had it in a booth, we had it in Jensen's keynote, and then let's go iron out all the networking kinks. And that's not easy. And so, uh, that can come later. And so that was the way that we layered that back in.Yeah. ButKyle: It's not really about saying like, you don't have to do the, the maintenance or operational work. It's more about saying, you know, it's kind of like [00:18:00] highlights how progress is incremental, right? Like, what is the minimum thing that we can get to. And then there's SOL for like every component after that.But there's the SOL to get you, get you to the, the starting line. And that, that's usually how it's asked. Yeah. On the other side, you know, like SOL came out of like hardware at Nvidia. Right. So SOL is like literally if we ran the accelerator or the GPU with like at basically full speed with like no other constraints, like how FAST would be able to make a program go.swyx: Yeah. Yeah. Right.Kyle: Soswyx: in, in training that like, you know, then you work back to like some percentage of like MFU for example.Kyle: Yeah, that's a, that's a great example. So like, there's an, there's an S-O-L-M-F-U, and then there's like, you know, what's practically achievable.swyx: Cool. Should we move on to sort of, uh, Kyle's side?Uh, Kyle, you're coming more from the data science world. And, uh, I, I mean I always, whenever, whenever I meet someone who's done working in tabular stuff, graph neural networks, time series, these are basically when I go to new reps, I go to ICML, I walk the back halls. There's always like a small group of graph people.Yes. Absolute small group of tabular people. [00:19:00] And like, there's no one there. And like, it's very like, you know what I mean? Like, yeah, no, like it's, it's important interesting work if you care about solving the problems that they solve.Kyle: Yeah.swyx: But everyone else is just LMS all the time.Kyle: Yeah. I mean it's like, it's like the black hole, right?Has the event horizon reached this yet in nerves? Um,swyx: but like, you know, those are, those are transformers too. Yeah. And, and those are also like interesting things. Anyway, uh, I just wanted to spend a little bit of time on, on those, that background before we go into Dynamo, uh, proper.Kyle: Yeah, sure. I took a different path to Nvidia than that, or I joined six years ago, seven, if you count, when I was an intern.So I joined Nvidia, like right outta college. And the first thing I jumped into was not what I'd done in, during internship, which was like, you know, like some stuff for autonomous vehicles, like heavyweight object detection. I jumped into like, you know, something, I'm like, recommenders, this is popular. Andswyx: yeah, he did RexiKyle: as well.Yeah, Rexi. Yeah. I mean that, that was the taboo data at the time, right? You have tables of like, audience qualities and item qualities, and you're trying to figure out like which member of [00:20:00] the audience matches which item or, or more practically which item matches which member of the audience. And at the time, really it was like we were trying to enable.Uh, recommender, which had historically been like a little bit of a CP based workflow into something that like, ran really well in GPUs. And it's since been done. Like there are a bunch of libraries for Axis that run on GPUs. Uh, the common models like Deeplearning recommendation model, which came outta meta and the wide and deep model, which was used or was released by Google were very accelerated by GPUs using, you know, the fast HBM on the chips, especially to do, you know, vector lookups.But it was very interesting at the time and super, super relevant because like we were starting to get like. This explosion of feeds and things that required rec recommenders to just actively be on all the time. And sort of transitioned that a little bit towards graph neural networks when I discovered them because I was like, okay, you can actually use graphical neural networks to represent like, relationships between people, items, concepts, and that, that interested me.So I jumped into that at [00:21:00] Nvidia and, and got really involved for like two-ish years.swyx: Yeah. Uh, and something I learned from Brian Zaro Yeah. Is that you can just kind of choose your own path in Nvidia.Kyle: Oh my God. Yeah.swyx: Which is not a normal big Corp thing. Yeah. Like you, you have a lane, you stay in your lane.Nader: I think probably the reason why I enjoy being in a, a big company, the mission is the boss probably from a startup guy. Yeah. The missionswyx: is the boss.Nader: Yeah. Uh, it feels like a big game of pickup basketball. Like, you know, if you play one, if you wanna play basketball, you just go up to the court and you're like, Hey look, we're gonna play this game and we need three.Yeah. And you just like find your three. That's honestly for every new initiative that's what it feels like. Yeah.Vibhu: It also like shows, right? Like Nvidia. Just releasing state-of-the-art stuff in every domain. Yeah. Like, okay, you expect foundation models with Nemo tron voice just randomly parakeet.Call parakeet just comes out another one, uh, voice. TheKyle: video voice team has always been producing.Vibhu: Yeah. There's always just every other domain of paper that comes out, dataset that comes out. It's like, I mean, it also stems back to what Nvidia has to do, right? You have to make chips years before they're actually produced.Right? So you need to know, you need to really [00:22:00] focus. TheKyle: design process starts likeVibhu: exactlyKyle: three to five years before the chip gets to the market.Vibhu: Yeah. I, I'm curious more about what that's like, right? So like, you have specialist teams. Is it just like, you know, people find an interest, you go in, you go deep on whatever, and that kind of feeds back into, you know, okay, we, we expect predictions.Like the internals at Nvidia must be crazy. Right? You know? Yeah. Yeah. You know, you, you must. Not even without selling to people, you have your own predictions of where things are going. Yeah. And they're very based, very grounded. Right?Kyle: Yeah. It, it, it's really interesting. So there's like two things that I think that Amed does, which are quite interesting.Uh, one is like, we really index into passion. There's a big. Sort of organizational top sound push to like ensure that people are working on the things that they're passionate about. So if someone proposes something that's interesting, many times they can just email someone like way up the chain that they would find this relevant and say like, Hey, can I go work on this?Nader: It's actually like I worked at a, a big company for a couple years before, uh, starting on my startup journey and like, it felt very weird if you were to like email out of chain, if that makes [00:23:00] sense. Yeah. The emails at Nvidia are like mosh pitsswyx: shoot,Nader: and it's just like 60 people, just whatever. And like they're, there's this,swyx: they got messy like, reply all you,Nader: oh, it's in, it's insane.It's insane. They justKyle: help. You know, Maxim,Nader: the context. But, but that's actually like, I've actually, so this is a weird thing where I used to be like, why would we send emails? We have Slack. I am the entire, I'm the exact opposite. I feel so bad for anyone who's like messaging me on Slack ‘cause I'm so unresponsive.swyx: Your emailNader: Maxi, email Maxim. I'm email maxing Now email is a different, email is perfect because man, we can't work together. I'm email is great, right? Because important threads get bumped back up, right? Yeah, yeah. Um, and so Slack doesn't do that. So I just have like this casino going off on the right or on the left and like, I don't know which thread was from where or what, but like the threads get And then also just like the subject, so you can have like working threads.I think what's difficult is like when you're small, if you're just not 40,000 people I think Slack will work fine, but there's, I don't know what the inflection point is. There is gonna be a point where that becomes really messy and you'll actually prefer having email. ‘cause you can have working threads.You can cc more than nine people in a thread.Kyle: You can fork stuff.Nader: You can [00:24:00] fork stuff, which is super nice and just like y Yeah. And so, but that is part of where you can propose a plan. You can also just. Start, honestly, momentum's the only authority, right? So like, if you can just start, start to make a little bit of progress and show someone something, and then they can try it.That's, I think what's been, you know, I think the most effective way to push anything for forward. And that's both at Nvidia and I think just generally.Kyle: Yeah, there's, there's the other concept that like is explored a lot at Nvidia, which is this idea of a zero billion dollar business. Like market creation is a big thing at Nvidia.Like,swyx: oh, you want to go and start a zero billion dollar business?Kyle: Jensen says, we are completely happy investing in zero billion dollar markets. We don't care if this creates revenue. It's important for us to know about this market. We think it will be important in the future. It can be zero billion dollars for a while.I'm probably minging as words here for, but like, you know, like, I'll give an example. NVIDIA's been working on autonomous driving for a a long time,swyx: like an Nvidia car.Kyle: No, they, they'veVibhu: used the Mercedes, right? They're around the HQ and I think it finally just got licensed out. Now they're starting to be used quite a [00:25:00] bit.For 10 years you've been seeing Mercedes with Nvidia logos driving.Kyle: If you're in like the South San Santa Clara, it's, it's actually from South. Yeah. So, um. Zero billion dollar markets are, are a thing like, you know, Jensen,swyx: I mean, okay, look, cars are not a zero billion dollar market. But yeah, that's a bad example.Nader: I think, I think he's, he's messaging, uh, zero today, but, or even like internally, right? Like, like it's like, uh, an org doesn't have to ruthlessly find revenue very quickly to justify their existence. Right. Like a lot of the important research, a lot of the important technology being developed that, that's kind ofKyle: where research, research is very ide ideologically free at Nvidia.Yeah. Like they can pursue things that they wereswyx: Were you research officially?Kyle: I was never in research. Officially. I was always in engineering. Yeah. We in, I'm in an org called Deep Warning Algorithms, which is basically just how do we make things that are relevant to deep warning go fast.swyx: That sounds freaking cool.Vibhu: And I think a lot of that is underappreciated, right? Like time series. This week Google put out time. FF paper. Yeah. A new time series, paper res. Uh, Symantec, ID [00:26:00] started applying Transformers LMS to Yes. Rec system. Yes. And when you think the scale of companies deploying these right. Amazon recommendations, Google web search, it's like, it's huge scale andKyle: Yeah.Vibhu: You want fast?Kyle: Yeah. Yeah. Yeah. Actually it's, it, I, there's a fun moment that brought me like full circle. Like, uh, Amazon Ads recently gave a talk where they talked about using Dynamo for generative recommendation, which was like super, like weirdly cathartic for me. I'm like, oh my God. I've, I've supplanted what I was working on.Like, I, you're using LMS now to do what I was doing five years ago.swyx: Yeah. Amazing. And let's go right into Dynamo. Uh, maybe introduce Yeah, sure. To the top down and Yeah.Kyle: I think at this point a lot of people are familiar with the term of inference. Like funnily enough, like I went from, you know, inference being like a really niche topic to being something that's like discussed on like normal people's Twitter feeds.It's,Nader: it's on billboardsKyle: here now. Yeah. Very, very strange. Driving, driving, seeing just an inference ad on 1 0 1 inference at scale is becoming a lot more important. Uh, we have these moments like, you know, open claw where you have these [00:27:00] agents that take lots and lots of tokens, but produce, incredible results.There are many different aspects of test time scaling so that, you know, you can use more inference to generate a better result than if you were to use like a short amount of inference. There's reasoning, there's quiring, there's, adding agency to the model, allowing it to call tools and use skills.Dyno sort came about at Nvidia. Because myself and a couple others were, were sort of talking about the, these concepts that like, you know, you have inference engines like VLMS, shelan, tenor, TLM and they have like one single copy. They, they, they sort of think about like things as like one single copy, like one replica, right?Why Scale Out WinsKyle: Like one version of the model. But when you're actually serving things at scale, you can't just scale up that replica because you end up with like performance problems. There's a scaling limit to scaling up replicas. So you actually have to scale out to use a, maybe some Kubernetes type terminology.We kind of realized that there was like. A lot of potential optimization that we could do in scaling out and building systems for data [00:28:00] center scale inference. So Dynamo is this data center scale inference engine that sits on top of the frameworks like VLM Shilling and 10 T lm and just makes things go faster because you can leverage the economy of scale.The fact that you have KV cash, which we can define a little bit later, uh, in all these machines that is like unique and you wanna figure out like the ways to maximize your cash hits or you want to employ new techniques in inference like disaggregation, which Dynamo had introduced to the world in, in, in March, not introduced, it was a academic talk, but beforehand.But we are, you know, one of the first frameworks to start, supporting it. And we wanna like, sort of combine all these techniques into sort of a modular framework that allows you to. Accelerate your inference at scale.Nader: By the way, Kyle and I became friends on my first date, Nvidia, and I always loved, ‘cause like he always teaches meswyx: new things.Yeah. By the way, this is why I wanted to put two of you together. I was like, yeah, this is, this is gonna beKyle: good. It's very, it's very different, you know, like we've, we, we've, we've talked to each other a bunch [00:29:00] actually, you asked like, why, why can't we scale up?Nader: Yeah.Scale Up Limits ExplainedNader: model, you said model replicas.Kyle: Yeah. So you, so scale up means assigning moreswyx: heavier?Kyle: Yeah, heavier. Like making things heavier. Yeah, adding more GPUs. Adding more CPUs. Scale out is just like having a barrier saying, I'm gonna duplicate my representation of the model or a representation of this microservice or something, and I'm gonna like, replicate it Many times.Handle, load. And the reason that you can't scale, scale up, uh, past some points is like, you know, there, there, there are sort of hardware bounds and algorithmic bounds on, on that type of scaling. So I'll give you a good example that's like very trivial. Let's say you're on an H 100. The Maxim ENV link domain for H 100, for most Ds H one hundreds is heus, right?So if you scaled up past that, you're gonna have to figure out ways to handle the fact that now for the GPUs to communicate, you have to do it over Infin band, which is still very fast, but is not as fast as ENV link.swyx: Is it like one order of magnitude, like hundreds or,Kyle: it's about an order of magnitude?Yeah. Okay. Um, soswyx: not terrible.Kyle: [00:30:00] Yeah. I, I need to, I need to remember the, the data sheet here, like, I think it's like about 500 gigabytes. Uh, a second unidirectional for ENV link, and about 50 gigabytes a second unidirectional for Infin Band. I, it, it depends on the, the generation.swyx: I just wanna set this up for people who are not familiar with these kinds of like layers and the trash speedVibhu: and all that.Of course.From Laptop to Multi NodeVibhu: Also, maybe even just going like a few steps back before that, like most people are very familiar with. You see a, you know, you can use on your laptop, whatever these steel viol, lm you can just run inference there. All, there's all, you can, youcan run it on thatVibhu: laptop. You can run on laptop.Then you get to, okay, uh, models got pretty big, right? JLM five, they doubled the size, so mm-hmm. Uh, what do you do when you have to go from, okay, I can get 128 gigs of memory. I can run it on a spark. Then you have to go multi GPU. Yeah. Okay. Multi GPU, there's some support there. Now, if I'm a company and I don't have like.I'm not hiring the best researchers for this. Right. But I need to go [00:31:00] multi-node, right? I have a lot of servers. Okay, now there's efficiency problems, right? You can have multiple eight H 100 nodes, but, you know, is that as a, like, how do you do that efficiently?Kyle: Yeah. How do you like represent them? How do you choose how to represent the model?Yeah, exactly right. That's a, that's like a hard question. Everyone asks, how do you size oh, I wanna run GLM five, which just came out new model. There have been like four of them in the past week, by the way, like a bunch of new models.swyx: You know why? Right? Deep seek.Kyle: No comment. Oh. Yeah, but Ggl, LM five, right?We, we have this, new model. It's, it's like a large size, and you have to figure out how to both scale up and scale out, right? Because you have to find the right representation that you care about. Everyone does this differently. Let's be very clear. Everyone figures this out in their own path.Nader: I feel like a lot of AI or ML even is like, is like this. I think people think, you know, I, I was, there was some tweet a few months ago that was like, why hasn't fine tuning as a service taken off? You know, that might be me. It might have been you. Yeah. But people want it to be such an easy recipe to follow.But even like if you look at an ML model and specificKyle: to you Yeah,Nader: yeah.Kyle: And the [00:32:00] model,Nader: the situation, and there's just so much tinkering, right? Like when you see a model that has however many experts in the ME model, it's like, why that many experts? I don't, they, you know, they tried a bunch of things and that one seemed to do better.I think when it comes to how you're serving inference, you know, you have a bunch of decisions to make and there you can always argue that you can take something and make it more optimal. But I think it's this internal calibration and appetite for continued calibration.Vibhu: Yeah. And that doesn't mean like, you know, people aren't taking a shot at this, like tinker from thinking machines, you know?Yeah. RL as a service. Yeah, totally. It's, it also gets even harder when you try to do big model training, right? We're not the best at training Moes, uh, when they're pre-trained. Like we saw this with LAMA three, right? They're trained in such a sparse way that meta knows there's gonna be a bunch of inference done on these, right?They'll open source it, but it's very trained for what meta infrastructure wants, right? They wanna, they wanna inference it a lot. Now the question to basically think about is, okay, say you wanna serve a chat application, a coding copilot, right? You're doing a layer of rl, you're serving a model for X amount of people.Is it a chat model, a coding model? Dynamo, you know, back to that,Kyle: it's [00:33:00] like, yeah, sorry. So you we, we sort of like jumped off of, you know, jumped, uh, on that topic. Everyone has