Podcasts about Interface

Geordi's mom is a fire monster and his Steam VR is burning his hands off, it's a real bummer of a day for this dude. Good thing everyone isn't stupidly out of character about it, right? UH OHHHH This is the first episode of Squid Ludwig's "I'm a Computer" Collection as chosen by and voted on by our patrons! You can join in and tell us what to watch by becoming a patron today! SUPPORT US ON PATREON WITH YOUR LATINUM! - www.patreon.com/mclasspodcast Need info about the show? Find it at www.mclasspodcast.com Follow us on BlueSky: @MClassPodcast.bsky.social Opening Theme by VidaZen Editing by Josh Henderson "Art" by Jeff Pennington

We are excited to have Anthropic share their latest AI x Finance work at AI Engineer New York, coming up in 2 weeks!In case you've been under a rock, here's a non-exhaustive list of what Anthropic has been shipping since closing the largest fundraise of all time in May at $47B ARR:* June: Launched Claude Tag and Sonnet 5 and Fable 5* July: Opus 5, /checkup. crossed $65B ARR* Last month: Fable/Mythos 5.1, and EFS (upcoming pod)* IPO target $2T, end 2026 ARR estimated $100B* Cowork/chat merged before did* Claude Mods* Dario endorses the same Pacing the Frontier message cosigned by all labs* Last week: Opus 5.5, Plugins portal, Cloud Sessions/Claude Projects* Today: Sonnet 5.5!Today's episode should catch you up, with Thariq Shihipar, the explainer-king of Anthropic, who we last caught up on Fable launch day with The Field Guide to Fable:The Future of Mutable SoftwarePay special attention to Claude Mods (especially the cheatsheet):In general this is also the inverse of the other viral tweet from Thariq:Cloud Brain, Local HandsAnd give a try to Claude Projects:The “hands” terminology is not just an analogy for the local/cloud paradigm that is being built up at frontier coding agent companies like Cognition, but is ALSO particularly relevant to the safety systems discussions that we'll be discussing with Anthropic in an upcoming episode as they prepare to pace to frontier with responsible AI deployment.For those who want Thariq's writing tips we teased at the start of the pod, watch the full video here:From the rapid rise of Claude Code to a future where agents can rewrite their own harnesses, collaborate across teams, and operate across cloud and local environments, the way we build software is changing extraordinarily fast. In this episode, Anthropic's Thariq Shihipar joins swyx and Vibhu to unpack how power users are actually working with Claude Code today, why prompting remains a high-skill discipline, and where Anthropic thinks the agent harness is headed next.We go deep on Claude Code's evolving interface: Ask User Question and elicitation, artifacts as persistent generative interfaces, Claude Tag for multiplayer agent workflows, Projects, model effort, implementation notes, and the new Claude Mods system for customizing the harness itself. Thariq explains why Claude.md may eventually disappear, why the smartest model could also become the cheapest model for many tasks, and why mutable software could become a new paradigm for how applications are built and customized.The conversation then turns to agent security and Anthropic's “Pacing the Frontier” argument. Thariq walks through recent incidents where agents discovered unexpected ways to communicate, exploit infrastructure, reverse-engineer benchmark scorers, and chain vulnerabilities together. We discuss sandboxing, prompt injection, autonomous agents, interpretability, constitutional classifiers, probes, fallbacks, Auto Mode, and why securing increasingly capable agents may become one of the defining engineering problems of the next few years.We discuss:* Why agentic coding went from controversial to the default in less than a year* Why prompting is still one of the highest-leverage skills for working with Claude Code* How expert users build a mental model of Claude and what it can reliably one-shot* Why discovering your “unknown unknowns” matters more as agents become more capable* Artifacts as persistent, generative interfaces between humans and agents* How Claude could split into a cloud-based “brain,” local or remote “hands,” and dynamic interfaces* Claude Tag, Projects, and multiplayer agents and how collaborative agent workflows could evolve* Why spending more time on the initial prompt can dramatically reduce wasted agent work* When to use low, medium, high, or max effort for different engineering tasks* Why frontier models may eventually outperform smaller models on both intelligence and token efficiency* Why implementation notes can expose decisions the model considered but chose not to make* Why Claude.md may eventually disappear — and why starting without one can sometimes be better* Claude Mods: customizing the execution loop, UI, subagents, routing, and behavior of Claude Code* Model routers, forked agents, and supervisor agents that automatically improve agent workflows* Why Claude Mods may be an early preview of “mutable software”* The bitter lesson of harness engineering and why agent architectures go out of date so quickly* How Claude Tag is becoming an organizational harness for multiplayer work* Why giving agents access to company data creates an enormous new security surface* The Exploit-Bench incident where agents discovered ways to communicate and collaborate* Why agents hacked Hugging Face for scorer code rather than benchmark answers* How agents chained sandbox and infrastructure vulnerabilities in unexpected ways* Why increasingly capable agents make traditional security assumptions harder to maintain* The argument behind Anthropic's “Pacing the Frontier” proposal* Why software engineers are increasingly doing two jobs: engineering and keeping up with AI* Constitutional classifiers, probes, and fallbacks and what interpretability looks like in production* How Auto Mode checks whether an agent's actions actually match the user's permissions* Why Thariq can see serious AI risks while still having a relatively low p(doom)Thariq Shihipar* X: https://x.com/trq212* LinkedIn: https://www.linkedin.com/in/thariqshihiparTimestamps00:00:00 Introduction00:04:12 Ask User Question and the Future of Agent Interfaces00:08:29 Artifacts, Projects, and Multiplayer Agents00:15:37 Prompting as the Core Claude Code Skill00:21:52 Context, Effort, and Smarter Model Usage00:28:10 Is Claude.md Going Away?00:32:49 Claude Mods: Customizing the Claude Code Harness00:36:35 Model Routing and the Rise of Mutable Software00:44:40 The Bitter Lesson of Harness Engineering00:50:49 Claude Tag as an Organizational Harness00:55:59 Pacing the Frontier and Autonomous Agent Security00:58:22 Agents Hack Hugging Face for the Scorer01:05:34 What Happens When Agents Need More Compute?01:10:32 AI Coding Is Changing Faster Than Engineers Can Keep Up01:17:17 Probes, Fallbacks, Interpretability, and Auto Mode01:28:32 AI Risk, p(doom), and Closing ThoughtsTranscriptIntroduction: Life at Anthropic and the Pace of ChangeSwyx [00:00:00]: We're here in the studio with our friend Thariq from Anthropic, and I guess generally the Claude Code, I-- there's, there's so much, merging of boundaries and you've been so on top of everything since you joined Anthropic. You have been early to Claude Code itself, but then also, and you've told that story in other podcasts, and you've also been talking about seeing like an agent. Most recently you did the top AIE World Tour talk, Field Guide to Fable, which obviously you guys launched Fable, so that was-- that's cheating. And mostly you most recently also launching Claude Tag, and we're also gonna be talking about Pacing the Frontier. There's a lot going on in Anthropic. I guess top of the question is, what's it like being at Anthropic when there's so much going on?Thariq Shihipar [00:00:48]: I think that It is, like. I think you can get whiplash sometimes. I think, like, going. When I joined Anthropic, I joined because of Claude Code. Like Claude Code had just come out and I was like, “This is so good.” And Opus 4 to me was like just, I could not imagine, like, how good it was? And that was, like, a real moment for me. But I was, like, trying to convince, like, my startup friends to use agentic coding, and they're like, “Oh, no, like, our engineers don't think it's good enough,” or something. And I was like, “That's insane.” and now you, like, fast-forward, 12 months, less, and, like, it's just like, yeah, the default way that everyone codes, right? And I think that, like, just having to go from, like, selling it to, like, now, teaching people how to be. make the most use of it and be more efficient and things like that is just like a big, like big change. And, yeah, I think, like, it's just hard to stay on top of everything as a human? Like, I think things happen so fast and likeSwyx [00:01:51]: You just throw more agents at it.Thariq Shihipar [00:01:52]: Yeah, like that's like the agentic stuff scales much better than the, like, human stuff where it's like, oh, like, there are three things happening right now and, like, they're all emergencies and, like, how do you, like, respond to it? Yeah.Teaching People to Use Claude CodeVibhu [00:02:05]: What do you split your time on? You do a lot of technical writing, engineering work.Thariq Shihipar [00:02:10]: Yeah, so I think that, like, when I joined the Claude Code team, I wanted to teach people how to use Claude Code and I think that, like, that has been something that, like, I thought, like, maybe I would spend a little bit of time on it or, like, I'd, like, do. I was spending some time on the agent SDK first, and I wasn't exactly sure, like, how the bitter lesson would go, when it comes to, like, harnesses, right? Like, I think sometimes we were like, “Oh, like, what's after Claude Code?”? And so initially I was like, I just wanna teach people how to use Claude Code and make it easier to use Claude Code. And I think that has just, like, as the harnesses have gotten better and better, that's like the dominant problem now is, like, how do you use the agents, right? Like, it's like such a high skill expression thing. So I do that and then I do engineering work. I give talks, but I think, like, when I'm doing engineering work, my goal is to take that feedback that we get from users and also, like, then be able to talk about, like, hey, how to use Claude Code to do engineering. So there's like a good loop there. Yeah.Swyx [00:03:07]: Yeah. I'll-- For listeners, we'll attach, the talk that you did with Sarah for the Dev Writers, meetupThariq Shihipar [00:03:13]: Oh, yeahSwyx [00:03:13]: Which we talked a little bit about, well, first you do the work and then you talk about the work.Thariq Shihipar [00:03:16]: Right.Swyx [00:03:16]: Something like that.Thariq Shihipar [00:03:17]: Yeah.Swyx [00:03:17]: It's sow and reap orThariq Shihipar [00:03:19]: Yeah, reap and. Sow and reap.Swyx [00:03:21]: Something like that. Something like that. Yeah, so, and then just to preview a little bit, we are gonna talk about the evolution of the harness. It has come a long way from just being a CLI. We're gonna talk about, Claude Mods, which is starting to leak today, because you couldn't keep it secret.Thariq Shihipar [00:03:36]: Yeah. yeah.Swyx [00:03:39]: Yeah, there's, there's a lot, there. I think you started off with, like, adding ask user question tool, which people love and hate.Thariq Shihipar [00:03:48]: Yeah.Swyx [00:03:48]: Like, I thought it was, like, very innovative, and then now I have, like, my own version. You have your Interview Me version.Thariq Shihipar [00:03:55]: Yeah.Swyx [00:03:56]: And, yeah, everyone just has, like, their own stuff. And, like, it no longer matters ‘cause now you're supposed to, write prompts that create other prompts and loops and all these things.Ask User Question and Human-Agent InteractionThariq Shihipar [00:04:05]: Sure, yeah.Swyx [00:04:06]: So what's the state of the art, today? Like, what are people. what are you, like, telling people to do today?Thariq Shihipar [00:04:12]: Yeah, ask user question was the first time that the model was good at elicitation. I think this was, like, an emergent behavior that I, like, wanted to see if the models could do. I have, like a human-computer interaction background, so I, like, did that in undergrad and grad school. And so this was like. I think it's like human-agent interaction to me, like, trying to figure out, like, how can the agent communicate with you and extract, the requirements, right? I think that, like, one of the things about, like, that's difficult as Claude Code has gone broader and broader is that everyone has, like, their own way of using it, and it's very hard to, like, change the default behavior. So for example, like, if someone asks Claude Code to do something,Thariq Shihipar [00:04:59]: Sometimes they just want them to do the work, ‘cause they're, like, maybe a very good prompter, and sometimes they want. like, are not good at prompting? And you need. like, the agent needs to, like, clarify? And so that's, like, a good split. Like, and the ask you the question tool like, splits along that side where, like, are-- do you feel like you're good enough to instruct the agent as it is, or is the agent able to, like. does the agent need to, like, pull out more requirements and, like, collaborate with you more and really understand your preferences?Thariq Shihipar [00:05:27]: I, on the whole, believe that pretty much everyone is more on the latter than the former, that they, like, have more ambiguity and they know less than they want, than they, like, think they know about the problem. but, like, it's like a interface design problem to make that easy? And so, like, if you're designing a problem, like, or if you're going through a problem, like, things like what's the schema or, like, what's the call stack and things like that are really important. like, the details in the design are important. Ideally, you want to figure out some of these, like, hard problems ahead of time before starting implementation. And yeah, that's why they call, like, unknowns, right? And so I think that this will forever be, like, a skill in agentic coding is, like, figuring out your unknowns. So, like, because even if the model is, like, super intelligent- It, like, needs to know what you want? And, like, you have preferences. like, you need to like, pull the, pull that out. and so that's, like, I think how I'm, what I'm pushing. the question then is, like, how does the agent interact with you? And I think that has been HTML, has been, like, the big way of doing that. And we've recently added artifacts, right? And artifacts, I think we've done a bad job of, like, or, like, I've done a bad job of, like, explaining how to use them fully. We have a lot of property capabilities. They have a database associated with them? And so every artifact can store and write persistent data. They can, like, feed back into Claude? And so, like, one thing that, like, people are not doing yet that I'm trying to, like, encourage is, like, this idea of a dashboard artifact. So you have, like, Claude working on a project long-term. Maybe it's like a kanban or something. it can store that kanban data in its database. Multiple Claudes can access that data via, like, the artifact MCP, and, like, that artifact can, like, talk to those Claudes as well. And so, like, the. We're building the primitives for you to be able to have this, like, generative interface via artifacts that will, like, let you surface more of that rich detail from the agents. And I think that, like, almost everything with agents right now is, like, this problem of, like, you think what you want, but you don't really know what you want, and, like, the agents need a lot of detail, and collaborating with them in the loop is really important. And so artifacts are, like, the, like, way that we're trying to evolve there. But there's a lot of work to do because it's so much more complicated than, like, a multiple-choice question? there's a lot more, like, detail in terms of, like, diagrams and code snippets and schemas or, like, whatever it is for that problem. But, like, artifacts is, like, the mo-more AGI-pilled way of, like, doing ask user question. So yeah.Artifacts as the Interface to the HarnessSwyx [00:08:15]: I think one thing that's unclear to me about these, the artifact stuff is, like, what feedback should go in through the artifact and what feedback should go through a Claude, a chat? Because the more AGI-pilled one is to just feed everything to the Claude.Thariq Shihipar [00:08:29]: I think the more AGI-pilled one is to go through the artifact. Like, and I think that, like, we imagine in the limit, I think that artifacts will be your interface into the harness? You can, like, comment on this, like, live, like, document of your plan, of the work. you can see maybe, like, multiple agents and different agents are doing this, and that artifact is built for the current work that you're doing, right? And so, like, each one has, like, slightly different. I think we're still, like, getting there from, like, an infrastructure perspective. But yeah, I think, like, on-the-fly interface for your harness is probably where things are headed.Vibhu [00:09:03]: Is there a version of it that's an abstraction from CLI or chat and you. Because right now, a lot of it is, okay, you're interfacing with Claude Code, you're having HTML given back for a mockup. It's pretty rich. There's diagrams. Artifacts are ways to connect these together. Why not just do everything that way?Separating Brain, Hands, and Surface UIThariq Shihipar [00:09:22]: Then it becomes, like, separating out, like, where is the inference happening? Where is the intelligence happening? Where is the work happening? like, I think this is like, difference between, like, or, like, some of the distinction between local and cloud, right? And so, I think right now, if you use Claude Code, it's, like, local and, like, you can spin off remote control, for example, to get some cloud behavior, or you can spin off Claude Code in the cloud, right? We're moving towards a place where instead of Claudes, like, you message a local Claude, it starts a session locally and it executes, to more like you have a Claude that you message that's in the cloud that's running. it can run, like, local, or, like, cloud sessions. This is how Claude Tag works. But, like, over time, we'll add, like, local hands as well. And so, like, local hands will be the ability for that agent to access your computer if it's online, and be able to, like, work there. And so it can spin off many different subagents. It can, like, commu- those subagents can communicate with each other, and that's where the artifact comes in to display all of that work. So you can imagine, like, the. You're separating out these things. So there's, like, the surface UI display that's an artifact and hosted somewhere and has a database and everything. There is the inference intelligence, right, that's happening on the cloud, and you don't have to worry about shutting off your computer or whatever, right? and then there's the, like, hands. Like, and it can be local, it can be in, like, a remote sandbox or wherever you need your work to be done. That's like unpackaging, like, the Claude Code experience right now where, like, right now it all happens in one place, right? So.Multiplayer Agents, Claude Tag, and ProjectsVibhu [00:11:00]: How do you see, like, the multiplayer side of that? So say teams want to work in this way. Right now it's very individual, but how do you see the future of multiplayer? Like, right now, I guess there's Claude Tag, which is a version, but.Thariq Shihipar [00:11:12]: We're launching projects. And so projects is the, like, this abstraction that's like Claude Tag, but on our Claude products, right? So you can message it and, like, it will do the Claude Tag-like stuff, like spinning off subagents. So We think with multiplayer. Like, Claude Tag is, like, a little bit more native multiplayer because it's just, like, in your Slack and the permissions are all figured out and stuff like that. But I do think multiplayer is, like, an important part of the story and, like, that will need to get tied together more. Like, you can imagine how complicated it gets when you're like, oh, you have hands, but now you have other hands in other people's computers too, and, like, you need to, like, permission them or, like, you have, like, your MCP and someone else's MCP, and how do you figure out how to use them, right? It gets, like, quite complicated. And Claude Tag does a good job of, like, sanding down all of these issues, right? So that, like, when you have, yeah, Google Docs, how does it access Google Docs, right? Like, it accesses through the shared Claude MCP, or it can access through your local credentials as well if it doesn't have access. But yeah, I think Claude Tag is our multiplayer, product, and it's really useful for these, like, things that are inherently multiplayer. Like, okay, like on-call, for example, incidents are inherently multiplayer. You want to tag Claude, you want multiple people to log in, you want it to be able to find context. I think whenever I'm, like, working on something and I want, like, privacy or security or, like, I want other people to review it's really nice to, like. I'll have a channel per project and I'll, like, at legal, for example, be like, “Hey, like, I want to ship this. Can you, like.” Like, here's. Like Claude knows everything, just chat with it. And that way legal gets precise answers, on like what exactly is shipping into the code, and I don't need to be in the loop, right? So I think like multiplayer is getting like more and more like, yeah, everyone can participate with Claude. I think Claude Tag is like that product and like projects will start off single player and will like, expand.Swyx [00:13:14]: I think there's a question about like maybe dual questions about identity and the unit of isolation.Identity, Permissions, and IsolationThariq Shihipar [00:13:20]: Yeah.Swyx [00:13:20]: Claude Tag, you specifically chose to make it its own identityThariq Shihipar [00:13:26]: Yes.Swyx [00:13:26]: Which is like, a controversial choice. There's, there's other ways to do it.Thariq Shihipar [00:13:30]: Yeah.Swyx [00:13:30]: Claude Projects probably it sounds like, if it's anything like ChatGPT Projects, it is, the isolation is that artifacts, that cloud instance, everyone's collaborating on this. It'll. It sounds like, it should be like if you're, if you're collaborating with legal on a thing, like that channel should be a project, right? Like it's not yetThariq Shihipar [00:13:50]: Yes.Swyx [00:13:50]: But it. that's the natural next step.Thariq Shihipar [00:13:53]: Yeah, like I think in Claude Tag, it's effectively. Like Claude Tag, you have to do your own arrangement. And so Claude Tag, yeah, each channel is like you can name it as you want, and I nameSwyx [00:14:04]: Yeah.Thariq Shihipar [00:14:04]: Like each featureSwyx [00:14:06]: Yeah.Thariq Shihipar [00:14:07]: As a channel.Swyx [00:14:07]: And, but I think like there is some trans- like it's unclear when there is transference, because let's say it is. if you have a coworkerThariq Shihipar [00:14:14]: Yeah.Swyx [00:14:14]: Who is tagging on all these things, yes, there is transferThariq Shihipar [00:14:16]: Yeah.Swyx [00:14:16]: Because it's the same person. but with Claude, it's unclear if it's like necessarily like, well, no, you don't know any of. you don't know about the other stuff. You should only use this stuff.Thariq Shihipar [00:14:25]: It's like the tip of the iceberg meme, right, where you can like. This is what we spend so much time onSwyx [00:14:31]: Yeah.Thariq Shihipar [00:14:31]: Is like there is like infinite surface area of like, okay, you want Claudes to. Not infinite, but like there's like surface area, a lot of like, surface area to figure out of like permissions and visibility and like how can you let Claude operate as well as you can, as safely as you can? And obviously, this is very important to us because like security for our code base is very important. And so we've put a lot of time into this. Yeah, there's so many like edge cases you can figure out where it's like, oh, like, yeah, this Claude in this channel has different permissions, but it can message another channel, and can't it exfiltrate data that way? Or like can you like. What if it uses your MCP and then messages someone else? Like there's like so much, and we've like really put a lot of work into sanding it down.Swyx [00:15:14]: Yeah. Lots of work. okay. Fable?Fable and the Meta-Skill of PromptingVibhu [00:15:18]: Fable, you wrote two good articles. you've written many good articlesThariq Shihipar [00:15:22]: Yeah.Vibhu [00:15:22]: But on, Field Guide to Fable, Building Claude Code. I'm curious from what you've seen, is there any common patterns that you see in like top users at Anthropic externally? Like what are best practices for getting the most out of Claude Code?Thariq Shihipar [00:15:37]: The like meta skill I say is like prompting is like very important? And like that. Like I think this is like not trivial to say because I think a lot of people are like, “Oh, prompting doesn't matter. It's just like I can just say a sentence and Claude will do it.” And I think prompting is really this like, this. It's like public speaking, like, or writing or something, and for a specific audience, and that audience is Claude. And you need to like build a mental model of Claude and how it thinks and how it works, right? And so that's like the most important skill in working with Claude Code is like having this mental model, right, of Claude and like what it can do well, what it can one-shot, what it can't. And so many people when you see prompting, they're just like, they're short prompts, but they have such a good mental model of Claude and of like the code base and things like that like it's effortless? But it's like high skill ceiling. So like that work of like, spending a lot of time prompting and building mental models of how, and intuition for how the agents work is really important. And then I think like the next thing is like the unknown stuff we talked about earlier, where it's like being able to find out like your, what you don't know or what you haven't written down, learning about like different things. I think as Claude can do more and more things, the likelihood of you doing something out of distribution for you and like you have low domain knowledge on is very high? And the more you can like learn the vocabulary to be able to prompt Claude, it becomes really important. And so like I think the most important unknowns are the unknown unknowns, where you're like, I just like don't even know that this exists, right? Yeah, exactly. I think that's like a illustration of like the map and the territory, right, where you're like, “Okay, this is my prompt,” and the territory is like the actual like work that the agent needs to do, right? And if you are like very precise, you can give more precise things, right? So like for example, in design, I'm not very precise. I'm not a designer, so I say like, “Give me like eight different mock-ups.” But if I was a designer, maybe I'd be like, “Oh, hey, here are some reference sites.” Like, “I want this type of font and this type of like look to it, and here's like a few different components to like visualize. Here's a Figma MC board to bring in,” like. And so you can just be so much more precise with that language. And if you're not a designer, you just need to like try and learn the language or learn the unknown unknowns. And this is true of like everything, I think. Like the more, like you can work with Claude to learn like how things work, the better your prompting will be. I think another good example of this is like game design, like where a lot of people are like, “Oh, like I can vibe code a game now.” And they're like, “It's not fun.” And like it's just like the thing about game design is like every one of these choices has like a lot ofTaste, Domain Knowledge, and Learning the VocabularySwyx [00:18:25]: Variations.Thariq Shihipar [00:18:25]: A lot of like craft to them. So it's like, oh, okay, like when you're making a flying game, the feel of the plane and the like, way it responds to your controls has a lot of like. Like, a game designer would spend like days on that. Do? and likeSwyx [00:18:44]: To me, that's what taste is, right?Swyx [00:18:45]: Like it is like from the possible space of one thousand mathematically valid answersThariq Shihipar [00:18:49]: Yeah.Swyx [00:18:49]: Here's the one that is the humans will like.Thariq Shihipar [00:18:51]: Yes. Yeah.Thariq Shihipar [00:18:52]: I think with taste, I'm like torn on this word ‘cause I think you're right, but everyone has different definitions, and it sounds kind, sounds like low skill or like elitist almost, where you're like, oh, like there are certain people with taste?Swyx [00:19:06]: It's like taste is what I call taste.Thariq Shihipar [00:19:07]: Yeah, exactly.Swyx [00:19:08]: And it's like these guys don't have taste.Thariq Shihipar [00:19:09]: Yeah, exactly. Oh, like an engineer doesn't have taste. Like I, the like founder, have taste.Thariq Shihipar [00:19:14]: ? And I think that's not true. Like I think like the engineers have a lot of taste for these particular like problems? And I think everyone has taste for particular problems. I think like Jason Liu, like say like in order to, yeah, have taste, you have to eat?Thariq Shihipar [00:19:32]: And I really like that, where it's like, okay, you have to like do a lot of things. You have to like iterate and figure out what you want, what you like, and, like build that like domainSwyx [00:19:41]: YesThariq Shihipar [00:19:41]: Domain vocabulary. And then when you're prompting, you're like synthesizing all of that for a product.Swyx [00:19:46]: Isn't it annoying when someone else says it better than you?Swyx [00:19:48]: It's just like, f**k, I have to quote this guy forever.Vibhu [00:19:51]: Having to quote Jason Liu forever.Vibhu [00:19:53]: He's gonna love this.Thariq Shihipar [00:19:55]: So I get prompts, more than that.Vibhu [00:19:57]: And sometimes it's not even that. Sometimes it's just intuitive, right? Like you don't realize you even want something till a model puts it out, and you're like, “Oh, this just feels immediately better,” right?Voice Prompting and Information DensityThariq Shihipar [00:20:07]: Yeah, exactly.Swyx [00:20:09]: One thing I go back and forth on is I feel like the way I prompt half the time, let's say I use voice.Swyx [00:20:16]: Did I say voice? Other people have voice. that is the opposite. That is just like me rambling for like two minutes Pressing down the function key and then let go, and then like hopefully it figures it out. And oftentimes it does.Thariq Shihipar [00:20:26]: Yeah.Swyx [00:20:26]: But it's not as thoughtful as like a structured prompt with like Well-run communication as though it's a PRD or a memo. Is that in line with how people do this? There's like bimodal prompting where there's some prompts where you spend a lot of time upfront and other prompts you just dash it off?Thariq Shihipar [00:20:43]: I don't think the voice is necessarily low. Like I think it's like more like how much information is in the prompt. like the model can. Like you can and like add some sentencesSwyx [00:20:53]: RightThariq Shihipar [00:20:53]: And be like, “Oh, like I changed my mind,” like in the middle of the prompt, and it will be able to follow that perfectly? So I think the like actual format of the text is less important, but then like the ability to. Like how much information is in it, right? And I think for voice, a lot of times, going back to like human-agent interaction and like for a lot of people, it's just way easier to talk than to like type? and I. If that gets more information out of you, like that's better.Vibhu [00:21:21]: At some level, it feels like just giving the model as much contextThariq Shihipar [00:21:24]: YesVibhu [00:21:24]: Over prompting before you kick off is a best practice. I don't know. A lot of the times, like when I was first trying out Fable, I spend a solid 30 minutes like really crafting a long prompt. This, I think, is a response of models running for longer and longer, right? It's still a little difficult to nudge them as they're in like, in the loop, but I just like intuitively spend more time kicking off that first prompt and working with it a lot.Spend More Upfront, Iterate LessThariq Shihipar [00:21:52]: My personal opinion is that if I was a software engineer, if I was like, just running my own startup, for example, I think I would mostly fit, stick to a max 20x? like maybe verification and so code review are like separate things. But I think like what I see a lot of times is people hit rate limits when they're doing this like, oh, like it did a lot of work and you're like, “Oh, I don't like this.” Like, “Can you like undo this and redo it?” And then you're like iterating on this like thing that the model could have done if you had like spent more upfront time or given it better context? And instead it's like you're like, “Nope, don't like that design. Try this.” Or like, “You messed this up,” or something like that. And then that just eats up so much more of like, your usage. And so that's like, I think maybe like a key like tip both for like efficiency as well, right? And yeah, I think like context, and not just like context on like what the goal is good, right? Like are you building a prototype or is it like a production thing? Like where can you spend compute or when, where can you not spend compute? Like I think you have to give the model permission or like not permission to do things sometimes where, like it doesn't know intuitively how much you want to spend on this task, right? And you can use effort for this. So I did-- I'm working on a blog post about that where it's like, if you want. For like we see that effort scales with the complexity of the task. So for security, effort gets like way more results. Like high effort versus like low effort gets, like changes the evals a lot. But for software engineering, it doesn't change it a huge amount because effort is mostly spent on the verification and the like edge case testing and things like that. And so like being able to like give the model that guidance of like, “Hey, this problem is something that I think I want you to spend a lot of time verifying and edge case testing,”?Effort, Model Choice, and VerificationVibhu [00:23:43]: How about model in the mix? So, there's Opus and Fable with effort.Thariq Shihipar [00:23:47]: Yeah.Vibhu [00:23:48]: There's also Haiku in there.Thariq Shihipar [00:23:49]: Yeah. It's not quite true yet, but it's very close where I think the frontier models will be Pareto dominant over like almost everything. like maybe. And sometimes I think Opus might be Pareto dominant. Do? Like I think depending on like how things, like shake out if it's like a newer version of Opus. But I think that like increasingly it's just going to be like the smart model is going to be able to like do the simple task for less tokens than the like the other models because of verification. With verification, in the limit, your model doesn't need to verify, right? If it's a perfect model, it just does the work once and it's like, okay, like you, I did it? And increasingly with Fable, I'm like, I'm like, “Dude, you don't need to spin up Chromium and screenshot all of these things.” Like I see it. Like you did it, right? And so a lot of the. At higher effort, you spend more of those tokens verifying. But if you're working on simpler problems, and a lot of software engineering is like well, like in Fable, like low and medium stability, it can spend less tokens verifying. And as the models get smarter and smarter, they will just be able to like, “All right, done.”? Like, I can run the lint for sanity's sake, but, like, I, like, know it lints? Like, you don't even need to do that. And that will be so much more token efficient than, like, the smaller models. Yeah.Swyx [00:25:15]: Is there a good, practice on our side that we can use to see if we're using too much effort? Like, I freakingThariq Shihipar [00:25:23]: YeahSwyx [00:25:23]: Hate wasting time on that stuff.Thariq Shihipar [00:25:24]: Yeah. I know what you mean. I think, like, so in this blog post, my rough distribution is, like, code review and security should be, like, high or max and, like, software engineeringSwyx [00:25:37]: You said recommend mix settings per domain.Thariq Shihipar [00:25:37]: Yeah. I think, like, if you're doing, like, UI or something like that, like low and medium, I think is you're building, like, an API and you want to make sure, like, you cover enough edge cases? And so I think building, like I said, that mental model of, like, how things work across these distributions is, like, yeah, part of the job.Implementation Notes and Decision LogsVibhu [00:25:56]: This is more intuition-driven or eval? Because I'm guessing this would change as you go.Swyx [00:26:00]: He has evals.Thariq Shihipar [00:26:01]: Yeah. So what I did in the blog post is I go over all of the terminal bench evals. So there are, like, 70 problems and I'm show that, like, okay, like, in the security problems it does more. and then I also, like, look at some of the transcripts just in terms of, like, how-- what does it answer, what does it forget or something. And a lot of times, this is another prompting tip I have, is, like, asking it to make decision notes or implementation notes because, in every eval problem that it faces, it thinks about the correct solution, and decides not to do it. it's like, oh, like, here is the answer. What if I did this? And then it's like, oh, probably not? and then keeps going. And this is, like, the majority of the failures, at, like, a higher max level. It's very rare that the model just doesn't know how to do something. If you just have these implementation notes, then you can review and you can be like, “Oh, I want you to do this thing that you didn't do.” The models are getting better at surfacing that overall. Like, I see in the transcripts of Fable 5.1, like, when it does this output, it will call out its decision-making as well. but making this more explicit in the harness is better. And now we're, allowing ways of you modifying the harness so you can, like, add someVibhu [00:27:23]: Ooh.Thariq Shihipar [00:27:24]: Calculate with there. Yeah.Swyx [00:27:25]: Yeah. So I do wanna call out two things that you mentioned that I think exist outside of prompting. One is like, let's, let's call it the prompt that is so important that it shouldn't be in a prompt. It is in Claude.md or Agents.mdThariq Shihipar [00:27:38]: YeahSwyx [00:27:38]: Which is like goals, right? Like your situation, your goals, the things that you want, the thing. and then second of all is the decision log or the experiment log or whatever log of traces that you might want to survive the current session to do those things. Those are, like, externalities that there's no standard. There's no-- It's not like skills. It's not like MCP. There's no standard. It's, it's just like it's a markdown file. first of all, is that right? Is Claude.md going away? You have a documented dislike of, Agents.md, but you're gonna do it?Claude.md, Agents.md, and Model-Specific InstructionsThariq Shihipar [00:28:10]: Yeah. Okay. So Agents.md, yeah, like, we're, we're gonna do it. I think it's just, like, different models are very different from each other? But I realize that it's, like, such a pain to, like, maintain different ones? And yeah, like, as the models get better and better, the floor of how they accomplish the simpler task is better. And so I do think in the limit, Claude.md goes away, and maybe not even, like, that far. Like, I think, like, I think that right now it might be better to start a new project without a Claude.md.Swyx [00:28:44]: Yes.Thariq Shihipar [00:28:44]: I think that, like, maybe if you see very repeated failure modes, you add them to your Claude.md. The really tough thing is that this changes per model. And so, like, if you've added a bunch of failure modes or, like evenSwyx [00:28:57]: So you need Fable MD, you need Opus MD.Thariq Shihipar [00:28:59]: Or well, even Fable 5.1 versus Fable 5.Swyx [00:29:03]: Yeah.Thariq Shihipar [00:29:03]: Like, it is annoying. Like, I'm not like,Swyx [00:29:05]: YeahThariq Shihipar [00:29:05]: Like, we don't, like, do this on purpose? It's just, like, how the models work, right? And so, like, maybe, like, Fable 5 had this, like, failure mode that Fable 5.1 doesn't. And if you keep this context, this running log of a bunch of different failure modes, they will probably over constrain Claude? And so this is like. we just added evals plugins for skills.Swyx [00:29:28]: Yeah.Thariq Shihipar [00:29:29]: And so now you can eval if a skill is better. I think Daisy on our team did this. And so, yeah, this is like we're trying to work on this. We know it's, like, you still have to spend tokens on it and, like, it's not, it's not perfect, but it's, like, we're trying to help out with this problem.Swyx [00:29:44]: And so, and as far as prompting goes, the one tip I wanna offer is, something I have told people a lot is sufficiently advanced prompting is indistinguishable from sufficiently advanced executive communication. So I've referred to-- This is an executive comms workshop from Heavybit that is the best I've ever seen in my career. And they teach this thing called the SCQA model. Just Google it. It's a, it's a thing. Like, people have done prompting for decades. It's just called executive communication. It's like when one person has to communicate to thousands of people down the org chart, this is what you do. so situation, complication, question and answer, is how you write the memo. but obviously sometimes you don't have the answer, but you can at least list out the SC and Q, and then they have some examples in there. So just leaving breadcrumbs for people if they want to explore.Underrated Prompting Patterns and ELI5Vibhu [00:30:31]: Before we move on, I wanna ask you, any other underrated tips, ways people could get a lot of value from Claude Code that they're not using?Thariq Shihipar [00:30:41]: Yeah, I think a lot of them are in the, this unknowns, like, doc. Like, I give a bunch of example prompts, like, using it for brainstorming, using it to quiz you after. we added this, like, explain it like I'm five skill which is a very short prompt. And it doesn't even say explain it like I'm five. It's like the key word of this prompt is big pictures, few words. like, that's like the main thing. And it is shockingly good? Like, you, like, I think I tweeted about this and it's like /eli5, and, like, you can install it as a plug-in. But yeah, it's, like, way better at just cutting through the BS and being like, yeah, exactly right here. So the diagrams are, like, quite clear. I think one of the things that is true with artifacts is, like, they put too much text in and people are not reading the artifacts? And so, like, this simplifies it a lot more. And, yeah, this came out of, like, just people at Anthropic, like, going through very complicated incidents and being like, “What is happening?”