like, their own, own journey.Cost Quality Latency TradeoffsKyle: And I, I like to think of it as defined by like, what is the model you need? What is the accuracy you need?Actually I talked to NA about this earlier. There's three axes you care about. What is the quality that you're able to produce? So like, are you accurate enough or can you complete the task with enough, performance, high enough performance. Yeah, yeah. Uh, there's cost. Can you serve the model or serve your workflow?Because it's not just the model anymore, it's the workflow. It's the multi turn with an agent cheaply enough. And then can you serve it fast enough? And we're seeing all three of these, like, play out, like we saw, we saw new models from OpenAI that you know, are faster. You have like these new fast versions of models.You can change the amount of thinking to change the amount of quality, right? Produce more tokens, but at a higher cost in a, in a higher latency. And really like when you start this journey of like trying to figure out how you wanna host a model, you, you, you think about three things. What is the model I need to serve?How many times do I need to call it? What is the input sequence link was [00:34:00] the, what does the workflow look like on top of it? What is the SLA, what is the latency SLA that I need to achieve? Because there's usually some, this is usually like a constant, you, you know, the SLA that you need to hit and then like you try and find the lowest cost version that hits all of these constraints.Usually, you know, you, you start with those things and you say you, you kind of do like a bit of experimentation across some common configurations. You change the tensor parallel size, which is a form of parallelismVibhu: I take, it goes even deeper first. Gotta think what model.Kyle: Yes, course,ofKyle: course. It's like, it's like a multi-step design process because as you said, you can, you can choose a smaller model and then do more test time scaling and it'll equate the quality of a larger model because you're doing the test time scaling or you're adding a harness or something.So yes, it, it goes way deeper than that. But from the performance perspective, like once you get to the model you need, you need to host, you look at that and you say, Hey. I have this model, I need to serve it at the speed. What is the right configuration for that?Nader: You guys see the recent, uh, there was a paper I just saw like a few days ago that, uh, if you run [00:35:00] the same prompt twice, you're getting like double Just try itagain.Nader: Yeah, exactly.Vibhu: And you get a lot. Yeah. But the, the key thing there is you give the context of the failed try, right? Yeah. So it takes a shot. And this has been like, you know, basic guidance for quite a while. Just try again. ‘cause you know, trying, just try again. Did you try again? All adviceNader: in life.Vibhu: Just, it's a paper from Google, if I'm not mistaken, right?Yeah,Vibhu: yeah. I think it, it's like a seven bas little short paper. Yeah. Yeah. The title's very cute. And it's just like, yeah, just try again. Give it ask context,Kyle: multi-shot. You just like, say like, hey, like, you know, like take, take a little bit more, take a little bit more information, try and fail. Fail.Vibhu: And that basic concept has gone pretty deep.There's like, um, self distillation, rl where you, you do self distillation, you do rl and you have past failure and you know, that gives some signal so people take, try it again. Not strong enough.swyx: Uh, for, for listeners, uh, who listen to here, uh, vivo actually, and I, and we run a second YouTube channel for our paper club where, oh, that's awesome.Vivo just covered this. Yeah. Awesome. Self desolation and all that's, that's why he, to speed [00:36:00] on it.Nader: I'll to check it out.swyx: Yeah. It, it's just a good practice, like everyone needs, like a paper club where like you just read papers together and the social pressure just kind of forces you to just,Nader: we, we,there'sNader: like a big inference.Kyle: ReadingNader: group at a video. I feel so bad every time. I I, he put it on like, on our, he shared it.swyx: One, one ofNader: your guys,swyx: uh, is, is big in that, I forget es han Yeah, yeah,Kyle: es Han's on my team. Actually. Funny. There's a, there's a, there's a employee transfer between us. Han worked for Nater at Brev, and now he, he's on my team.He wasNader: our head of ai. And then, yeah, once we got in, andswyx: because I'm always looking for like, okay, can, can I start at another podcast that only does that thing? Yeah. And, uh, Esan was like, I was trying to like nudge Esan into like, is there something here? I mean, I don't think there's, there's new infant techniques every day.So it's like, it's likeKyle: you would, you would actually be surprised, um, the amount of blog posts you see. And ifswyx: there's a period where it was like, Medusa hydra, what Eagle, like, youKyle: know, now we have new forms of decode, uh, we have new forms of specula, of decoding or new,swyx: what,Kyle: what are youVibhu: excited? And it's exciting when you guys put out something like Tron.‘cause I remember the paper on this Tron three, [00:37:00] uh, the amount of like post train, the on tokens that the GPU rich can just train on. And it, it was a hybrid state space model, right? Yeah.Kyle: It's co-designed for the hardware.Vibhu: Yeah, go design for the hardware. And one of the things was always, you know, the state space models don't scale as well when you do a conversion or whatever the performance.And you guys are like, no, just keep draining. And Nitron shows a lot of that. Yeah.Nader: Also, something cool about Nitron it was released in layers, if you will, very similar to Dynamo. It's, it's, it's essentially it was released as you can, the pre-training, post-training data sets are released. Yeah. The recipes on how to do it are released.The model itself is released. It's full model. You just benefit from us turning on the GPUs. But there are companies like, uh, ServiceNow took the dataset and they trained their own model and we were super excited and like, you know, celebrated that work.ZoomVibhu: different. Zoom is, zoom is CGI, I think, uh, you know, also just to add like a lot of models don't put out based models and if there's that, why is fine tuning not taken off?You know, you can do your own training. Yeah,Kyle: sure.Vibhu: You guys put out based model, I think you put out everything.Nader: I believe I know [00:38:00]swyx: about base. BasicallyVibhu: without baseswyx: basic can be cancelable.Vibhu: Yeah. Base can be cancelable.swyx: Yeah.Vibhu: Safety training.swyx: Did we get a full picture of dymo? I, I don't know if we, what,Nader: what I'd love is you, you mentioned the three axes like break it down of like, you know, what's prefilled decode and like what are the optimizations that we can get with Dynamo?Kyle: Yeah. That, that's, that's, that's a great point. So to summarize on that three axis problem, right, there are three things that determine whether or not something can be done with inference, cost, quality, latency, right? Dynamo is supposed to be there to provide you like the runtime that allows you to pull levers to, you know, mix it up and move around the parade of frontier or the preto surface that determines is this actually possible with inference And AI todayNader: gives you the knobs.Kyle: Yeah, exactly. It gives you the knobs.Disaggregation Prefill vs DecodeKyle: Uh, and one thing that like we, we use a lot in contemporary inference and is, you know, starting to like pick up from, you know, in, in general knowledge is this co concept of disaggregation. So historically. Models would be hosted with a single inference engine. And that inference engine [00:39:00] would ping pong between two phases.There's prefill where you're reading the sequence generating KV cache, which is basically just a set of vectors that represent the sequence. And then using that KV cache to generate new tokens, which is called Decode. And some brilliant researchers across multiple different papers essentially made the realization that if you separate these two phases, you actually gain some benefits.Those benefits are basically a you don't have to worry about step synchronous scheduling. So the way that an inference engine works is you do one step and then you finish it, and then you schedule, you start scheduling the next step there. It's not like fully asynchronous. And the problem with that is you would have, uh, essentially pre-fill and decode are, are actually very different in terms of both their resource requirements and their sometimes their runtime.So you would have like prefill that would like block decode steps because you, you'd still be pre-filing and you couldn't schedule because you know the step has to end. So you remove that scheduling issue and then you also allow you, or you yourself, to like [00:40:00] split the work into two different ki types of pools.So pre-fill typically, and, and this changes as, as model architecture changes. Pre-fill is, right now, compute bound most of the time with the sequence is sufficiently long. It's compute bound. On the decode side because you're doing a full Passover, all the weights and the entire sequence, every time you do a decode step and you're, you don't have the quadratic computation of KV cache, it's usually memory bound because you're retrieving a linear amount of memory and you're doing a linear amount of compute as opposed to prefill where you retrieve a linear amount of memory and then use a quadratic.You know,Nader: it's funny, someone exo Labs did a really cool demo where for the DGX Spark, which has a lot more compute, you can do the pre the compute hungry prefill on a DG X spark and then do the decode on a, on a Mac. Yeah. And soVibhu: that's faster.Nader: Yeah. Yeah.Kyle: So you could, you can do that. You can do machine strat stratification.Nader: Yeah.Kyle: And like with our future generation generations of hardware, we actually announced, like with Reuben, this [00:41:00] new accelerator that is prefilled specific. It's called Reuben, CPX. SoKubernetes Scaling with GroveNader: I have a question when you do the scale out. Yeah. Is scaling out easier with Dynamo? Because when you need a new node, you can dedicate it to either the Prefill or, uh, decode.Kyle: Yeah. So Dynamo actually has like a, a Kubernetes component in it called Grove that allows you to, to do this like crazy scaling specialization. It has like this hot, it's a representation that, I don't wanna go too deep into Kubernetes here, but there was a previous way that you would like launch multi-node work.Uh, it's called Leader Worker Set. It's in the Kubernetes standard, and Leader worker set is great. It served a lot of people super well for a long period of time. But one of the things that it's struggles with is representing a set of cases where you have a multi-node replica that has a pair, right?You know, prefill and decode, or it's not paired, but it has like a second stage that has a ratio that changes over time. And prefill and decode are like two different things as your workload changes, right? The amount of prefill you'll need to do may change. [00:42:00] The amount of decode that you, you'll need to do might change, right?Like, let's say you start getting like insanely long queries, right? That probably means that your prefill scales like harder because you're hitting these, this quadratic scaling growth.swyx: Yeah.And then for listeners, like prefill will be long input. Decode would be long output, for example, right?Kyle: Yeah. So like decode, decode scale. I mean, decode is funny because the amount of tokens that you produce scales with the output length, but the amount of work that you do per step scales with the amount of tokens in the context.swyx: Yes.Kyle: So both scales with the input and the output.swyx: That's true.Kyle: But on the pre-fold view code side, like if.Suddenly, like the amount of work you're doing on the decode side stays about the same or like scales a little bit, and then the prefilled side like jumps up a lot. You actually don't want that ratio to be the same. You want it to change over time. So Dynamo has a set of components that A, tell you how to scale.It tells you how many prefilled workers and decoded workers you, it thinks you should have, and also provides a scheduling API for Kubernetes that allows you to actually represent and affect this scheduling on, on, on your actual [00:43:00] hardware, on your compute infrastructure.Nader: Not gonna lie. I feel a little embarrassed for being proud of my SVG function earlier.swyx: No, itNader: wasreallyKyle: cute. I, Iswyx: likeNader: it's all,swyx: it's all engineering. It's all engineering. Um, that's where I'mKyle: technical.swyx: One thing I'm, I'm kind of just curious about with all with you see at a systems level, everything going on here. Mm-hmm. And we, you know, we're scaling it up in, in multi, in distributed systems.Context Length and Co Designswyx: Um, I think one thing that's like kind of, of the moment right now is people are asking, is there any SOL sort of upper bounds. In terms of like, let's call, just call it context length for one for of a better word, but you can break it down however you like.Nader: Yeah.swyx: I just think like, well, yeah, I mean, like clearly you can engage in hybrid architectures and throw in some state space models in there.All, all you want, but it looks, still looks very attention heavy.Kyle: Yes. Uh, yeah. Long context is attention heavy. I mean, we have these hybrid models, um,swyx: to take and most, most models like cap out at a million contexts and that's it. Yeah. Like for the last two years has been it.Kyle: Yeah. The model hardware context co-design thing that we're seeing these days is actually super [00:44:00] interesting.It's like my, my passion, like my secret side passion. We see models like Kimmy or G-P-T-O-S-S. I'm use these because I, I know specific things about these models. So Kimmy two comes out, right? And it's an interesting model. It's like, like a deep seek style architecture is MLA. It's basically deep seek, scaled like a little bit differently, um, and obviously trained differently as well.But they, they talked about, why they made the design choices for context. Kimmy has more experts, but fewer attention heads, and I believe a slightly smaller attention, uh, like dimension. But I need to remember, I need to check that. Uh, it doesn't matter. But they discussed this actually at length in a blog post on ji, which is like our pu which is like credit puswyx: Yeah.Kyle: Um, in, in China. Chinese red.swyx: Yeah.Kyle: It's, yeah. So it, it's, it's actually an incredible blog post. Uh, like all the mls people in, in, in that, I've seen that on GPU are like very brilliant, but they, they talk about like the creators of Kimi K two [00:45:00] actually like, talked about it on, on, on there in the blog post.And they say, we, we actually did an experiment, right? Attention scales with the number of heads, obviously. Like if you have 64 heads versus 32 heads, you do half the work of attention. You still scale quadratic, but you do half the work. And they made a, a very specific like. Sort of barter in their system, in their architecture, they basically said, Hey, what if we gave it more experts, so we're gonna use more memory capacity.But we keep the amount of activated experts the same. We increase the expert sparsity, so we have fewer experts act. The ratio to of experts activated to number of experts is smaller, and we decrease the number of attention heads.Vibhu: And kind of for context, what the, what we had been seeing was you make models sparser instead.So no one was really touching heads. You're just having, uh,Kyle: well, they, they did, they implicitly made it sparser.Vibhu: Yeah, yeah. For, for Kimmy. They did,Kyle: yes.Vibhu: They also made it sparser. But basically what we were seeing was people were at the level of, okay, there's a sparsity ratio. You want more total parameters, less active, and that's sparsity.[00:46:00]But what you see from papers, like, the labs like moonshot deep seek, they go to the level of, okay, outside of just number of experts, you can also change how many attention heads and less attention layers. More attention. Layers. Layers, yeah. Yes, yes. So, and that's all basically coming back to, just tied together is like hardware model, co-design, which isKyle: hardware model, co model, context, co-design.Vibhu: Yeah.Kyle: Right. Like if you were training a, a model that was like. Really, really short context, uh, or like really is good at super short context tasks. You may like design it in a way such that like you don't care about attention scaling because it hasn't hit that, like the turning point where like the quadratic curve takes over.Nader: How do you consider attention or context as a separate part of the co-design? Like I would imagine hardware or just how I would've thought of it is like hardware model. Co-design would be hardware model context co-designKyle: because the harness and the context that is produced by the harness is a part of the model.Once it's trained in,Vibhu: like even though towards the end you'll do long context, you're not changing architecture through I see. Training. Yeah.Kyle: I mean you can try.swyx: You're saying [00:47:00] everyone's training the harness into the model.Kyle: I would say to some degree, orswyx: there's co-design for harness. I know there's a small amount, but I feel like not everyone has like gone full send on this.Kyle: I think, I think I think it's important to internalize the harness that you think the model will be running. Running into the model.swyx: Yeah. Interesting. Okay. Bash is like the universal harness,Kyle: right? Like I'll, I'll give. An example here, right? I mean, or just like a, like a, it's easy proof, right? If you can train against a harness and you're using that harness for everything, wouldn't you just train with the harness to ensure that you get the best possible quality out of,swyx: Well, the, uh, I, I can provide a counter argument.Yeah, sure. Which is what you wanna provide a generally useful model for other people to plug into their harnesses, right? So if youKyle: Yeah. Harnesses can be open, open source, right?swyx: Yeah. So I mean, that's, that's effectively what's happening with Codex.Kyle: Yeah.swyx: And, but like you may want like a different search tool and then you may have to name it differently or,Nader: I don't know how much people have pushed on this, but can you.Train a model, would it be, have you have people compared training a model for the for the harness versus [00:48:00] like post training forswyx: I think it's the same thing. It's the same thing. It's okay. Just extra post training. INader: see.swyx: And so, I mean, cognition does this course, it does this where you, you just have to like, if your tool is slightly different, um, either force your tool to be like the tool that they train for.Hmm. Or undo their training for their tool and then Oh, that's re retrain. Yeah. It's, it's really annoying and like,Kyle: I would hope that eventually we hit like a certain level of generality with respect to training newswyx: tools. This is not a GI like, it's, this is a really stupid like. Learn my tool b***h.Like, I don't know if, I don't know if I can say that, but like, you know, um, I think what my point kind of is, is that there's, like, I look at slopes of the scaling laws and like, this slope is not working, man. We, we are at a million token con