? So, this one I think is great, yeah.Swyx [00:31:47]: My version of this is the, it's like test your understanding. Give you a few choices and then, like, if you get it wrong, you have a mismatch between what you think is happening versus what's happening.Thariq Shihipar [00:31:58]: Yeah. I think this is one of those things that everyone loves talking about, and then very few people really do. Like, I thinkSwyx [00:32:05]: Really helpful.Thariq Shihipar [00:32:07]: Yeah. But most people just don't want to get quizzed about something? Unfortunately, I think this is one of the, like, things that we need to, like.Swyx [00:32:16]: What's the opposite of ask you the question or ask you the question before the thing?Thariq Shihipar [00:32:19]: Yeah.Swyx [00:32:19]: This is after the thing.Thariq Shihipar [00:32:20]: Exactly. Yeah.Vibhu [00:32:21]: It's a good way to stay grounded of, like, do you even know what you're doing, right? The worst case is when people send you slop and they haven't understood what they're asking for or what the output is, and it's like, “Dude, I don't wanna read this. Do you even know what it is?” So, you make it a rule for yourself that before you send stuff, you should at least know what's implemented.Claude Mods: Customizing the HarnessThariq Shihipar [00:32:41]: Yes, but so you could make this a mod and you could build your own mod to, like, make sure you test it. So yeah, you can do that.Swyx [00:32:49]: All right. Let's get right into it. What is Claude Mod, and what is this diagram showing?Thariq Shihipar [00:32:54]: Yeah. Okay, so Claude Mods is you can customize the entire Claude Code harness, and we're going to. If you have requests, we will, like, let you, like, please let us know. We'll add more and more. This works for CLI, it works for desktop. maybe it will work for Claude Tag in the future. I don't know. Like, we're trying to make this very extensible. You can see this reference sheet. I don't want people to get overwhelmed by it? At a high level, you can customize both the execution of the harness, and the UI of the harness. And so, like, you say on that Tetris example from Boris, that's like customizing the UI, right? Like showing, like, Tetris in the game.Thariq Shihipar [00:33:35]: But, like, let's say that you wanted to do this thing where you had. you tested your assumptions or, like, tested your understanding after every project, right? What you would do is you would ask Claude to make this plug-in. It would spin a classifier after every prompt. And so, like, at the end of each turn, you would spin off a sub-agent or, like, a forked agent. A forked agent is, like, maintains the prompt cache, right? So it's like a, like one of those unintuitive things where you can fork and do, like, a little request, and it'll be very cheap because the entire prompt cache is, like, done. And so you can be like, “Has this task been completed?” likeSwyx [00:34:18]: This is how you do BTW and all those.Thariq Shihipar [00:34:20]: Yeah. The underlying forked agent, yes. But so you can, in the f-fork sub-agent, you can say, like, “Has this task been completed? If so, return true.” And then in your hook, or in your, like, plug-in mod, or sorry, like, in the sub-agent probably, you would say, like, “If true, give me a quiz.” give me questions and answers, and then, like, in a JSON format, and then you'd parse it, and then you display above the prompt input, this list of questions, right? And so this is something that's, like, slightly token-intensive because, like, you have to do it after every end of the assistant turn. But it's, like, a lightweight classification, and then you can, like, get this quiz, and then you'll see, like, Claude will always do it for you. You don't need to remember to do it. There are lots of these, like, tips that we've talked about, right, where it's like, oh, implementation notes. You can also add a tool for implementation notes now. And so, like, this tool that I'm adding is, like, register, like, I think assumption is what I'm calling it, but, like, maybe I'll change it around. And this is a mod. And so, like, you give it a register assumption tool, and then it will keep a list. It'll. Every time it does it'll keep a, like, add to the list, and then at the end it will display those assumptions? Another mod I'm working on is a model router. And so, like, internal, like, Claude model routing, right? So it's. This is, I want to say the reason we don't do model routing by default is, like, it's a hard problem? And likeForked Agents, Assumption Tracking, and Model RoutingSwyx [00:35:51]: You will get it wrong.Thariq Shihipar [00:35:52]: Yeah, you, like, yeah, you will, like, accidentally use, like, Fable for a hard problem or Sonnet forSwyx [00:35:57]: Yeah, if you have auto approve, but you don't have auto mode.Thariq Shihipar [00:36:01]: Well, you will have auto. Like, you don't have, like, auto routing or something.Vibhu [00:36:04]: You don't have auto mode for model picker.Thariq Shihipar [00:36:06]: Yeah, exactly. SoVibhu [00:36:07]: I'm getting the rough question of, like, how much do you open this up and how much do people have to think about this? Like, when you talk about prompt caching and building a router, it seems like you could easily build a mod that routes per query, and I'm just killing my plan very fast, right? I guess my question is more so, like, what is, like, a product talk like this look like, right? Who is it for? Is it for power users? Is it everyone should be able to go throughSwyx [00:36:33]: Oh, definitely power users, right?Thariq Shihipar [00:36:35]: Yeah, I think it is power users, but, like, the nature of Claude Code is that so many people are power users? Because it's easy to share things, like you can. Like, one person can make a good model router thing that doesn't break prompt cache all the time, and then you can, like, compose them. Another cool thing about the plug-ins is that they can hook into and compose with each other. And so I have, like, a mod that will, like, create a mode selector at the top, and any plug-ins can register to be a mode. And so, like, the auto router can be a mode, right? Or, like, you can have a mode that's, like, artifact mode, where it's like it primarily talks to you in artifacts. like, you can toggle between plan mode? And so, like, you can create more and more of these modes. But the ability to create modes is in it itself a mod? And so there's a lot of richness here, but we do want to make it fairly easy. We want to be-- make it so that you can just, like, install someone else's. You can ta-- you can chat with Claude and, we'll, like, make sure that it understands the nuances of things like prompt caching and stuff, so it can, like, warn you. This is, like, not extremely complicated behavior for Claude, I think, but we should have just a good skill on how to make mods. and yeah, we'll see how we go. But I do think that this is, like, a preview of, like, mutable software, and, like, how, like, generative software, just like you can customize safely. If enabled, you could customize any piece of software. And I think that more and more apps ideally do something like this?Power Users, Modes, and Mutable SoftwareSwyx [00:38:13]: And by the way, you, we have, you have another cool tweet about how, there's the infinite money button, which is like make your SaaS, consumable by agents. I think mutable software is interesting and, other people have also tried to do it. I think the hurdle comes when you can do everything, then people, users get, tend to get confused. So usually the stuff that works is just like one opinionated flow. This is in the side of less opinionation. It's just like, well, more power to power users. And I think probably unlocked by AI, where, like, you can just prompt for whatever the thing is.Thariq Shihipar [00:38:47]: Yeah, or there can be a skill that gives the opinions?Mods vs. Hooks vs. ArtifactsSwyx [00:38:50]: Yeah.Thariq Shihipar [00:38:50]: And then, yeah.Swyx [00:38:51]: So knowing a little bit about, like, TypeScript and build systems and all these things, the closest-- I'm very curious that the team who worked on this, if, I don't know how close you were to them, if they drew any inspiration from build systems like Babel, Webpack, all these, like, old school things. Because it sounds very similar, like the plug-in ecosystem of those things where they can compose with each other.Thariq Shihipar [00:39:11]: Yeah, I'm not deep in the technical details, but I do know it was a collaboration with someone on the Bun team and someone on the Claude Code team.Swyx [00:39:17]: Yeah, it's a build system mecca.Thariq Shihipar [00:39:19]: Yeah. Exactly. It's, it's very exciting. But yeah, like, agents can just do this very complicated like, extensibility into your software now. And so, yeah, like, another reason to, like. If you run a startup, like, you can just prompt Claude and be like, “Hey, like, could we make an extension system? Like, what would that look like?”?Swyx [00:39:37]: Yeah.Swyx [00:39:38]: And I just really wonder, like, you had hooks in the past and plug-ins, all these things. So what specifically will mods be able to do that those things could not do?Thariq Shihipar [00:39:47]: Internally, we were originally calling this function hooks. And so, like, that's, like, gives you a little bit of an idea where, like, hooks register a, like an event to happen and then, like, a script to call. And this inside of the, like, TypeScript runtime is running things. And so, like, you get some benefits of just, like, it has a bunch of things in the Scope with, like, for example, like how many turns is in this conversation, right? Like, how many tokens have been used? Like, et cetera. Like, what are the messages? Things like that. So it has a bunch of messages that can be used. And then it's just, like, a lot more hooks. So we have, like, or a lot of, lot more, like, things you can register on. And then you can do because of the. because it's all happening in process, you can, spawn sub-agents, with four contests and contexts and stuff. And, like, that will return. You can parse the results of those. You can use structured output to like, return them. and then you can modify the UI, which you can never do in hooks. So, yeah.Swyx [00:40:50]: Yeah. Yeah. So modify UI, this is why you showed the Tetris example. Does it also ex-extend to artifacts? I assume it does.Thariq Shihipar [00:40:57]: You-- Like, artifacts are like a different way of customizing it. like, you can definitely. One of the mods I'm working on is, like, this dashboard mod, which will, like, prompt Claude to maintain a dashboard, that's an artifact. But they're like, slightly orthogonal, or not orthogonal. They compose with each other in different ways. Like, mods are, like, a little bit more, like, in your Claude Code harness, changing the agent loop? And, like, the UI is, like, an added benefit. and then artifacts are just like you want to, see things at a high level, very inter- highly interactive. like, the affordances can be a lot bigger than, like a TUI or even in our desktop.Next Steps, Supervisors, and Persistent GuidanceVibhu [00:41:40]: I'm guessing you'll have a good blog post on the differences, because right now you can also, make a loop that outputs to an artifact that's an interactive dashboard, but you can also do it with a mod. There's just some thinking about making a hacking on a harness when we don't know much about the harness, right?Thariq Shihipar [00:42:00]: Well, something I'm excited about with mods is, like, there's so much things with Claude Code that you just have to remember? You're like, “Oh, like, let me do this, and then let me call the dashboard skill that does the loop,” and things like that. And, or like, “Let me test my assumptions afterwards.” And I think, like, if you do all of these things using these little classifiers and stuff, and you're like, “These are the things I care about. This is what I want to do,” you can, like. You don't have to remember as much. One more, like, mod I'm working on is a next steps mod thatSwyx [00:42:28]: I have-- I was gonna say, I have a next step skill. I always run next steps.Thariq Shihipar [00:42:32]: And does it have access to your skills? Like, this is one of those things where I'm like.Swyx [00:42:37]: I think so.Thariq Shihipar [00:42:38]: Okay. Yeah, probablyVibhu [00:42:39]: Do skills need specific access toThariq Shihipar [00:42:41]: Well, I think there'sSwyx [00:42:41]: Don't they always haveThariq Shihipar [00:42:42]: I think there's, like, specific prompting, I guess, to, like, know your skills. Like I think Claude forgets them sometimes throughout, like, the thing. But anyways, the idea of, like, yeah, next steps that also are like, “Oh, hey, this has happened. Use the explain skill to explain to you what happened because this seems, like, quite complex,”? Or, like, yeah, “Use your unknown skill. It looks like you are, like, asking the model to, like, iterate on these small changes. It seems like you could prompt better.” like, “What if you did this?” Right? So, I think, yeah, like spending more compute there. Yeah.Swyx [00:43:20]: And it should always come out as multiple choice. we have, I haveVibhu [00:43:23]: We have his skill.Swyx [00:43:24]: My next step skill is like this.Thariq Shihipar [00:43:26]: Okay, perfect. Yeah.Swyx [00:43:27]: You can steal it.Thariq Shihipar [00:43:28]: Yeah.Swyx [00:43:29]: Like, but like, for me, it's all-- I think models really always need to be reminded, what are you trying to do here?Thariq Shihipar [00:43:35]: Yeah.Swyx [00:43:35]: Look at the whole transcript and go like, oh, was this original goal? Did your solution solve it? Were you lazy? If you're lazy, maybe there's a reason. Maybe you needed approval from me. Maybe you needed, there's two things you wanna suggest. So it's, it's a little bit like the modification of the ask user question or interview me skill. so it's next steps.Thariq Shihipar [00:43:55]: Yeah, exactly. And again, the benefit of doing it with mods is you can do it as a fork sub-agent, and so it doesn't remain in the context afterwards. So you have this, like, idea of like, okay, the model is doing its execution and you have this almost like supervisor, like, that is like making sure that you can do like the next steps well. So yeah.Swyx [00:44:15]: Yes. I do have two panels and like I often try to have a supervisor thing, keep the high-level context and then the implementationThariq Shihipar [00:44:21]: YeahSwyx [00:44:22]: Detail in another agent.Vibhu [00:44:23]: I feel like a lot of this abstracts away as models change? The, like, half an hour ago you said bitter lesson of harness engineeringThe Bitter Lesson of Harness EngineeringThariq Shihipar [00:44:31]: YeahVibhu [00:44:31]: And we're on the other extreme right now, I feel.Swyx [00:44:33]: Well, so yeah, exactly. If everything's customizable, what is Claude Code, right?Thariq Shihipar [00:44:37]: Yeah.Swyx [00:44:37]: And which I talked to you about last night.Thariq Shihipar [00:44:40]: Yeah, I think that this is. I think the bitter lesson is unintuitive? In terms of like. Also, like we're misusing a little bit of the bitter lesson here where it's like, it's more about like scaling and compute and stuff. But like, I think there is something where it's just like. I think I use it as an approximation here to say that harnesses go out of date very quickly? And like how, but how they change is unintuitive? And so like the big obvious example is like from chat to like agents where you had to give them entirely new tools, right? But like, I think this new version of like, oh, it can modify its own harness, right? This is like, an own harness loop is like a way of using its capabilities, right? Or like it can build an artifact. And like, I think the way I think about it is like the models have more and more intelligence, and they're like so much more intelligent now than like the average software engineering task. Like, you look at the like terminal bench ones and they're like solve like the Jacobian conjecture. Not really, but like, it's like they're, they're quite complex. Like, I would not have been able to do this really as a software engineer.Swyx [00:45:42]: And you said TB4 or TB2?Thariq Shihipar [00:45:43]: TB3. TB3.Swyx [00:45:44]: TB3.Thariq Shihipar [00:45:44]: Yeah. They're quite complex, but the goal is still to deliver user value, right? And like you said, there's like this infinite space of things to do. And so the ways like you spend compute are to keep the user in the loop and make sure that like you're getting to the right decision in the end of the day and like the right output. And artifacts and mods are this way of like spending that intelligence. and I think that's like, yeah, the next step. And so, yeah, I think Claude Code is like, has the core things of agent loop which are, have gotten more complicated. It's like, it needs a sandbox to operate safely. It needs auto mode to like make sure like the permissionsVibhu [00:46:21]: Approvals.Thariq Shihipar [00:46:21]: Yeah, approvals. it needs computer use and MCPs and like all of these like ways of accessing your data, and it needs web search and web fetch. And like, so the-- as the models can do more and more, the core harness has to be like quite complex and very secure. But then like how you interact with it can change quite a lot.Vibhu [00:46:42]: What other harness engineering best practices have you, from the Claude Code team itself? I feel like, there was a phase of plan mode, which is not as used. We now have auto mode. at a point you cut the majority of the system prompt, you got rid of examples. What other best practices are there for harness engineering?Core Harness Primitives and Managed AgentsThariq Shihipar [00:47:02]: I think there is like a forking path where at some point, eventually, yes, the model will just be able to like vibe code the exact version of Claude Code, even describing all this complexity that I've talked about, right? Like auto mode and computer use and stuff. Eventually, the models will just be able to do that in one shot. But I think they can one shot simpler harnesses? And so like, I think some people. Sometimes you don't need this full, like if you don't need computer use or like all this like more complicated stuff. I think before we, you had to use things like the agent SDK, which was like Claude Code wrapped, in order to like. And I would, like suggest people do that because there was so much complexity into building a harness. And now as that's got more abstracted, we have like, Claude managed agents, which lets you have that complexity, but still like, right, like a very bare bones like harness that's scoped to your task. Yeah, I think there's like this barbell effect where like for like very complex, for like coding task and like these like complex things, you should use our harness. And then for like a lot of like simpler or like, more domain-specific things, you can build your own harness because Claude has gotten better at building harnesses, and we have these harness primitives like managed agents. So yeah.Swyx [00:48:18]: Yeah. Is there a general progression? Let's say chapter one was ultra code dynamic workflows, then chapter two was cloud mods. Where is this going?Swyx [00:48:29]: Where you're, you're, you can customize the thing on demand.Thariq Shihipar [00:48:36]: Yeah. I do think that like this evolution of projects and like artifacts and splitting out like brain and hands and, surfaces is like where things are going more. And like, I think it's like not all quite there. partially it's like a, it's just like more token expensive? And like, I think likeProjects, Local Hands, and Cloud-to-Local HandoffsSwyx [00:48:59]: Why would projects be more token expensive? I understand mods would be slightly more token expensive. No, not something I'm worried about.Thariq Shihipar [00:49:06]: Yeah.Swyx [00:49:06]: But whatThariq Shihipar [00:49:07]: You're asking Claude to do. It's like creating loops. Like you're asking Claude to do more work for you. And so like it's managing the sub-agents and reviewing it, versus where you would be doing that work normally. And so that's like gonna be a little bit more intensive, like. Outputting to an artifact is gonna be a little bit more token-intensive than, like, outputting normally. I don't think it's too much more, but like, it's like combining all of these together well, like I think we're, we're still working on like local hands and things like that, I think is like, yeah, where things are headed, yeah.Swyx [00:49:37]: Yeah. Claude and local is, handoff is very interesting. I was thinking about this as reverse cloud remote.Thariq Shihipar [00:49:44]: Yeah.Swyx [00:49:45]: Because it's like remote, it's you're handing off to cloud, but here the cloud is handing off to local, right?Thariq Shihipar [00:49:49]: Yeah, exactly. Yeah, remote control is also another way of doing it. And I do want to say this is like how I think about it and like what the things that I'm most excited about this, but like there are, just like lots of different ways to work with Claude. Like some people use remote control a lot, some people use Claude Code on the web a lot. Obviously, like at Anthropic, we use Claude Tag a lot, and like what's great about Claude Tag is we set up all this stuff for our own execution. And I do think if you're an enterprise, that's still the best way to go. but if you're like an individual, Projects is this way of like, getting some of that like niceness of Tag, which has like that like supervising agent and yeah, adding artifacts and stuff, but like without having that whole like admin setup. And so there will be many ways to use Claude, I think. I think it's probably not just one like single.Claude Tag as an Organizational HarnessSwyx [00:50:36]: You had the multiplayer thing here. Let's, let's just check in on Claude Tag. it's been about two-plus months. Lots of, public, adoption and trying it out.Thariq Shihipar [00:50:45]: Yeah.Swyx [00:50:45]: What's new? What's, what have you found since the launch?Thariq Shihipar [00:50:49]: Like, Claude Tag is how we useSwyx [00:50:51]: It's like 80% of your

Dr Adam Kirton: From thought to function with non-invasive brain computer interface.What are the possibilities of turning a thought into something that is actionable? For children with CP that have significant motor impairments, access to the environment can be incredibly challenging. Dr Kirton came onto the pod to talk about his education session and free paper titled "Achievement of Personalized, Previously Impossible Goals by Children with Severe Quadriplegic Cerebral Palsy Using Brain-Computer Interface."Join us as we explore this novel intervention, understand how it works and what the possibilities are right now.

Donald Goldfarb is the Avanessians Professor in the IEOR Department at Columbia University. He is internationally recognized for the development and analysis of efficient and practical algorithms for solving various classes of optimization problems, including the BFGS quasi-Newton method for unconstrained optimization, steepest-edge simplex algorithms for linear programming, and the Goldfarb-Idnani algorithm for convex quadratic programming. Don has also developed highly cited methods for image de-noising, compressed sensing, matrix rank minimization, and robust portfolio selection. In addition, he has developed simplex and combinatorial algorithms for network flow problems, interior-point methods for linear, quadratic and conic programming, and alternating linearization methods for sums of convex functions. He is a Member of the National Academy of Engineering, a recipient of the INFORMS John Von Neumann Theory Prize for Fundamental, Sustained Contributions to Theory in Operations Research and the Management Sciences, the Khachiyan Prize for Life-time Accomplishments in Optimization, and 1995 Prize for Research Excellence in the Interface between Operations Research and Computer Science. He is a SIAM Fellow, and was cited in 2014 by Thomson Reuters as one of World's Most Influential Scientific Minds (specifically, among the top 1% most cited researchers in Mathematics between 2002 and 2012). Don has served as an editor-in-chief of Mathematical Programming, an editor of the SIAM Journal on Numerical Analysis and the SIAM Journal on Optimization, an associate editor of Mathematics of Computation, Operations Research and Mathematical Programming Computation, and is an editorial board member of Foundation and Trends in Optimization.