This episode is a must-listen for COOs, Agile Coaches, and Business Leaders who want to bridge the gap between "technical agility" and "business agility."When startups grow, they often bring in "responsible adults" who implement traditional playbooks in Finance, HR, and Legal. While well-intentioned, these silos often create a "factory mindset" that undermines the very agility that made the company successful.In this episode, Dave West is joined by Tyson Bertmaring, VP Partnership Success at Dyno Therapeutics and Yuval Yeret, Professional Scrum Trainer, to discuss how Dyno Therapeutics is taking a different path. By applying the Agile Product Operating Model (APOM) to General & Administrative (G&A) functions, Dyno is treating its organizational capabilities as a product to be engineered, not a hierarchy to be managed.What you'll learn:The Stewardship Mindset: Moving from local optimization (like chasing $10k in interest income) to systemic value (ensuring vendor reliability).The "Two Jobs" Challenge: Balancing "running the business" with "building a better system."G&A as a Service: Identifying essential services—like talent acquisition and contracting—and developing them into exceptional "internal products."More!Subscribe to the Professional Scrum Unlocked Substack for more insights on this episode and others!

Your browser does not support the audio element. Know Your States, Know Your Community discusses the state of Hawaii with Dyno Wahl. The post Dyno Wahl on Hawaii appeared first on KRFY Radio.