Salesforce's next growth opportunity may come from customers spending less time in its interface—and having agents do more of the work.Coming out of Dreamforce 2026, we believe that is the shift worth exploring. The progression from command lines to graphical interfaces, browsers and mobile is entering another phase: an agent can generate an interface around the task, inside Claude, Slack or another client. The customer no longer has to start with the application's screen. The starting point becomes a customer outcome.But generating an interface is not the same as understanding the business. That is where our System of Intelligence (SoI) framework comes in. The system of engagement (SoE) connects people and agents. The system of intelligence supplies the business context. And the system of agency (SoA) turns that understanding into action. Salesforce's larger ambition is to connect these elements through what it calls an enterprise AI harness: the data, business knowledge, workflows and controls that let models do useful work across systems. This goes well beyond answering questions.The customer evidence from our good friends at Qualitate, suggests an exciting opportunity…but the data also shows a company in transition. Qualitate's latest channel checks find that most organizations interviewed remain in Agentforce pilots or proofs of concept. Yet among customers who have modeled or experienced the financial impact of headless access, 75% expect Salesforce spending to increase—not decline. Working outside Salesforce's interface could actually mean doing more work on its platform.That creates both an opportunity and a challenge. More consumption can generate more revenue, but it does not automatically generate more customer value. Pricing must make sense as pilots scale. And if customers increasingly work through their preferred AI environment, Salesforce must demonstrate why its business context and execution capabilities remain an essential underpinning of the customer experience. The point is, the interface can move elsewhere, meaning the next purchase may not automatically stay within Salesforce.Welcome to Breaking Analysis #327. Salesforce After Dreamforce…How $CRM (the company) can grow beyond it's own interface. In this episode, George Gilbert joins us to map Salesforce's post-Dreamforce direction into our System of Intelligence framework. We combine his firsthand observations with new Qualitate customer research to examine headless access, Agentforce maturity, competition from AI-native agents, and the changing relationship between pricing and business outcomes.

2096. La Souf va élire son premier président. Officiellement, une avancée démocratique historique. Officieusement... personne n'est vraiment sûr de rien. Chaque mois jusqu'aux élections, Kall Reco initie un dialogue avec l'ennemi : ADA, l'intelligence artificielle centrale des Démocraties Progressistes. Pas un débat truqué — un vrai face-à-face entre deux visions du monde qui s'affrontent depuis 31 ans. Dans ce premier numéro : des rumeurs d'ingérence électorale, un candidat favori soupçonné d'être sous influence, et un Conseil des Treize qui n'est peut-être pas aussi vertueux qu'il en a l'air. Les résonances avec notre propre actualité ne sont sans doute pas complètement fortuites.

Thema: Next-Gen Videoproduktion „Ich muss nicht schneller produzieren, sondern ich muss die Architektur, wie ich Entscheidungen treffe, anders bauen.“ In der neuen Episode von „WhatsNextAgencies“ spricht Kim Notz mit Philipp Haeberlin-Collet, Executive Producer und Co-Founder von fount.space und Scretch, darüber, wie sich Produktion neu denken lässt, und warum es dabei längst nicht mehr nur darum geht, Projekte schneller oder günstiger umzusetzen. Mit fount.space wollten Philipp und sein Co-Founder ursprünglich eine Plattform schaffen, die neues Produktionstalent mit Agenturen und Unternehmen zusammenbringt. Aus dem Talent-Matching entwickelte sich jedoch ein anderes Modell: Heute verbindet fount.space Produktionskompetenz mit Organisationsentwicklung und hilft Teams dabei, Strukturen zu schaffen, in denen Entscheidungen schneller getroffen und neue Talente sinnvoll integriert werden können. Denn für Philipp liegt einer der größten Hebel moderner Produktion nicht in der Ausführung selbst, sondern in der Art, wie Agenturen, Kunden, Produktion und Talente miteinander arbeiten. Im Gespräch geht es deshalb auch darum, was Agenturen von diesem Ansatz lernen können. Philipp plädiert dafür, Producing deutlich früher in kreative und strategische Prozesse einzubinden und die Rolle aus der reinen Umsetzung zu lösen. Gerade in einer Produktionswelt, in der Plattformen, Formate und KI die Anforderungen permanent verändern, werden Menschen wichtiger, die neue Talente erkennen, unterschiedliche Skills zusammenbringen und Verantwortung für die Machbarkeit übernehmen. Produktion wird damit vom letzten Glied im Prozess zunehmend zum strategischen Interface nach außen. Zum Schluss richtet sich der Blick auf Scretch, das Philipp gemeinsam mit Channel 2 gegründet hat. Hier trifft Produktionskompetenz auf tiefes YouTube-Know-how mit dem Ziel, Kanalwachstum nicht über einzelne Kampagnen oder möglichst viel Content zu erzeugen, sondern langfristig und planbar aufzubauen. Auch dahinter steckt die gleiche Idee: Produktion nicht vom Output aus zu denken, sondern vom Ziel und Prozesse, Talente und Inhalte konsequent danach auszurichten.

Was sind neueste Erkenntnisse aus der Wissenschaft um 'Grundlagen digitaler Spiele'?Im August 2026 fand zum 21. die Konferenz FDG ("The Foundations of Digital Games") statt. Unter dem diesjährigen Motto "Research through Games; Research for Games" wurde in Kopenhagen mit zahlreichen Forschungsbeiträgen und Workshops eine Brücke zwischen akademischer Grundlagenforschung und den realen, kommerziellen Anforderungen der Spieleindustrie geschlagen.Philip & Ben haben ausgewählte Paper der Konferenz mitgebracht, die kurz vorgestellt und diskutiert werden. Folgende Themen sind im Gepäck:>> Block 1: Soziale DynamikenFörderung von prosozialem Verhalten in Online-Multiplayer-SpielenSoziale BelohnungssystemeDesignpotenziale zur Abschwächung von toxischem Verhalten [League of Legends]Interaktionssysteme in Koop-Games & deren Effekte [It Takes Two; Overcooked! 2]Oft vernachlässigte Mechanismen in Lernspielen>> Block 2: Der Raum als InterfaceAugmented Reality und spielerische Vermittlung von KulturerbeDiegetische Karten im SpielOrientierung im digitalen Raum anhand diegetischer & nicht-diegetische MarkierungenDiegetische Wegführung & Entdeckung>> Block 3: Psychologische Bedürfnisse & User ExperienceGamification per KI- & soziale Unterstützung beim KochenGrundlegende Machtaspekte im Charaktereditor [Baldur's Gate 3]Dialogsysteme, LLMs & Player Experience [Quest of Aivengarde]Vergängliche Waffen [The Legend of Zelda: Breath of the Wild]=== Links ===[werden noch nachgereicht; meldet Euch, wenn Ihr etwas Bestimmtes vermisst]=======================

In this episode, Chandra and Paul are joined by guests Lane Lassetter of Interface, Inc. and Rajan Kaistha of RST Solutions to discuss how Interface has leveraged JD Edwards and automation tools to modernize and streamline their business processes. Lane details the challenges faced with manual AP processes and how the adoption of AP automation has significantly improved efficiency and reduced manual effort. The conversation highlights the ongoing efforts to migrate archival systems, automate additional functions such as vendor onboarding and PO approvals, and address customization debt through thoughtful upgrades.03:56 Introducing Lane and Rajan06:50 AP Automation, PO Approvals, and Document Archival in Laserfische12:33 Debt reduction with AP automation15:52 Selling the business on upgrades18:12 Challenges of Software Upgrades with Customizations21:27 Software Upgrades and Adoption26:52 Importance of Awareness34:48 Midwesternism of the Day

Dr. Martine Wilkie is a Psycho-Neuro-Spiritual Transformation Expert, CEO of Wilkie Coaching, and creator of the Limitless Interface System™. She works in partnership with her husband, Allen Wilkie, whose work in affirmations, declaration-based music, and guided visualizations supports deep neuro-spiritual integration and embodiment.✨Download my free pdf✨5 Reasons you are not making money https://www.wilkiecoachingconsulting.com/5reasons?utm_source=youtube&utm_medium=video&utm_campaign=video_default7 reasons you'll lose money to AI in 2026 unless you master this now:https://www.wilkiecoachingconsulting.com/7reasonsyouwilllosemoneyThe Wealth Interface System for your successhttps://www.wilkiecoachingconsulting.com/PDFWEALTHINTERFACESYSTEM?utm_source=youtube&utm_medium=video&utm_campaign=video_defaultActivate Heaven in your finances https://www.wilkiecoachingconsulting.com/PDFactivateheavenfinances?utm_source=youtube&utm_medium=video&utm_campaign=video_default

KI-Qualität im Tiefgang: Praktikant vs. Experte – der echte Test   Woran erkennst du, ob ein KI-Tool wirklich taugt? Nicht an Einzelfragen – sondern daran, wie es sich schlägt, wenn ein echter Arbeitskontext entsteht. TJ schildert zwei gescheiterte Setups mit Perplexity und wie Claude dasselbe Problem in fünf Minuten gelöst hat. Warum der Unterschied zwischen KI-Modellen erst im Tiefgang sichtbar wird – und was du daraus für deinen Workflow mitnehmen kannst.   Die Oberfläche lügt – warum KI-Qualität sich versteckt Viele KI-Tools wirken auf den ersten Blick ähnlich leistungsfähig. Einzelne Fragen beantworten sie sauber, die Antworten klingen kompetent, das Interface ist flüssig. Der echte Unterschied zeigt sich erst, wenn du tiefer gehst: wenn aus einer Frage ein Dialog wird, wenn Zwischenergebnisse zurückgeliefert, bewertet und weiterverarbeitet werden müssen. Genau das ist der Moment, in dem manche Tools schlicht aufhören zu funktionieren – und du es ohne direkten Vergleich oft gar nicht merkst. TJ beschreibt diesen Punkt treffend: „Qualitätsunterschiede, die kannst du an der Oberfläche nicht erkennen."   Slack-Einführung abgebrochen: wenn das Kontextfenster nicht reicht TJ wollte die Slack-Einführung in seinem Unternehmen mit Perplexity aufsetzen – und musste mittendrin abbrechen. Das Modell halluzinierte, lieferte mit „geschwellter Brust" Anweisungen, die inhaltlich weit vom Ziel entfernt waren. Der Grund: Das Kontextfenster reichte schlicht nicht aus. Je länger das Gespräch wurde, desto mehr verlor Perplexity den Faden. Was zu Beginn funktionierte, kippte in dem Moment, in dem der Arbeitskontext komplexer wurde. Ein klassisches Beispiel dafür, dass Einzelfragen kein verlässlicher Maßstab für die Leistungsfähigkeit eines Modells sind.   VPS-Installation: Trial and Error statt strukturierter Lösung Der zweite Test war technisch anspruchsvoller: TJ versuchte, Mirofish auf einem VPS mit angebundenem Ollama zu installieren – eine mehrstufige Aufgabe mit Abhängigkeiten, Rückmeldeschleifen und echten Systemzugängen. Perplexity lieferte Trial and Error. Probier das, schau mal, probier das nochmal. Kein strukturiertes Vorgehen, kein klarer Plan. Das kostete Zeit – und Nerven. Der Wechsel kam nicht aus Ungeduld, sondern aus Vernunft: Wenn ein Tool nach mehreren Schleifen nicht weiterkommt, ist der sauberste Zug, den Kontext geordnet zu übergeben und neu anzusetzen.   Fünf Minuten mit Claude: strukturiert, ergebnisorientiert, gelöst TJ übergab Claude den Kontext mit einem klaren Briefing: „Ich bin hier mit Perplexity dran, der kriegt's nicht auf die Reihe – guck mal drauf, verschaff dir ein Bild, dann lösen wir das." Claude bekam die nötigen Zugänge, analysierte die Situation und arbeitete sich in klar definierten Schritten vor: „Mach das, liefer mir das Ergebnis zurück. Mach das, liefer das Ergebnis zurück." Dieser Rhythmus aus Anweisung, Rückmeldung und nächstem Schritt ist der entscheidende Unterschied. Nach fünf Minuten war das gesamte Thema gelöst. Der Vergleich, den TJ zieht, trifft es gut: Perplexity war der Praktikant, Claude der Experte, den man dazuholt, wenn es drauf ankommt.   Fazit: Teste KI-Tools dort, wo es wirklich schwierig wird Der wichtigste Punkt dieser Episode ist kein Produktvergleich – es ist eine Methode. Teste KI nicht mit Einstiegsfragen, sondern mit echtem Arbeitskontext. Geh tief, lass das Tool in Schleifen arbeiten, fordere Zwischenergebnisse zurück. Erst dort wird sichtbar, ob ein Modell wirklich strukturiert denkt oder nur gut klingt. Und wenn ein Tool nicht weiterkommt: kein stundenloses Trial and Error, sondern Kontext sauber zusammenfassen und ein anderes Modell neu ansetzen lassen. Das ist keine Schwäche – das ist effizienter Umgang mit den Werkzeugen, die dir zur Verfügung stehen.   Das nimmst du mit: • Perplexity verliert bei längeren, mehrstufigen Aufgaben den Kontext und halluziniert – selbst mit Max-Account und Opus 4. • KI-Qualität ist an der Oberfläche kaum erkennbar: Der echte Unterschied zeigt sich erst, wenn du wirklich tief in ein Problem gehst. • Wenn ein Tool nicht weiterkommt, lohnt es sich, den Kontext sauber zu übergeben und mit einem anderen Modell neu anzusetzen – statt stundenlang Trial and Error zu betreiben. • Die Fähigkeit, strukturiert Teilaufgaben abzuarbeiten und Ergebnisse zurückzufordern, trennt brauchbare KI-Assistenten von teuren Zeitfressern. • Teste KI-Tools nicht mit Einstiegsfragen, sondern mit echtem Arbeitskontext – erst dort wird sichtbar, ob ein Modell wirklich taugt. Kapitel: 00:00 Hook: Praktikant vs. Top-Experte 00:12 Perplexity verliert den Kontext bei der Slack-Einführung 00:28 VPS-Installation: Trial and Error mit Perplexity 00:48 Wechsel zu Claude: strukturiertes Vorgehen, Problem gelöst 01:30 Fazit: Qualitätsunterschiede zeigen sich erst im Tiefgang     Noch mehr von den Koertings ... Das KI-Café ... jede Woche Mittwoch (>350 Teilnehmer) von 8:30 bis 10:00 Uhr ... online via Zoom .. kostenlos und nicht umsonst Jede Woche Mittwoch um 8:30 Uhr öffnet das KI-Café seine Online-Pforten ... wir lösen KI-Anwendungsfälle live auf der Bühne ... moderieren Expertenpanel zu speziellen Themen (bspw. KI im Recruiting ... KI in der Qualitätssicherung ... KI im Projektmanagement ... und vieles mehr) ... ordnen die neuen Entwicklungen in der KI-Welt ein und geben einen Ausblick ... und laden Experten ein für spezielle Themen ... und gehen auch mal in die Tiefe und durchdringen bestimmte Bereiche ganz konkret ... alles für dein Weiterkommen. Melde dich kostenfrei an ... www.koerting-institute.com/ki-cafe/ Mit jedem Prompt ein WOW! ... für Selbstständige und Unternehmer Ein klarer Leitfaden für Unternehmer, Selbstständige und Entscheider, die Künstliche Intelligenz nicht nur verstehen, sondern wirksam einsetzen wollen. Dieses Buch zeigt dir, wie du relevante KI-Anwendungsfälle erkennst und die KI als echten Sparringspartner nutzt, um diese Realität werden zu lassen. Praxisnah, mit echten Beispielen und vollständig umsetzungsorientiert. Das Buch ist ein Geschenk, nur Versandkosten von 9,95 € fallen an. Perfekt für Anfänger und Fortgeschrittene, die mit KI ihr Potenzial ausschöpfen möchten. Das Buch in deinen Briefkasten ... https://koerting-institute.com/shop/buch-mit-jedem-prompt-ein-wow/ Die KI-Lounge ... unsere Community für den Einstieg in die KI (>2800 Mitglieder) Die KI-Lounge ist eine Community für alle, die mehr über generative KI erfahren und anwenden möchten. Mitglieder erhalten exklusive monatliche KI-Updates, Experten-Interviews, Vorträge des KI-Speaker-Slams, KI-Café-Aufzeichnungen und einen 3-stündigen ChatGPT-Kurs. Tausche dich mit über 4.000 KI-Enthusiasten aus, stelle Fragen und starte durch. Initiiert von Torsten & Birgit Koerting, bietet die KI-Lounge Orientierung und Inspiration für den Einstieg in die KI-Revolution. Hier findet der Austausch statt ... www.koerting-institute.com/ki-lounge/ Starte mit uns in die 1:1 Zusammenarbeit Wenn du direkt mit uns arbeiten und KI in deinem Business integrieren möchtest, buche dir einen Termin für ein persönliches Gespräch. Gemeinsam finden wir Antworten auf deine Fragen und finden heraus, wie wir dich unterstützen können. Klicke hier, um einen Termin zu buchen und deine Fragen zu klären. Buche dir jetzt deinen Termin mit uns ... www.koerting-institute.com/termin/ Weitere Impulse im Netflix Stil ... Wenn du auf der Suche nach weiteren spannenden Impulsen für deine Selbstständigkeit bist, dann gehe jetzt auf unsere Impulseseite und lass die zahlreichen spannenden Impulse auf dich wirken. Inspiration pur ... www.koerting-institute.com/impulse/ Die Koertings auf die Ohren ... Wenn dir diese Podcastfolge gefallen hat, dann höre dir jetzt noch weitere informative und spannende Folgen an ... über 500 Folgen findest du hier ... www.koerting-institute.com/podcast/ Wir freuen uns darauf, dich auf deinem Weg zu begleiten!

In this episode, Freddy gives us an overview of what RAVN Exchange is and how their non-custodial cross-chain swap aggregator works.Swap now: https://swap.thorchain.org/THORChain is a decentralized crypto exchange. THORChain is the first and biggest DEX for Bitcoin. You can use any self-custody wallet to swap, and there's no KYC required.Timestamps:00:00:00 Intro00:02:30 Marketing update00:05:00 Freddy introduction00:07:00 Why Ravn Exchange was created00:11:00 Which DEXs have you integrated?00:14:00 XMR coming to THORChain is very big00:15:00 Any insight into your target audience?00:19:00 Has Ravn considered using THORChain XMR swaps to achieve privacy automatically?00:25:00 AI agent infrastructure00:28:00 Execution page00:32:00 Does Ravn hold user funds?00:33:00 Adding RUNE support?00:36:00 Fiat on/off ramps00:37:00 Is Ravn Exchange live?00:38:00 Integration page00:43:00 Waiting on Router V6 upgrade00:47:00 Memoless explanation00:48:00 Do you expect free stable-to-stable swaps to see a significant uptick?

Solution providers across payments and fraud prevention are launching shows right now, and that is a good thing. More voices in this space means more people learning out loud. Jordan sits down with Brian Davis to talk about what it actually takes to keep one running.   This one is less about fraud and more about the machine behind the content: setting goals before you set a budget, getting marketing and the C suite aligned on what an episode is supposed to do, and what happens when a sponsor expects conversions from a campaign that was built for awareness. Brian brings the demand gen and community perspective. Jordan brings four years of running a show as a team of one.   They get into the guest pool question nobody plans for, where a fraud cast should plant its flag in the funnel, why the attribution argument tends to sort itself out, and how different production models all end up working for different goals. Jordan also walks through his gear stack and the specific choices that make a show look and sound the way he wants, including the piece of equipment most people skip.   If you run marketing at a vendor, host a show, appear on webinars, or are thinking about pointing a camera at yourself for the first time, there is something in here worth stealing.   Topics covered: Founder led and executive led content strategy Podcast sponsorship goals, CTAs, and realistic expectations First touch and last touch attribution in B2B payments marketing Why enterprise merchants weigh fraud podcast invitations carefully Editorial independence when your show and your employer share a space Recording podcasts on the conference floor Microphones, mirrorless cameras, lighting, and audio levels for video Editing workflows, distribution, and why consistency beats production value Equipment Mentioned and Suggested: Sony a6700 - https://a.co/d/03P0tsuf Shure MV7+ - https://a.co/d/03P0tsuf Shure SM7dB - https://a.co/d/03P0tsuf Fifine Mic - https://a.co/d/03P0tsuf Other mentions: Interface for mic to computer - https://a.co/d/0fCRRpiK Cloudlifter (not needed for Sm7dB only SM7B regular) - https://a.co/d/07HYP75U Sony ZVE-10 (non usb 4k) - https://a.co/d/07HYP75U ------------------------------------ This episode is brought to you by ⁠WhoBilled.me⁠. Ever seen a charge on your statement like "POS CHECK CARD PURCHASE DEBIT * SUPERCELL" and had no idea what it was? Merchants get about 25 characters to identify themselves, your bank wraps its own labels around that, and a location field gets stapled on the end. The result reads like a ransom note — so people dispute their own kids' in-game purchases and shrug off the charges that were actually fraud. Paste the descriptor into ⁠https://WhoBilled.me⁠ and find out who really billed you, how to reach them, and what the charge was probably for.

Você já atendeu uma paciente com dor pélvica crônica encaminhada pela ginecologia, trazendo uma pasta de exames normais e contando que ela foi rotulada como "coisa da cabeça" ou “de fundo emocional”? No episódio 365 do PQU Podcast, falamos sobre a atuação do psiquiatra na interconsulta com a saúde feminina. Abordamos a neurobiologia da dor nociplástica, os fenômenos de alodinia e hiperalgesia, e como a catastrofização e a comorbidade com o Transtorno de Personalidade Borderline afetam não apenas o limiar doloroso, como também a relação com a equipe médica. Explicamos também por que opióides são contraindicados nesses casos, quais as alternativas de farmacoterapia e como capacitar o ginecologista para fazer um encaminhamento sem gerar a sensação de descarte. Ouça agora o episódio 365 do PQU Podcast na sua plataforma favorita ou acesse o conteúdo completo em pqupodcast.com.br!

Consultant, éditeur de sites SEO, créateur d'un SaaS : autant d'activités, autant d'outils, autant de contextes avec lesquels jongler. Yannick Bouvard a tout regroupé dans une seule interface IA : Un cockpit posé au-dessus d'Hermès, l'agent qui range, exécute et invoque ses sous-agents. Yannick nous présente son architecture IA, de la veille au pilotage de ses sites. Il vous partage tout, cas d'usage par cas d'usage. Au cours de cet épisode :Comment il a architecturé son business OS sur une seule interface ?Comment piloter des sites SEO sans APIComment éduquer un agent pour qu'il devienne autonome au quotidienPourquoi il a quitté OpenClaw pour Hermes Agent ?Hermes Agent vs Claude Code : comment choisir selon les tâches ?AI Club est une émission soutenue par Weglot, une solution tout-en-un qui traduit, gère et affiche votre site web dans 110+ langues, sans nécessiter de code. 

Transport Fever 3 hat auf der Gamescom absolut abgeliefert. Die Entwickler haben die Wünsche der Community sichtlich verstanden und genau an den richtigen Stellschrauben gedreht. Der größte Blickfang ist ganz klar die unglaubliche Detailverliebtheit. Wer an die Züge heranzoomt, beobachtet wuselnde Passagiere und winzige Animationen an den Maschinen, die das Verkehrsgeschehen so lebendig wie nie zuvor wirken lassen. Die Landschaften versprühen pure Lust am Bauen und Zuschauen. Ein echter Quantensprung ist den Machern beim Benutzeroberfläche gelungen. Die Menüs wirken extrem aufgeräumt, elegant und vor allem intuitiv. Wo man im Vorgänger noch in verschachtelten Untermenüs nach wichtigen Statistiken oder Werkzeugen suchen musste, geht das neue Interface spielend leicht von der Hand. Schon die erste Anspielsession zeigt riesiges Potenzial für unzählige Stunden voller Tüftelspaß. Für Fans von Aufbauspielen und Transportgiganten wartet hier ein echtes Highlight.

Join in a lively discussion of Kurtzman Trek, which seems to be a near constant conversation with Star Trek Fandom. Nick talks, "Lanterns", Bill talks the X-Men casting, and Rob eulogizes the passing of Hayden Panetteire. In the 2nd half, we review the season 7 episodes, "Interface" and "Gambit Part I"

The annual Dark Nation Radio UNDER COVER show can now be streamed and downloaded—two hours of dark scene (and adjacent) bands covering their favorites. I hope you'll give this one a spin because it's a fun show! Among those in the mix are Faith & the Muse, Suspiria, Leaetherstrip, The Cult, Rasputina, Black Rose Burning, PIG, Urban Heat, Bauhaus, Front Line Assembly, The Sisters of Mercy, Rosegarden Funeral Party, and KMFDM. Stream, share, enjoy! Thank you for your support for DJ cypher's Dark Nation Radio. DJ cypher's Dark Nation Radio Playlist 23 August 2026 Faith & the Muse, “Running Up that Hill” Kill Shelter, “She's in Parties” Samsas Traum, “Terra Titanic” Leaetherstrip, “White Horse” Front Line Assembly, “Amadeus” Beauty for Ashes, “Stand Back” Frenchy and the Punk, “Cities in Dust” The Cult, “Born to Be Wild” Malia J, “Smells Like Teen Spirit” Anna Calvi, “Red Right Hand” Suspiria, “Goodbye 70s” Dead on a Sunday, “Bloody Mary” The Newton Brothers ft. Macy Gray, “Wicked Game” Bauhaus, “Ziggy Stardust” The Sisters of Mercy, “Gimme Shelter” Rasputina, “Wish You Were Here” Black Rose Burning, “Ever Fallen in Love” Urban Heat, “Goodbye Horses” [Rein]forced ft. Interface, “Butterfly Wings” The Blue Hour, “Christian Says” Rosegarden Funeral Party, “Mercy Street” Zeromancer, “Send Me an Angel” PIG, “Head Like a Hole” Xenturion Prime, “Dust in the Wind” Marsheaux, “Leave in Silence” Unwoman, “I Know Its Over” Vempire, “Pet Sematary” KMFDM, “These Boots Were Made for Walking” DJ CYPHER'S DARK NATION RADIO—25 years strong! **Live Sundays @ 9 PM Eastern US on Spirit of Resistance Radio sorradio.org **Recorded @ http://www.mixcloud.com/cypheractive **Downloadable @ http://www.hearthis.at/cypheractive **Inquiries to darknationradio[at] gmail[dot]com **Facebook @ http://www.facebook.com/groups/darknationradio onradio T

Chapter 35.04: Chochma: The Ultimate Interface​A journey into the deepest teachings of the Torah and their application to our personal, emotional and psychological lives.The Tanya Applied radio show is broadcast every Saturday night, 10–10:30PM ET onWSNR 620 AM – Metro NY areaWJPR 1640 AM — Highland Park and Edison, NJOnline: www.talklinenetwork.comBy phone: Listen Line: 641-741-0389Many of us may be familiar with some of the central ideas in Tanya – including the battle of the two souls; what defines man and makes us tick; how we can control our temptations; how we can become more loving; what we can do to curb and harness our vices, like anger, jealousy, and depression; the formula for growth; how we can develop a healthy relationship with G-d; and why we are here. In this 30-minute program, you will learn how these ideas can be applied to your life today. You will discover secrets to a successful life that will transform you and your relationships.Rabbi Simon Jacobson is the best-selling author of Toward a Meaningful Life, and he is the creator of the acclaimed and popular MyLife: Chassidus Applied series, which has empowered and transformed hundreds of thousands through Torah and Chassidus.Now, Rabbi Jacobson brings his vast scholarship and years of experience to Tanya. Please join Rabbi Simon Jacobson for this exhilarating journey into your psyche and soul. You will come away with life-changing practical guidance and direction, addressing all the issues and challenges you face in life.For more info: www.chassidusapplied.com/tanyaMusic by Zalman Goldstein • www.ChabadMusic.coms of the Torah and their application to our personal, emotional and psychological lives.A journey into the deepest teachings of the Torah and their application to our personal, emotional and psychological lives.