Send us a textHappy Friday!!! Join us this week as we celebrate the Perfect Team, Perfect Story and Perfect Ending to the College football season! Plus all the Stats Leaders and Need to know in all the pro sports, racin and rasslin plus the return of UFC for 2026 and so so much more its the Best Breakfast Wrestling & Sports Podcast on your Fridays its the Eeez N Beez Podcast!!Support Our Sponsors:Major Performance & Dyno    Dustin SheltonLimpyJasper Graham660 TV       Dave DoanSupport the show

When 1910 Meets 2026: Racing Internals in Brass Era Beasts!

Send us a textHappy Friday!!! Thanks for joining us again as we get your Natty Set Up Playoff Ready and inline with all the Stats Leaders and Need to Know plus so so much more its the Best  breakfast Wrestling & Sports Podcast on your Fridays its the Eeez N Beez Podcast!Support Our Sponsors: Major Performance & Dyno    Dustin SheltonLimpyJasper Graham660 TV   Dave DoanSupport the show

Send us a textHappy Friday!! And Happy Last Episode of the 2025 Year! Join us this week as we dive into all the sporting news updates and need to know along with a couple Very Special Guests to end the Year out Strong in out Sponsors Jasper Graham and Dustin Shelton, as we Award the Eeez N Beez Podcast 2025 No Prep Awards and get you set up for 2026 and so so much more it the Best Breakfast Wrestling & Sports Podcast on your Fridays its the Eeez N Beez Podcast!!Support Our Sponsors:Major Performance & Dyno   Dustin SheltonLimpy Jasper GrahamSupport the show

Stream/Buy: fanlink.tv/GR396 After a powerful series of releases, Dyno returns to Gain Records with his brand-new two-track project, Memento EP — a journey through dark, emotional, and deeply textured techno soundscapes. The title track “Memento” unfolds with a dark yet refined atmosphere, blending deep electronic tones and immersive rhythms. Its hypnotic energy and peak-time intensity are crafted to ignite the dance floor while maintaining Dyno's signature sense of depth and tension. On the B-side, “Spectrum” explores a more hypnotic and atmospheric dimension. Subtle layers and pulsating basslines build an underground vibe that captures the introspective side of Dyno's sound — deep, evolving, and emotionally charged. With Memento EP, Dyno delivers a bold statement of contemporary techno — sophisticated, powerful, and unmistakably his own. ©️ 2025 Gain Records | Gain Plus www.gainrecords.com #SuperTechno #DreamTechno #WeAreWhatWePlay

Stream/Buy: fanlink.tv/GR396 After a powerful series of releases, Dyno returns to Gain Records with his brand-new two-track project, Memento EP — a journey through dark, emotional, and deeply textured techno soundscapes. The title track “Memento” unfolds with a dark yet refined atmosphere, blending deep electronic tones and immersive rhythms. Its hypnotic energy and peak-time intensity are crafted to ignite the dance floor while maintaining Dyno's signature sense of depth and tension. On the B-side, “Spectrum” explores a more hypnotic and atmospheric dimension. Subtle layers and pulsating basslines build an underground vibe that captures the introspective side of Dyno's sound — deep, evolving, and emotionally charged. With Memento EP, Dyno delivers a bold statement of contemporary techno — sophisticated, powerful, and unmistakably his own. ©️ 2025 Gain Records | Gain Plus www.gainrecords.com #SuperTechno #DreamTechno #WeAreWhatWePlay

From PRI in Indianapolis: we sit down with Willy Krup of Willy's Carburetor & Dyno Shop to discuss the new fuel cell vent system. https://www.facebook.com/mhford https://www.youtube.com/melhambeltontv