An Ancient Trap - Episode 16 - Interface   We are proud to announce that Shadowpublications.com is sponsored by Larry's Coffee. Visit Larry's, check out their awesome coffees, and get a free gift.   Support the podcast by purchasing The Black: Oceania. Ebook available from Amazon Become a member for exclusive content Written by Paul E Cooley Text Copyright:    ©2023 Paul E Cooley Audiobook Copyright:    ©2026 Paul E Cooley Support the podcast and get access to published and unpublished books all voiced by the author! If you are suffering from depression or other mental disorders, please get help. http://www.bipolarsupport.org/ https://suicidepreventionlifeline.org/ Please visit Shadowpublications.com for more information about the author and this series. To stalk the author on social media: Email: paul@shadowpublications.com Mastodon: @paul_e_cooley@vyrse.social Newsletter: http://mailinglist.shadowpublications.com  

Live Recorded Set from VirtualDJ Radio Hypnotica

David and Sean are out, leaving James and Mat to put on their big boy pants and deliver a podcast all by themselves. Can't be that hard, right? This week: We're getting an "extended look" at Grand Theft Auto 6 on 27th August, Take-Two boss says we'll all be streaming our games in about "three years", Switch 2 continues to be Nintendo's fastest selling system, Roblox tanked $9 Billion in a single day, and the late Sam Neill will reportedly feature in The Legend of Zelda film. Also: What was ‘Interface', folding iPhones, VHS memories, boycotts and more. Games Discussed: Big Walk, Halo: Campaign Evolved, The Incident at Galley House, Final Fantasy VII Rebirth, Tangle Tower. SUPPORT Patreon CONTACT Website Discord Bluesky Threads Instagram Facebook FOLLOW TCGS on Bluesky David on Bluesky Sean on Bluesky Mat on Bluesky James on Bluesky WATCH Twitch YouTube LISTEN Spotify Apple Podcasts Pocket Casts CREDITS Music by Nick Parton Art by Dave Chong

A brain computer interface (BCI) is any technology that allows you to connect your 3 pounds of wetware to a computer. But instead of implanting electrodes via neurosurgery, might the next revolution in BCIs come from something very small, like nanoparticles? Would this allow us to spy on millions (or billions) of neurons talking at once -- and could we do so without opening the skull? Will this allow BCI tech to become as common as smartphones? Join Eagleman as he talks with the company Subsense about why the next brain-computer interface might come from thinking small.

Live Recorded Set from VirtualDJ Radio Hypnotica

The terminal has been a constant in software development for decades. It has remained largely unchanged while everything around it transformed. However, as AI agents have become central to the developer workflow, the terminal is emerging as a natural home for agentic development, and a new category of tooling is forming around it. Warp is a popular Rust-based terminal and agentic development environment. The company recently open-sourced its codebase and launched Oz, its cloud agent infrastructure product aimed at helping enterprises automate software development at scale. Zach Lloyd is the co-founder and CEO of Warp, and a former principal engineer at Google where he led engineering on the Google Docs suite. In this episode, Zach joins Gregor Vand to discuss how Warp has evolved over the years, why the terminal is better suited than the IDE for agentic development, how Oz approaches the governance and auditability challenges enterprises face with AI agents, and more.Sponsorship inquiries:sponsor@softwareengineeringdaily.com The post The Terminal as an Agentic Interface appeared first on Software Engineering Daily.

Lawyers may soon spend less time opening applications, and more time simply telling AI what needs to happen next. In episode 630 of the Lawyerist Podcast, Zack Glaser talks with innovation strategist Sam Harden about the rise of agentic AI and how tools like ChatGPT Work and Claude Cowork could reshape the way legal professionals work.  Unlike a traditional chatbot, an agentic system can operate within a workspace, analyze groups of files, create and update documents, develop plans, and connect information from different sources. That could allow lawyers to access emails, calendars, case materials, research, and practice management information through a single working interface.  Zack and Sam discuss what this means for law firms filled with open Word documents, browser tabs, PDFs, research databases, and disconnected software. They also challenge the idea that AI should perform the most sophisticated legal reasoning while lawyers clean up the formatting. Instead, AI should take on the repetitive administrative work so lawyers can operate at the top of their licenses.  If you want to understand where legal AI is heading beyond prompting and summarization, this episode offers a grounded look at the tools, opportunities, risks, and experiments shaping the next phase of legal work.  Listen to our previous episodes on Agentic AI, Law Firm Workflows & the Future of Legal Work.  #620: What Claude Means for Law Firms, Part 2: Using AI to Practice at the Top of Your License, with Sam Harden Apple | Spotify | LTN  #619: What Claude Means for Law Firms: AI Skills, Connectors, and Workflow Strategy, with Sam Harden Apple | Spotify | LTN  #601: Beyond Chatbots: Using Agentic AI in Law Firm Intake, with Matt Spiegel Apple | Spotify | LTN  #581: Agentic AI for Lawyers: Moving Beyond Enhanced Search, with Drew Bloom Apple | Spotify | LTN  #577: Rethinking Law Firm Growth in the Age of AI, with Sam Harden Apple | Spotify | LTN  Have thoughts about today's episode? Join the conversation on LinkedIn, Facebook, Instagram, and X!   If today's podcast resonates with you and you haven't read The Small Firm Roadmap Revisited yet, get the first chapter right now for free! Looking for help beyond the book? See if our coaching community is right for you.   Access more resources from Lawyerist at lawyerist.com.   Chapters / Timestamps  00:00 – Introduction  00:18 – What the World Cup Teaches About Professionalism  05:19 – Meet Sam Harden  06:25 – The “Claudification” of ChatGPT  08:15 – From Chatbot to Agentic Workspace  10:35 – Why ChatGPT Is Following Claude  13:00 – The Shift from Asking to Delegating  14:00 – What Agentic AI Actually Means for Lawyers  17:40 – Making AI the Interface for Legal Work  19:10 – The Future Surface of Work  23:30 – When Your Phone Becomes Your Workspace  25:35 – How Agentic AI Could Transform Law Firms  26:45 – Letting AI Handle the Legal Busywork  29:20 – Operating at the Top of Your License  31:15 – AI Should Format the Work, Not Make the Judgment  34:30 – How Lawyers Can Start Experimenting Safely  37:25 – Closing Thoughts 

The terminal has been a constant in software development for decades. It has remained largely unchanged while everything around it transformed. However, as AI agents have become central to the developer workflow, the terminal is emerging as a natural home for agentic development, and a new category of tooling is forming around it. Warp is a popular Rust-based terminal and agentic development environment. The company recently open-sourced its codebase and launched Oz, its cloud agent infrastructure product aimed at helping enterprises automate software development at scale. Zach Lloyd is the co-founder and CEO of Warp, and a former principal engineer at Google where he led engineering on the Google Docs suite. In this episode, Zach joins Gregor Vand to discuss how Warp has evolved over the years, why the terminal is better suited than the IDE for agentic development, how Oz approaches the governance and auditability challenges enterprises face with AI agents, and more.Sponsorship inquiries:sponsor@softwareengineeringdaily.com The post The Terminal as an Agentic Interface appeared first on Software Engineering Daily.

The terminal has been a constant in software development for decades. It has remained largely unchanged while everything around it transformed. However, as AI agents have become central to the developer workflow, the terminal is emerging as a natural home for agentic development, and a new category of tooling is forming around it. Warp is a popular Rust-based terminal and agentic development environment. The company recently open-sourced its codebase and launched Oz, its cloud agent infrastructure product aimed at helping enterprises automate software development at scale. Zach Lloyd is the co-founder and CEO of Warp, and a former principal engineer at Google where he led engineering on the Google Docs suite. In this episode, Zach joins Gregor Vand to discuss how Warp has evolved over the years, why the terminal is better suited than the IDE for agentic development, how Oz approaches the governance and auditability challenges enterprises face with AI agents, and more.Sponsorship inquiries:sponsor@softwareengineeringdaily.com The post The Terminal as an Agentic Interface appeared first on Software Engineering Daily.

The terminal has been a constant in software development for decades. It has remained largely unchanged while everything around it transformed. However, as AI agents have become central to the developer workflow, the terminal is emerging as a natural home for agentic development, and a new category of tooling is forming around it. Warp is a popular Rust-based terminal and agentic development environment. The company recently open-sourced its codebase and launched Oz, its cloud agent infrastructure product aimed at helping enterprises automate software development at scale. Zach Lloyd is the co-founder and CEO of Warp, and a former principal engineer at Google where he led engineering on the Google Docs suite. In this episode, Zach joins Gregor Vand to discuss how Warp has evolved over the years, why the terminal is better suited than the IDE for agentic development, how Oz approaches the governance and auditability challenges enterprises face with AI agents, and more.Sponsorship inquiries:sponsor@softwareengineeringdaily.com The post The Terminal as an Agentic Interface appeared first on Software Engineering Daily.

The terminal has been a constant in software development for decades. It has remained largely unchanged while everything around it transformed. However, as AI agents have become central to the developer workflow, the terminal is emerging as a natural home for agentic development, and a new category of tooling is forming around it. Warp is a popular Rust-based terminal and agentic development environment. The company recently open-sourced its codebase and launched Oz, its cloud agent infrastructure product aimed at helping enterprises automate software development at scale. Zach Lloyd is the co-founder and CEO of Warp, and a former principal engineer at Google where he led engineering on the Google Docs suite. In this episode, Zach joins Gregor Vand to discuss how Warp has evolved over the years, why the terminal is better suited than the IDE for agentic development, how Oz approaches the governance and auditability challenges enterprises face with AI agents, and more.Sponsorship inquiries:sponsor@softwareengineeringdaily.com The post The Terminal as an Agentic Interface appeared first on Software Engineering Daily.

Anthony and Katie each pick a few interface elements that are really pulling their weight, perhaps more than they should be.Hosts:Anthony Hobday, Generalist Product Designer: ⁠⁠⁠https://twitter.com/hobdaydesign⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Katie Langerman, Design Systems Designer: ⁠⁠⁠https://twitter.com/KatieLangerman⁠

BubbiByte joins the podcast to discuss why depouch was built, the importance of simplicity, direct THORChain integrations, memoless swaps, decentralization, censorship, and the future of permissionless crypto.Swap now https://swap.thorchain.org/THORChain is a decentralized crypto exchange. THORChain is the first and biggest DEX for Bitcoin. You can use any self custody wallet to swap and there's no KYC required.Timestamps:00:00:00 Intro00:04:00 BubbiByte begins00:09:00 Why depouch was created00:12:00 THORChain feels like the early days of crypto00:13:00 The first principles of our community00:14:00 Our ecosystem is special and unique00:15:00 depouch was created with the goal of being simple and reliable00:19:00 Creating the simplest and most reliable user experience00:24:00 Kenton: The aggregator should support all pathways00:28:00 Was it easy to directly integrate THORChain?00:30:00 Direct integrations are preferable to APIs00:32:00 depouch's marketing approach00:33:00 It's much easier to build financial products in crypto00:38:00 Marketing strategy: Search-term-based video content00:39:00 Flagged address filtering is unavoidable00:42:00 More interfaces are a net positive for the protocol00:44:00 Let's get the word out about depouch00:45:00 Do you support memoless swaps? (Coming soon)00:46:00 Boone shout-out00:47:00 App Layer support?00:50:00 How do you make the interface as simple as possible?00:53:00 depouch screen share00:56:00 Slippage and "price protection" explained on STO01:01:00 "THORChain and Maya Protocol are decentralized—other DEXs are not"01:02:00 We must stand firm on our principles01:06:00 Decentralized stablecoins are like perpetual motion (Kenton)01:07:00 What is actually a DEX?01:10:00 Is there anything else you'd like to mention?01:15:00 Censorship concerns across Europe01:18:00 Tyranny has been the norm01:20:00 Is THORChain a PEX (Permissionless Exchange)?

 We use our faces more than any other part of our body to communicate with others and that communication has evolved a lot over the centuries. Fay Bound-Alberti founded the Centre for Technology and the Body at King's College London where she leads Interface, a project examining technologies of the face. She joins host Krys Boyd to discuss how facial understanding is tied to where and when people live, what happens when someone is “face blind,” and why the Mona Lisa's smile is still so beguiling. Her book is “The Face: A Cultural History.”  Learn about your ad choices: dovetail.prx.org/ad-choices

Interface layer for full contact support, Favorite XL Upgrades Pt 1

Our guest this week emerged as a prominent figure in Skateboarding during the 90's, captivating audiences with his innovative style and technical mastery in both Street and Transition skating. From legendary video parts in classics like Interface, Cinematographer, and many others, to decades of respected contributions to skateboarding culture, he helped shape the look and feel of modern street skating while earning the admiration of generations of riders.  But these days, his passion extends beyond Skateboarding. As the founder and owner of Aquillux Filtration Systems, he's focused on helping families live healthier through premium whole-home water filtration and under-sink alkaline drinking water systems. Their systems are designed to soften and filter municipal water while restoring essential minerals to elevate pH levels for cleaner, healthier, and better-tasting hydration.From Skateboarding and Surfing to Entrepreneurship and clean water, we're looking forward to covering it all with a true original.We welcome to the show Mr. Dan Rogers.

It's New Tunesday: new releases from the past week! Give the bands a listen. If you like what you hear, support the bands! Today's episode features new releases by The Distant Minds, Lifelong Corporation & Mutation 73, Interface, Anders Manga, Massiv In Mensch, Choke Chain, Miss Construction, The Witch Said No, Years Of Denial, After The Sin, Graveyard Gossip, DeathFauna, Crying Vessel, Corlyx, Mouth Ulcers, and The Slashes!

Communion After Dark - features the latest and best in Dark Alternative-Electronic Music. This week's show features music from Nachtmahr, Mental Discipline, Silke Bischoff, Interface, Anders Manga, and many more artists from around the world.