Nasal vaccines show new promise for human papillomavirus (HPV) to address cervical cancer and whooping cough. In business news, Korro's stock craters 81% as AATD interim Phase I/II results miss expectations. Additionally, Johnson & Johnson acquires Halda to expand their cancer pipeline while Merck acquires Cidara to boost antivirals. Lastly, the inaugural Genetic Agency Technology Conference (GATC) hosted by Dyno Therapeutics brought together a diverse group of researchers, entrepreneurs, and patient advocates to discuss the mission of genetic agency, or an individual's ability to take action at the genetic level to live a healthier life. Join GEN editors Corinna Singleman, PhD, Alex Philippidis, Fay Lin, PhD, and Uduak Thomas for a discussion of the latest biotech and biopharma news. Listed below are links to the GEN stories referenced in this episode of Touching Base: Cervical Cancer May Be Treatable with Intranasal Nanogel Vaccine GEN, November 15, 2025Novel Nasal Spray Vaccine for Pertussis Shows Promise By Corinna Singleman, PhD, GEN, November 12, 2025 StockWatch: Korro Craters 81% on Data; Patient Death Sours Analysts on Intellia By Alex Philippidis, GENEdge, November 16, 2025J&J Expands Cancer Pipeline with $3B Halda Acquisition By Alex Philippidis, GENEdge, November 18, 2025Merck to Acquire Cidara for $9.2B, Bolstering Antiviral Pipeline By Alex Philippidis, GEN, November 15, 2025 AI Meets Genetic Agency at Dyno GATC 2025By Fay Lin, PhD, GENEdge, November 14, 2025Genetic Agency on Display at GATC 2025By Kevin Davies, PhD, and Fay Lin, PhD, GEN, November 13, 2025Dyno GATC Announces AI Agents, Muscle Capsid, and Manufacturing PartnerBy Fay Lin, PhD, GEN Edge, November 11, 2025 Touching Base Podcast Hosted by Corinna Singleman, PhD Behind the Breakthroughs Hosted by Jonathan D. Grinstein, PhD Hosted on Acast. See acast.com/privacy for more information.

On the latest V8 Radio Podcast – Kevin's hopped up on cold meds so he's a bit goofy, but the mellifluous vibes are STRONG! We dive deep into SEMA Show 2025, automotive trivia, Q-Ball's GTO block resurrection, and a LOT more! Listen and subscribe! #V8Radio #SEMAShow #MuscleCars

Marc Karkossa, Co-Founder und CEO von DYNO, hat sein Start-Up mit einer klaren Mission gegründet: mithilfe von Technologie die Vorsorge fürs Alter effizienter zu gestalten. Als "B2B SaaS-Anbieter" digitalisiert DYNO die komplette Kette der betrieblichen Altersvorsorge (BAV). Im Gespräch mit Christoph Burseg spricht er offen über die Missstände in der Versicherungs- und Finanzindustrie. Marc und DYNO gehen einen mutigen Weg, indem sie keine Provision abrechnen, sondern sich ausschließlich über eine monatliche Softwaregebühr der Unternehmen finanzieren. Dies ermöglicht es den Nutzer:innen, deutlich rentabler und kostengünstiger in Altersvorsorgeprodukte zu investieren. Marc fordert radikale Reformen in der Altersvorsorge und verrät, warum der deutsche Staat durch überteuerte Produkte die altgediente Versicherungsindustrie quersubventioniert. In dieser Episode erfährst du: - Wie Lobbyarbeit der Versicherungs- und Finanzindustrie Veränderungen in Gesetzen verhindert. - Warum die betriebliche Altersvorsorge (BAV) als Geschäftsführer:in oder Arbeitnehmer:in ein steuerfreies Investment von bis zu 644 Euro monatlich in ETFs ermöglichen kann. - Wie DYNO mit einer SaaS-Lösung und KI die Lücke in der Altersvorsorge schließt und den administrativen BAV-Aufwand für Unternehmen komplett übernimmt. - Was Marc Karkossa an der Versicherungsbranche am meisten stört und was er am meisten an ihr schätzt. - Wie Technologie die gesamte Wertschöpfungskette reduzieren und dadurch die Altersvorsorge deutlich rentabler und transparenter machen kann. Christoph auf LinkedIn: https://www.linkedin.com/in/christophburseg Kontaktiere uns über Instagram: https://www.instagram.com/vodafonebusinessde/ DYNO Website: https://heydyno.de

For the first time in human history, we can diagnose thousands of genetic diseases—often for under $1,000—but we still can't treat most of them. The problem isn't understanding what's broken; it's delivering the fix to the right cells.Eric Kelsic, CEO of Dyno Therapeutics, joins a16z's Jorge Conde to explain how AI-designed protein shells are solving gene therapy's delivery crisis. They explore why Huntington's patients can now get 15 extra years of healthy life, how Dyno inverted the liver-to-brain delivery ratio by 1000x, and why capsids evolved by nature are now being designed by machine learning models trained on millions of variants.Eric introduces the concept of genetic agency—humanity's first-ever ability to take action at the DNA level—and details why solving delivery for common diseases will make ultra-rare disease treatments economically viable. Plus: what happens when gene therapy requires neurosurgery today but could be a simple injection tomorrow, why recent deaths in clinical trials prove we need better technology now, and how genetic medicine could become as routine as surgery within our lifetimes. Resources:Follow Eric on X: https://x.com/ekelsicFollow Jorge on X: https://x.com/JorgeCondeBioLearn more about GATC 2025: https://www.dynotx.com/gatc2025 Stay Updated:If you enjoyed this episode, be sure to like, subscribe, and share with your friends!Find a16z on X: https://x.com/a16zFind a16z on LinkedIn: https://www.linkedin.com/company/a16zListen to the a16z Podcast on Spotify: https://open.spotify.com/show/5bC65RDvs3oxnLyqqvkUYXListen to the a16z Podcast on Apple Podcasts: https://podcasts.apple.com/us/podcast/a16z-podcast/id842818711Follow our host: https://x.com/eriktorenbergPlease note that the content here is for informational purposes only; should NOT be taken as legal, business, tax, or investment advice or be used to evaluate any investment or security; and is not directed at any investors or potential investors in any a16z fund. a16z and its affiliates may maintain investments in the companies discussed. For more details please see a16z.com/disclosures.  Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

Send us a textHappy Friday!!!!! Join us this week as we get you set up for all the Weekends Leaders Stats and Need to know plus the craziness in the NBA world the UFC 321 fight card and of course the World Series predictions and so so much more its the Best Breakfast Wrestling and Sports Podcast on Your Fridays its the Eeez N Beez Podcast!!!Support Our Sponsor's:Major Performance & Dyno     Dustin SheltonLimpyJasper GrahamSupport the show

We make our way back to Hochman Fabrication and Speed to have Ben back on the show. The Evo has been through some changes, the shop has massively expanded, and it's almost time to part for World Cup: Import vs Domestic. High Performance Academy: https://hpcdmy.co/Minnoxide Use code "MINNOX" for 55% off ANY course Use Code "MINVIP" for $300 of the MINVIP Package Tuned By Shawn: https://www.tunedbyshawn.com Code "Minnoxide" for 5% off! Ship your car with Sure Thing Logistics: https://www.surethinglogistics.net MORE BIGGER Turbo T-Shirts:  https://www.minnoxide.com/products/more-bigger-t-shirt

Send us a textHappy Friday!!!  Join us this week as for the first time since last October we have ALL the Sports back at the same time!! We set you up with all the Stats Leaders and Need to Know plus what's coming up this weekend and so so much more its the Best Breakfast Wrestling & Sports Podcast on your Fridays its the Eeez N Beez Podcast!SUPPORT OUR SPONSORS:Major Performance & Dyno  Dustin Shelton LimpyJasper GrahamSupport the show

Send us a textHappy Friday and We are Glad to be Back!!! Join us this week as we recover from an Amazing weekend at War N The Woods and bring in BMF4 winner and Lead Sponsor of the Podcast Dustin Shelton! We also get caught back up on all the playoff races football stats and of course some Rasslin! Its the Best Breakfast Wrestling & Sports Podcast on your Fridays its the Eeez N Beez Podcast!!Support Our Sponsors:Major Performance & Dyno   Dustin SheltonLimpyJasper GrahamSupport the show

It's common for car enthusiasts to rush their car onto the dyno before it's truly ready, only to have it strapped down and the tuner uncover a list of issues. Nothing kills the excitement of chasing those long-awaited power figures faster than unexpected problems.Booking a session with remote tuning expert Shawn Christenson could save you thousands. Shawn, from Tuned by Shawn, is a Haltech specialist who can remotely tune your car from anywhere in the world.

Send us a textHAppy Friday and Happy First Friday in August!!! Join us this week as we dive into the Outlaws coming to the Rockies along with the Summer Slam card and predictions plus NFL Camp and MLB leaders all the Racin and so so much more it's the Best Breakfast Wrestling & Sports Podcast on your Fridays it's the Eeez N Beez Podcast!!Support Our Sponsors:Major Performance & Dyno , Dustin SheltonLimpy Jasper GrahamSupport the show

Send us a textHAppy Friday!! And Thanks for joining us this week as we Hit a Home Run on this AllStar loaded lineup of Stats Leaders and Need to Know plus our College Football predictions along with all the Racing UFC 318 card and Rasslin you can handle plus so so much more it's the Best Breakfast Wrestling & Sports Podcast on your Fridays it's the Eeez N Beez Podcast!!!Support Our Sponsors:Major Performance & Dyno   Dustin SheltonLimpyJasper GrahamSupport the show

In this episode of the Scrum.org Community Podcast, host Dave West sits down with Tyson Bertmaring, Head of Partnership Success and Adrian Veres, Chief Scientific Officer from Dyno Therapeutics, a cutting-edge gene therapy startup. They share how Dyno applies the ideas of the Agile Product Operating Model (APOM) to complex scientific research—shifting from traditional structures to empowered, cross-functional teams aligned to clear goals.You will hear how Dyno integrates APOM principles such as product-centric team design, continuous planning, and aligned incentives to drive innovation in a high-stakes environment. The conversation highlights how adopting a product mindset, supported by an enabling organization, creates the conditions for focus, adaptability, and breakthrough scientific results. 

The LabWorks Performance owner Anthony Sanchez joins Fenix and Hollywood on the RIG stage - sharing his love of two-wheels and pushing the limits of high performance sports bikes.  Anythony shares his experience from simple maintence and mods to performance builds and dyno tuning for the street and track. https://thelabworksperformancenm.com/ Theme song: "American Rocker" Steven Lane Production & Recording: FCD Productions Rust is Gold Coffee & Racing 3732 Eubank Blvd. NE Albuquerque, NM 87111

Real-world performance is what matters when tuning a vehicle, but let's not pretend the numbers on a dyno sheet mean nothing. The thing is… How can we trust one result from another? How are different dynos arriving at their calculated power and torque figures? And what's the deal with drivetrain losses? Todd Lewis from Mainline Dyno is here to answer these questions and many more. 

Send us a textHappy Friday!! Thanks for joining us this week as we have a Very Special Guest in last years War N The Woods No Prep BIKE Winner Robert Williams!! Plus all the Playoff updates MLB leaders, winners and need to know in the racing world plus we climb the ropes and drop the news in the squared circle plus so so much more its the Best Breakfast Wrestling & Sports Podcast on your Friday's its the Eeez N Beez Podcast!!SUPPORT OUR SPONSORS:Major Performance & Dyno   Dustin Shelton Limpy Jasper GrahamSupport the show

Send us a textHappy Friday!!! Join us this week as we hit the high banks and draft our way through the sporting world giving you all the news leaders recaps and need to know plus so so much it's the Best Breakfast Wrestling & Sports Podcast on your Fridays it's the Eeez N Beez Podcast!!!Support Our Sponsors:Major Performance & Dyno  Dustin SheltonLimpyJasper GrahamSupport the show

Michael Hughes is a postdoctoral researcher at St. Jude's Children's Hospital who studies the overlooked role of water in living systems. His work builds on a growing body of research suggesting that water is not just a passive solvent, but a highly structured, information-rich medium. Hughes proposes that under normal biological conditions, water's ability to form liquid crystalline phases, hydration shells, and coherent domains allows it to act more like an information storage system than an inert backdrop to biochemistry. Drawing on ideas like EZ water, interfacial water dynamics, and liquid-liquid phase separation inside cells that span thinkers from Gilbert Ling to Gerald Pollack, Hughes argues that health emerges from the fine-tuned electrical and structural properties of intracellular water. When this water-protein-electrical system breaks down, disease can result. He outlines a new approach to the body that's rooted in biophysics, not just molecular biology, which he believes might offer novel ways to maintain health and slow aging by restoring the electromagnetic coherence of the body.MAKE HISTORY WITH US THIS SUMMER:https://demystifysci.com/demysticon-2025PATREON https://www.patreon.com/c/demystifysciPARADIGM DRIFThttps://demystifysci.com/paradigm-drift-showPreprint of Michael's manuscript "Rethinking Cellular Organization: Phase Separation as a Unifying Principle in Molecular Biology" https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5171413Dr. Thomas Seyfried podcast w/ DemystifyScihttps://www.youtube.com/watch?v=rxHkXP3G3y4"Live Streaming of a Single Cell's Life over a Local pH Monitoring Nanowire Waveguide" https://pubs.acs.org/doi/10.1021/acs.nanolett.2c02185Rudolf Steiner's Agriculture Course: https://www.youtube.com/watch?v=fwSa8Lpy9-A 00:00 Go! 00:09:54 – Water, Fields & the Electric Body 00:15:01 – Biochemistry's Unifying Principles 00:21:26 – Water, Glutamine & Metabolism 00:23:02 – Liquid-Liquid Phase Separation 00:25:34 – Hydration & Cellular Structure 00:28:08 – Amyloids in Health & Disease 00:33:52 – Environment Shapes Amyloids 00:39:37 – Osmosis, Metabolism & Flow 00:41:04 – Soil Over Seed: Health Revolution 00:42:24 – Evolving Scientific Paradigms 00:46:08 – Cell Theory & Liquid Separation 00:50:34 – Rethinking Genetic Primacy 00:56:12 – Biochemical Research Challenges 01:01:58 – Terrain Theory & Post-Pandemic Trust 01:13:16 – Technology, Ethics & Evolution 01:16:06 – Metabolism as Societal Metaphor 01:21:09 – Lifespan, Healthspan & Food Systems 01:23:25 – Terrain Theory & Neurodegenerative Disease 01:25:10 – pH, Buffers & Biochemical Balance 01:30:03 – Cellular Function & pH Dynamics 01:35:17 – Biochemical Cell Environment 01:39:06 – Intracellular Phase Separation 01:43:07 – Insulin, Gradients & Phase Transitions 01:45:12 – Water, Food & Environmental Impacts 01:48:14 – Personal Diet & Exercise Design 01:57:09 – Experimenting with Your Health 02:00:11 – Dyno comp! #electricuniverse #biochemistry, #structuredwater , #cellularhealth, #watermemory, #metabolism, #quantumhealth, #naturalmedicine, #integrativemedicine, #nutritionalscience, #epigenetics, #philosophypodcast, #sciencepodcast, #longformpodcast ABOUS US: Anastasia completed her PhD studying bioelectricity at Columbia University. When not talking to brilliant people or making movies, she spends her time painting, reading, and guiding backcountry excursions. Shilo also did his PhD at Columbia studying the elastic properties of molecular water. When he's not in the film studio, he's exploring sound in music. They are both freelance professors at various universities. SOCIAL: - Discord: https://discord.gg/MJzKT8CQub- Facebook: https://www.facebook.com/groups/DemystifySci- Instagram: https://www.instagram.com/DemystifySci/- Twitter: https://twitter.com/DemystifySciMUSIC: -Shilo Delay: https://g.co/kgs/oty671

Ned Feehally is an absolute legend from the UK. He's one of the founders of the iconic climbing company, Beastmaker, and he's flashed up to V14. How's that for an intro?!Ned also wrote one of the best books on training — “Beastmaking”, and lately he's been working on 2 new companies he started with his wife, Shauna Coxsey, “Foxy Climbing” and “Mini Beasts”.SHOW NOTES:BeastmakerBeastmakingFoxy ClimbingSupport the showSupport us on Patreon: HEREVisit our podcast page: HERESign-up with one of our coaches: HEREFollow us on Instagram: HERE

We embrace our hybridity, stare down Lovecraftian Donkey-Dragon hybrids, and enter into true Dialogos.Supplementary Material 2501:06 DTG Grievance Mongering02:25 Book Club Reflections04:09 Important Health and Lifestyle Updates09:51 Andrew Huberman's Trail of Death17:14 Jeff Bezos and Media Control25:04 Another exciting round of Lab Leak Discourse!31:17 Scientific Evidence vs. Public Discourse38:28 Matt and Chris' Respectful Debate44:05 Rewriting of Covid History47:04 Conspiracies and Political Pressure50:40 Eric Weinstein is STILL Waiting for the Call59:41 Pageau considers the Lovecraftian Horrors of Sesame Street01:07:17 Sarah Haider (Re)Invents 'Pioneer Traditionalism'01:11:36 Chris Williamson's annual pilgrimage to the Khan01:12:37 Fact Checking Bullshit with Eric Weinstein01:17:16 Breathless Reactions to New Pyramid Theories01:22:59 Credulity Checking with Matt's Son01:24:40 Cruel Racist Attacks on Poor Graham Hancock from the Devil Flint Dibble01:31:44 The Insane Hypocrisy of Alternative Media: Corrupt Academics are being controlled!01:37:21 Soaring Rhetoric, Petty Tribalism, and Obvious Hypocrisy01:39:19 No Charity for evil Flint Dibble01:43:35 OutroThe full episode is available for Patreon subscribers (1hr 46 mins).Join us at: https://www.patreon.com/DecodingTheGurusSourcesNew York Times- Zeynep Tufekci: We Were Badly Misled About the Event That Changed Our LivesKristian Andersen's BluSky thread about the articleKristian Andersen's article about the emails/slack messages, etc.Huberman's lamentations for his dead friendsThe Rubin Report: Analyzing Trump's Tactics | Eric WeinsteinJoe Rogan Experience #2293 - Chris WilliamsonFlint Dibble: Megastructures under Giza Pyramids⁉️ ARCHAEOLOGY REWRITTEN or viral

The K-Swap E30 is running, and driving. What's your guess on how much HP it's making?

Доклады: Cian Ó Maidín | Welcome ( https://youtu.be/TXNklcdXtgI ) Ryan Dahl | Leveling up JavaScript ( https://youtu.be/f7OupG7NnGo ) Marco Ippolito | The path to native TypeScript ( https://youtu.be/4V9qwS--Ksg ) Yagiz Nizipli | Optimizing life and Node.js ( https://youtu.be/bKYG5oxIpC8 ) Aileen Villanueva Lecuona | Node.js ( https://youtu.be/W5QByzuhiI8 ) Michael Dawson | Node.js - What's new and what's next ( https://youtu.be/zDR9xoMKU8M ) Mikola Lysenko | AI powered malware hunting at scale ( https://youtu.be/cxJPiMwoIyY ) Isaac Schlueter | Building a faster package manager ( https://youtu.be/Z1zP6--rta4 ) Jean Burellier | Reviving Express: A challenging road for express 5.0 ( https://youtu.be/9qb6RPWVS4o ) Jonathan Frere | Cleaning up after yourself ( https://youtu.be/dzRGu7aSaLo ) Нас можно найти: 1. Telegram: https://t.me/proConf 2. Youtube: https://www.youtube.com/c/proconf 3. SoundCloud: https://soundcloud.com/proconf 4. Itunes: https://podcasts.apple.com/by/podcast/podcast-proconf/id1455023466 5. Spotify: https://open.spotify.com/show/77BSWwGavfnMKGIg5TDnLz

With Jeff Smith, Cam Benty and Steve Strope Presented by ARP Dyno Don was a pioneering racer sporting a handful of iconic drag cars. Now, his nephew, who has found his own niche in with performance Volvo parts carries on his legacy. Pro street pioneer Matt Hay joins in. Don Nicholson recently finished the full restoration of one of the race cars and had it out at SEMA, PRI and GNRS. Recorded at the Grand National Roadster Show. Checkout Rod Shows at @grandnationalroadstershow and https://www.rodshows.com. Visit ARP Bolts at https://www.arp-bolts.com for all of your engine fastener and hardware needs. Subscribe to Classic Truck Performance, All-Chevy Performance, and Modern Rodding magazines and the rest of In the Garage Media’s content at https://www.inthegaragemedia.com For more automotive videos and TV shows, visit Auto Revolution at https://www.autorevolutiononline.com

With Jeff Smith, Cam Benty and Steve Strope Presented by ARP Dyno Don was a pioneering racer sporting a handful of iconic drag cars. Now, his nephew, who has found his own niche in with performance Volvo parts carries on his legacy. Pro street pioneer Matt Hay joins in. Don Nicholson recently finished the full restoration of one of the race cars and had it out at SEMA, PRI and GNRS. Recorded at the Grand National Roadster Show. Checkout Rod Shows at @grandnationalroadstershow and https://www.rodshows.com. Visit ARP Bolts at https://www.arp-bolts.com for all of your engine fastener and hardware needs. Subscribe to Classic Truck Performance, All-Chevy Performance, and Modern Rodding magazines and the rest of In the Garage Media’s content at https://www.inthegaragemedia.com For more automotive videos and TV shows, visit Auto Revolution at https://www.autorevolutiononline.com

Send us a textToday I am joined by David Rocha! David was a well known rapper in the 90s - 2000s. His rap name was Sir Dyno. During the same time he was also a drug dealer and a gang member. David became very well known on the street by the police and from his music. He would eventually get arrested and go to prison. While in prison David surrendered his life to the Lord. Since he has been free he has been sharing the gospel. 

Diesel Motorsports President Ron Knoch joins the show to talk about the state of diesel racing and give his thoughts about what's happening in the world of trucks. The Truck Show Podcast is proudly presented by Nissan in association with Banks Power, AMSOIL, and EGR USA.

We're joined by the man behind Studfist.com - Dyno!!Sponsored by fuckyeah.uk kink3d.com toppedtoys.com xlube.com

Kenny Wallace gets his dirt car carburetor dyno test at Willy's in Mount Carmel, IL. #racing #kennywallace #nascar #dirtracing Brought to you by JEGS! Click here: http://jegs.ork2.net/rQ9Oy5 ***thumbnail photo by Josh James Artwork JEGS has been in business since 1960. Racers selling to racers. Focusing on American Muscle – but also big product line of automotive tools, garage gear & other performance parts. JEGS is well established with racers of all kinds, including the NHRA, bracket racing, circle track & more! Free shipping on orders over $199. Unrivaled expertise from techs. Millions of parts for every car person's needs. Sign up for their email for exclusive deals!

Emma Hunt is the US speed climbing record holder and will compete in the Paris Olympics. We talked about her intro to speed climbing, how strong you have to be for speed climbing, speed training, how speed shoes compare to other climbing shoes, her mental game and strategy in comps, prejudice against speed in the climbing world, whether the speed route will ever change, why speed is cool, and much more!Watch the Video Interview of this episode:EP 230: Emma Hunt — Uncut VideoBecome a Patron - 7 Day Free Trial!patreon.com/thenuggetclimbing Check out Crimpd!crimpd.comOr download the Crimpd app for free!The Nugget is sponsored by BetterHelp!betterhelp.com/NUGGETUse this link for 10% off your first month!Check out Mad Rock!madrock.comUse code “NUGGET” at checkout for 10% off your next order!PhysiVantage SUMMER SPECIAL!physivantage.com/discount/NUG20Use code "NUG20" at checkout for 20% off your next order of collagen or protein!We are supported by these amazing BIG GIVERS:Michael Roy, Craig Lee, Mark and Julie Calhoun, Yinan Liu, and Matt WalterShow Notes:  thenuggetclimbing.com/episodes/emma-huntNuggets:(00:00:00) – Intro(00:01:50) – Emma's intro to climbing & speed(00:04:08) – “I just wanna go fast.”(00:06:48) – Keeping the fire lit(00:09:28) – Beta changes(00:12:08) – The Start, Dyno, and Top(00:13:10) – Speed nerds(00:16:19) – A rock climber first(00:18:10) – Post-Olympic plans(00:20:41) – How strong are speed climbers?(00:23:25) – How speed climbers train(00:28:42) – Training sections of the speed route(00:30:14) – Off-the-wall training(00:31:56) – Her coaches(00:35:06) – Speed shoes(00:44:59) – Other sports(00:46:27) – Rock climbing as a kid(00:48:27) – What makes Emma so good at speed(00:49:58) – Pre-race rituals(00:51:36) – Speed mental game(00:56:37) – Olympic vs. World Cup format(00:59:06) – Seeds & sides(01:00:39) – Strategy(01:05:01) – Riding waves(01:11:28) – More about the Olympic format(01:13:18) – Speed prejudice & Toyko combined format(01:27:51) – Future Bouldering & Lead comps(01:29:20) – Speed climbing in the mainstream(01:35:22) – We celebrate gold(01:40:39) – Barriers to speed(01:42:30) – Emma's fastest time & goals(01:44:49) – Will the speed route ever change?(01:51:56) – 50-year-old goals(01:53:45) – Rapid fire questions(02:07:51) – Speed is cool

Shaver Specialties Racing Engines is legendary for their success and innovation in the world of Sprint car engine building. Head dyno operator Don MacAskill joins Joe Castello and Lake Speed Jr to talk about how he got into engine building and the R&D work done at Shaver Specialties.

Goldberg talks about hitting the drag strip in his Dodge Demon 170 with Kid Rock and Kenny Wayne Shepherd. Then we welcome Ray McClelland, dyno tuner and owner of Full Throttle Kustomz, back on the show. Presented by DrinkBravago.com

The guys get UCC Champion Ken Bruner on the line to talk about his trail to UCC, his experience at the event, and the build that brought home the trophy. Holman shares his latest exploits on the road, and Lightning is excited to premier some new TSP music. The Truck Show Podcast is proudly presented by Nissan in association with Banks Power and AMSOIL.

Darin Morgan has a rich history in engine building, from designing engines that race in the NHRA HEMI Challenge to working at Reher-Morrison, this life-long Pro Stock engine builder shares his journey on Hidden Horsepower.

Goldberg tells us about running over his iPhone with a lawn mower. Then he talks about his son's Bronco. Matt gets ready to drop off his Mustang Mach 1 for more tuning on the dyno.

In this episode of The Second Degree Podcast join Emily Merrell as she sits down with Kara Kaufmann, a talented musician, to dive into Kara's journey through music and motherhood. From playing piano since childhood to crafting custom jingles for businesses, Kara shares her evolution as an artist and entrepreneur. Discover how Kara's passion for music led her to reimagine her career in children's music and explore the intersection of creativity and parenthood. Get inspired by Kara's insights on finding success on your own terms and embracing the twists and turns of the creative journey. Tune in for a heartfelt conversation about pursuing your dreams and finding fulfillment in unexpected places.What You'll Learn:Kara Kaufman shares her musical journey from childhood piano lessons to crafting custom jingles for businesses.Discover how Kara balanced her passion for music with motherhood and found inspiration in her children's fascination with dinosaurs.Explore Kara's perspective on redefining success and embracing creativity on her own terms.Learn about the evolution of Kara's music career, from performing in bars to creating custom lullabies and jingles.Gain insights into the changing landscape of music promotion and the impact of social media on artists' autonomy and reach.To learn more about Kara Kaufmann and her music, visit her website Karakaufmann.com  and follow on instagram at karakaufmannmusicSign up for The Second Degree Membership! By becoming a member, we're getting more intimate than ever! Get the Membership now! Check our past episodes of The Second Degree podcast! Remember to follow us on Instagram. 

Goldberg talks about doing the driver introductions for the NASCAR race as Bristol Motor Speedway. Then the guys discuss the new Corvette E-Ray on the dyno and Goldberg's fun, custom car cover that he got. Presented by DrinkBravago.com

Earlier this year host Mike Musto made a post about how he wanted to put 10,000-miles on his 1968 Charger in 2024. There were comments and questions, but not so much about the miles, but more so about the engine and drivetrain combination. The specs on the engine are mild. A 440 cubic inch big block with iron 906 heads that were bored .30 over, a 470 lift cam, with an 800 double-pumper on top. The transmission is a 727 with a reverse valve body mated to a gear vendor through an 8 3/4 rear with a 3.55 gear – as for power though, Musto really had no idea what the old lump made.   Enter Hemmings own Evan Perkins, our resident engine guru. He suggested that Musto throw it on the dynamometer at Westech in Southern, California, a mere 450-miles from Musto's home. Not only would that tell him the power output, but as Perkins explains, using a dynamometer is one the best ways to tune your vehicle and possibly even get some extra power.

Here's an actual e-mail from The Untitled Beatles Podcast to M.P.L., sent on The Fifth of November, 2023: Hi Sir Paul or Freda! We are the Untitled Beatles Podcast, America's foremost discussion of profound, focused Beatles scholarship. With the holidays around the corner (AMERICAN ONES, LIKE CHRISTMAS! USA! USA! USA!) we wanted to represent all Beatles and Macca fans with this wish list for 2024: First off, please, absolutely do not deliver long-delayed remasters of “London Town” and “Back To The Egg”. Who needs' em! The most “recent” ones from 1993, with their harsh compression and lack of any meaningful bonus tracks, have held up JUST GREAT. But, please do make us buy “Band On The Run” again! Only this time, change things up. Maybe put the songs in a different order? Take away all of the beautiful arrangements that are baked into this album's legacy? Just one thing: please, do not include “Helen Wheels”. Feel me, holmes? We at the UBP - the home of Producer Casey's exclusive re-mix of your old band's most famous single, “The Movie Medley”, as you're well aware from your cruel lawsuit - guarantee that even the most skeptical fan will find this to be a stunning reissue we never knew we needed. Your skilled team can give this album an intimacy and rawness that somehow elevates the these already great songs. What do you think? Are you in? And while we have a minute with you Sir Paul, or Freda:

Welcome to Season 2 of Topsail Insider! Our  first episode of 2024 is for the small, service-oriented business owner who might be feeling overwhelmed and strapped for time. Are you running solo or with just a handful of employees? Do you find yourself buried in the day-to-day tasks of your business, leaving little room to focus on growth strategies like digital marketing and SEO? If this sounds familiar, you're not alone.In this episode, we sit down with Colin Pemberton, the innovative mind behind Dyno Digital. Colin understands the challenges of being a one-person operation or managing a small team while juggling multiple responsibilities. He's here to offer a solution that could transform your business.Yes, Colin's team can update your website or build one from scratch in as little as two weeks. But what sets Colin apart is his dedication to simplicity and efficiency. He's developed cutting-edge software that streamlines communication, handles invoicing, manages scheduling, and even helps you track your sales pipelines. And the best part? It's all conveniently accessible from your smartphone, so whether you're on a construction site, up on a roof, laying floors, or landscaping, you have everything you need right at your fingertips.So if you're tired of feeling overwhelmed and behind the curve, it's time to take action. Listen to this episode and discover how Colin Pemberton and Dyno Digital can help you take your small business to the next level – quickly, easily, and effectively!Dyno DigitalPhone: (910) 469-1681Email: info@dynodigital.io or colin@dynodigital.ioWebsite: https://dynodigital.io/Free Growth Plan: https://dynodigital.io/growthDyno Digital's Facebook PageDyno Digital's Instagram Page_________________________Topsail Insider is Sponsored by Saltwater Suites and Coming June, 2024 - Saltwater Resort! Saltwater Suites - Topsail Island's premier luxury hospitality experience!Book your beach getaway today at SaltwaterTopsail.com or call (910) 886-4818!Jim is my incredible, rockstSend Christa a message and let her know if you enjoyed the episode! Support the Show.Please Follow/Subscribe to Topsail Insider on your favorite podcast-listening platform so you don't miss a single episode! We're on Apple Podcasts, Spotify, iHeart Radio and more!Please visit TopsailInsider.com and sign up for our Mailing List where you'll get early access to upcoming episodes. Or leave a Voicemail for Topsail Insider right from the website - your message just might be featured in an upcoming episode!Also find and Follow Topsail Insider on LinkedIn, Facebook, Instagram, Twitter, and YouTube!If you are a Greater Topsail business owner or nonprofit and wish to be interviewed or wish to Sponsor or Advertise with Topsail Insider, please email christa@topsailinsider.com or call/text 910-800-0111.

Andy is the go to guy around here for Tuning drift cars. He has been tuning our Power FC cars for the last few years and also tunes a wide variety of other ECU brands. Usually based out of Freedom Motorsportz in PA, Andy has recently taken his dyno on the road and is now mobile! We even had some cars at Raceway Park last year. Make sure to check out his instagram below and feel free to shoot him a message if you need any tuning services. Make sure to leave us a review if you are liking this podcast! Thank you! @andys_mobile_dyno Check out our Sponsors! EAST COAST DRIFT SCHOOL: @eastcoastdriftschool AUTOMOTIVE SPECIALTY WRAPS: @automotivespecialtywraps https://www.automotivespecialtywraps.com/ We have a Patreon! With Exclusive Content and Podcasts: patreon.com/factionmotorsports Check us out on other platforms: Youtube: /FactionMotorsports Instagram: @factionmotorsports Facebook: /factionmotorsports Tiktok: @factionmotorsports --- Send in a voice message: https://podcasters.spotify.com/pod/show/factionmotorsports/message Support this podcast: https://podcasters.spotify.com/pod/show/factionmotorsports/support

Mattias Braach-Maksvytis is an expert boulderer and a doctor of PhysioTherapy from Australia. This episode is all about dynos! Ethan Pringle joins us for another fireside chat as we talk about how Mattias became “the dyno guy” in Rocklands, categories of difficulty and how to grade dynos, how training his legs made him a better all-around boulderer, the key to having the best trip of your life, changing his mindset and enjoying his climbing more than ever, and much more!Check out The Nugget on YouTube:youtube.com/@thenuggetclimbingThe Nugget is brought to you by BetterHelp!betterhelp.com/NUGGETUse this link for 10% off your first month!Check out Wonderful Pistachios!WonderfulPistachios.com to learn more!Check out Rhino Skin Solutions!rhinoskinsolutions.comUse code “NUGGET” at checkout for 20% off your next order!And check out EP 22 with Justin Brown to learn more about how to use Rhino products!Check out PhysiVantage!physivantage.com (link includes 15% off coupon)Use code "NUGGET15" at checkout for 15% off your next order!Check out Rumpl!rumpl.com/nuggetUse code "NUGGET" at checkout for 10% off your first order! We are supported by these amazing BIG GIVERS:Leo Franchi, Michael Roy, David Lahaie, Robert Freehill, Jeremiah Johnson, Scott Donahue, Eli Conlee, Skyler Maxwell, Craig Lee, Mark and Julie Calhoun, Yinan Liu, Renzollama, Zach Emery, and Brandt MickolasSupport on Patreon:  patreon.com/thenuggetclimbing Show Notes:  thenuggetclimbing.com/episodes/mattias-braach-maksvytisNuggets:0:05:26 – Exhales and accents0:08:02 – How Mattias and I first met outside a bathroom in Hueco0:11:26 – Becoming “the Dyno guy” in Rocklands, and his dyno resume0:18:16 – His first hard dynos, and early trips to Font0:21:06 – Hotspots for dynos around the world, and the new 8C/V15 dyno in Spain0:23:57 – Trying an obscure dyno in Bishop, and beta mining0:25:36 – ‘The End' 8A in Rocklands, and what makes a good dyno0:28:08 – Dyno FAs in Rocklands, and dynos that are ahead of their time0:32:12 – ‘Industry of Cool' 8A+, getting better at coordination dynos, which types of dynos hold their grades0:35:15 – How to grade a dyno, and categories of difficulty0:41:01 – Mattias' 8C dyno project, and having his best year of climbing ever0:43:01 – Changing his mindset, and becoming more playful0:51:58 – Needing reference points to determine grades0:53:45 – Training for his 5-year dyno project1:00:10 – Dyno technique, and breaking down the move1:04:19 – Right-handed 8A dynos in Rocklands, and the morpho nature of dynos1:08:36 – Nobody trains legs, how much Mattias weighs, and how increasing his leg strength helped his overall climbing1:11:11 – Getting hit by a van, and how rehab made him stronger1:13:36 – Why he was so psyched to send ‘Caroline' 7C+1:16:16 – Other trip highlights, and why lumbrical injuries have become more common1:23:55 – Being a sub-max comfortable guy, and not needing to do projects right now1:27:15 – Enjoying the chossy lowball, and letting go of pressure to send the mega1:32:43 – Coercing Mattias to try ‘Black Shadow' on his last day, and his level of fatigue at the end of the trip1:36:41 – Why the Basecamp boulder took so long to get developed1:37:43 – Spraying the tick list1:42:45 – The key to having the best trip of your life1:43:49 – Aligning your inspiration with your ability1:46:27 – Is it possible to climb near your potential after 2 months in Rocklands?1:49:45 – Starting his business ClimberCare1:54:47 – Studying to become a doctor of PhysioTherapy, and his evolution as a climber1:57:46 – Wobblers2:03:34 – Ethan's punt on ‘Rodan' 33/8c/5.14b in Waterval Boven2:07:00 – Self-deprecation and kindness2:10:02 – Drawing inspiration from the mutants2:11:21 – V14 goals2:15:50 – Better yeet your meaties