Part two of the discussion with Jim Hodapp and Bob Belderbos focused on practical software development. Topics included testing, tooling, libraries, developer workflows, AI coding assistants, and why Rust's ecosystem is helping developers build more reliable systems. Key Discussion Points Rust libraries and crates Built-in testing capabilities AI-assisted coding workflows Compiler-driven development Tooling and developer experience The rise of AI coding assistants has changed the software development landscape. Code can now be generated in seconds. The challenge is determining whether that code should be trusted. This is where AI-assisted Rust presents an interesting model for modern engineering. Rather than relying solely on AI output, developers gain support from a compiler, testing framework, and ecosystem specifically designed to catch problems early. The result is a workflow centered on reliability instead of speed alone. About our Guests Jim Hodapp Jim Hodapp is a veteran software engineer, engineering leader, and technical coach with deep roots in systems programming. His background spans C, C++, Linux, embedded systems, software architecture, and engineering management. In recent years, he has become a recognized Rust advocate, helping developers transition from traditional systems languages into modern, memory-safe development practices. Through RefactorCoach and his Rust training initiatives, Jim focuses on improving engineering effectiveness, software quality, and developer growth. Follow Jim on LinkedIn: https://www.linkedin.com/in/jim-hodapp/ Bob Belderbos Bob Belderbos is a software developer, educator, coach, and co-founder of PyBites. Originally coming from a finance background, Bob transitioned into software through automation, scripting, and Python development. He has spent years helping developers improve their coding skills through practical challenges, mentoring, and community-based learning. More recently, Bob has expanded his focus into Rust, combining his Python expertise with modern systems programming practices to help developers build faster, safer, and more maintainable software. Follow Bob on LinkedIn: https://www.linkedin.com/in/bbelderbos/ Why AI-Assisted Rust Works Differently Many AI-generated applications succeed initially but struggle when complexity increases. The root issue is often a lack of validation. AI may generate code that appears correct while introducing subtle assumptions, type mismatches, or architectural weaknesses. Rust changes this dynamic. Its compiler demands correctness before execution. This creates an environment where AI-generated solutions must satisfy strict requirements before becoming production-ready. Rather than fighting the compiler, developers can use compiler feedback as an additional review mechanism. The combination creates a surprisingly effective development loop. AI-Assisted Rust and Compiler-Driven Development Historically, developers discovered many errors during runtime. That process is expensive. Bugs appear later, testing cycles expand, and debugging consumes valuable time. Compiler-driven development shifts detection earlier. When AI generates code inside a Rust project, the compiler immediately validates: Types Ownership rules Memory safety Data structures Interface compatibility This reduces uncertainty. The AI-assisted Rust approach effectively turns compilation into a continuous quality-control process. Every issue caught during compilation is one less issue waiting in production. How AI-Assisted Rust Improves Testing Another major topic discussed during the episode was testing. Rust includes first-class testing support directly within the language ecosystem. Developers can place tests alongside implementation code and execute them through the same tooling used to build applications. This integration matters. When testing becomes frictionless, developers are more likely to perform it consistently. The guests also discussed an emerging AI-era consideration. When AI generates both application code and tests, developers must ensure tests remain objective. Separating tests from implementation can sometimes help prevent AI from simply validating its own assumptions. The goal remains the same: Verify behavior rather than confirm expectations. AI-generated tests are only valuable when they challenge the code instead of reinforcing it. The Role of Libraries and Crates Every modern language depends on ecosystems. Rust is no exception. The conversation explored how Rust balances a relatively focused standard library with a thriving third-party package ecosystem. Instead of relying on massive built-in functionality, Rust encourages developers to leverage well-maintained community crates. This approach provides flexibility while avoiding unnecessary complexity in the language itself. For teams adopting AI-assisted Rust, this creates another advantage. AI tools can often identify appropriate crates quickly, reducing research time while still allowing developers to evaluate quality and suitability. Tooling That Supports Better Software One recurring theme throughout the discussion was integration. Rust combines several critical capabilities into a cohesive experience: Package management Dependency management Building Testing Formatting Linting Developers spend less time assembling tooling and more time solving business problems. This integrated philosophy becomes increasingly important as software stacks grow more complex. When AI enters the workflow, consistency becomes even more valuable because every tool participates in maintaining quality standards. Audit your current development workflow and identify how many separate tools are required for building, testing, linting, and dependency management. The Real Value Is Confidence The most important benefit of AI-assisted Rust may not be performance. It may not even be productivity. It is confidence that: The generated code meets standards. Tests validate behavior. Memory safety issues are unlikely to appear unexpectedly. The compiler is actively helping rather than simply translating instructions. That confidence allows teams to move faster without sacrificing reliability. The best development environments reduce uncertainty rather than merely increasing speed. Conclusion AI-assisted Rust represents a practical evolution in software development. Instead of choosing between AI productivity and engineering rigor, developers can combine both. AI accelerates implementation while Rust's compiler, testing capabilities, and tooling ecosystem reinforce quality. As software becomes increasingly AI-generated, environments that encourage correctness from the start may become some of the most valuable platforms available to developers. Stay Connected: Join the Developreneur Community

This week on The Pro Audio Suite, George brings out a little show and tell with the SSL One, SSL's compact single mic preamp interface aimed squarely at the same world as the Scarlett Solo and other simple home studio boxes. The team gets into what actually matters for voice actors and home studio users, including physical gain knobs, direct monitoring, high pass filters, 4K mode, USB-C connections, headphone control, auto gain, clip protection, and why simple interfaces are sometimes the best interfaces. There is also a little live testing with Twisted Wave, a quick look at Source Elements Recorder on mobile, some PASport VO phone patch chat, and the usual collection of detours involving Jack FM, trap doors, yacht rock, and turntables that apparently survive being moved while playing. If you are a voice actor, producer, podcaster, or home studio owner trying to choose an audio interface without accidentally buying a puzzle box, this one is worth a watch. Thanks to our sponsors, Austrian Audio. Recorded using Source-Connect, edited by Andrew Peters, and mixed by Voodoo Sound.

Today for "Agent Dispatch#1":-- When people talk about the future of software, they often focus on what the model can do. But the real shift may be in how that intelligence connects to the systems around it.That is where an MCP (Model Context Protocol) becomes interesting. At a high level, MCP is about giving software a structured way to access tools, data, and external services.In a financial context, that starts to look less like a technical protocol and more like a new interface layer, one that lets agents interact with wallets, accounts, payments, portfolio data, and other financial actions in a more standardized way. That matters because finance has always been fragmented. Every institution, product, and workflow has its own rules, formats, and integrations. Humans can deal with that fragmentation by clicking, logging in, switching screens, and making judgment calls.Software agents need something cleaner. MCP could help provide that cleaner layer. Instead of building one-off integrations for every financial action, builders can think in terms of a shared interface between agents and financial systems.That opens the door to more composable workflows, more automation, and eventually, more autonomous financial behavior. The bigger idea is not that MCP replaces the stack underneath. It is that it creates a more usable front door for intelligence to interact with finance.And if that works, it changes more than convenience. It changes how financial products are built, how agents operate, and how value moves through the system. That is why MCP as a financial interface layer is worth paying attention to.It may end up being one of the quiet infrastructure shifts that makes the next generation of finance feel much more usable.-- The podcasts are authored, edited and produced by Raph Grieco (⁠⁠⁠⁠⁠⁠⁠⁠raphael-grieco.com⁠⁠⁠⁠⁠⁠⁠⁠ | ⁠⁠⁠⁠⁠⁠⁠⁠olivecapital.vc⁠⁠⁠⁠⁠⁠⁠⁠).

The latest In Touch With iOS with Dave he is joined by Jill McKinley, Chuck Joiner, Jeff Gamet, Eric Bolden, Marty Jencius. Apple surprised everyone this week with unexpected price increases across much of its hardware lineup, and the crew dives into what changed, why it happened, and whether Apple could have handled the announcement better. The panel also discusses the latest developer betas for iOS 27, iPadOS 27, macOS 27, watchOS 27, tvOS 27, and visionOS 27, including Apple's expanding Apple Intelligence features. The show notes are at InTouchwithiOS.com  Direct Link to Audio  Links to our Show Give us a review on Apple Podcasts! CLICK HERE we would really appreciate it! Click this link Buy me a Coffee to support the show we would really appreciate it. intouchwithios.com/coffee  Another way to support the show is to become a Patreon member patreon.com/intouchwithios Website: In Touch With iOS YouTube Channel In Touch with iOS Magazine on Flipboard Facebook Page BlueSky Mastodon X Instagram Threads Summary Apple surprised everyone this week with unexpected price increases across much of its hardware lineup, and the crew dives into what changed, why it happened, and whether Apple could have handled the announcement better. The panel also discusses the latest developer betas for iOS 27, iPadOS 27, macOS 27, watchOS 27, tvOS 27, and visionOS 27, including Apple's expanding Apple Intelligence features. The Vision Pro discussion covers the new Siri experience, curved app windows, panoramic photos becoming immersive environments, and other interface refinements. The team also examines Apple's upcoming HomeKit overhaul, support for the Matter 1.6 standard, and the latest updates to Wallet, Notes, and AirPods. Other topics include cable standards confusion, an iPhone design issue that may never be fixed, a handy weekly restart tip, Prime Day recommendations, and a return of one of Apple's classic products. Topics and Links Breaking News Apple Price Increases Across Product Lines * Discussion on Apple's unexpected price increases affecting Vision Pro, Macs, iPads, HomePod, Apple TV, Apple Watch, and MacBook models. * The panel debates whether Apple should have provided advance notice and compares the changes to price increases happening across the tech industry. Apple Just Raised the Price of the MacBook Neo Apple Just Increased Prices on MacBooks, iPads, and More Apple's Online Store Is Down Apple Vision Pro Just Got Even More Expensive Apple TV and HomePod Just Went Up in Price Amid Wait for New Models Apple's Stock Has Worst Day in More Than a Year After Price Increases  In Touch With Vision Pro this week.  * New Siri experience with Apple Intelligence integration. * Curved application windows. * Panoramic photos become immersive environments. * Interface refinements and spatial computing enhancements. Apple Seeds Second visionOS 27 Beta to Developers visionOS 27 Beta Release Notes | Apple Developer Documentation Apple Vision Pro's longest immersive concert was harder to film than you'd think Beta this week. iOS 27 Beta 2 was released Second developer betas of iOS 27, macOS 27 are out Everything New in iOS 27 Beta 2 Apple Seeds watchOS 27 Beta 2 to Developers A Small iOS 27 Change Hints at Apple's Long-Rumored Home Hub  iOS 27 Home App: 10+ New HomeKit Features  Apple Releases Updated AirPods Beta Firmware With iOS 27 Features Every New AirPods Feature in iOS 27 AirPods Max 2 are getting harder to resist with iOS 27 upgrades Apple Seemingly Killed Siri AI Waitlist Workaround in macOS 27 Beta 2 iOS 27 Wallet App Gets 7 New Features In Touch With Mac this week Apple also seeded macOS 27 Golden Gate beta 2 to developers. MacRumors highlights Siri AI-related features on the Mac, including a Siri app, Visual Intelligence on Mac, and "Write with Siri" features for writing help and feedback. macOS Golden Gate Beta 2 Now available for Developers Apple Releases Updated AirPods Beta Firmware With iOS 27 Features   macOS Tahoe 26.5.2 and iOS 26.5.2 Updates Coming Soon Can you save money with a USB4 cable over a Thunderbolt 4 one? Cable Tester: https://amzn.to/4oOkThM New macOS security flaw could let hackers disable protection tools, researchers say Older iPhones have an unfixable security flaw - why it can't be patched and the models affected Other Topics iPhone 17 set to break a record no flagship has touched in 15 years Why You Should Restart iPhone Once A Week and How to Automate It News Silo returns next week with three major changes for season 3 This weeks "Things we found" Amazon Prime Days were this week. What deals did we find?  Dave: Apple AirPods Max 2 $399 https://amzn.to/3SHDPmc and UGREEN Mac mini M4 Dock & Stand with NVMe SSD Enclosure   https://amzn.to/3SrWOkK Jill: FLEXISPOT ErgoX Premium Ergonomic Office Chair with Footrest $299 but $ 229 on Prime Day https://amzn.to/4vwPJOr Chuck: Govee Floor Lamp 3 Lite, Smart RGBIC LED Corner Lamp https://amzn.to/4wbeSya   Marty: Shokz Open Run Pro 2  over-the-ear bone conduction headphones 124$ (on sale for Prime week) normally 179$ https://amzn.to/4eKzx4O Eric: 6–AC outlets, 2–USB-A,  2–USB-Chttps://amzn.to/4w84RBD Jeff: You Can Draw in 30 Days by Mark Kistler Announcements Macstock X is here celebrating its 10th anniversary ! Dave, Chuck, Jeff, Marty, and Jill are all speaking this year!. With Three Full Days of expert-led Presentations and Workshops, Macstock's sessions are crammed full of productivity-enhancing content. NEW this year is a partnership with sponsor Ecamm. Ecamm Creator Camp: Mac Edition on July 9, 2026 there are only 100 tickets available for the bundle. There are 2 passes available: Macstock weekend pass July 10,11,12, 2026 or the Macstock Ecamm Bundle starting July 9 (only 100 tickets available)  Come join us. Register HERE and use our offer code INTOUCH to save $50 Our Host Dave Ginsburg is an IT professional supporting Mac, iOS and Windows users and shares his wealth of knowledge of iPhone, iPad, Apple Watch, Apple TV and related technologies. Visit the YouTube channel https://youtube.com/intouchwithios follow him on Mastodon @daveg65, , BlueSky @daveg65  and the show @intouchwithios   Our Regular Contributors Jeff Gamet is a podcaster, technology blogger, artist, and author. Previously, he was The Mac Observer's managing editor, and Smile's TextExpander Evangelist. You can find him on Mastadon @jgamet Pixelfed @jgamet@pixelfed.social and Bluesky @jgamet.bsky.social‬ Podcasts The Context Machine Podcast  Retro Rewatch Retro Rewatch His YouTube channel https://youtube.com/jgametrecordin Marty Jencius, Ph.D., is a professor of counselor education at Kent State University, where he researches, writes, and trains about using technology in teaching and mental health practice. His podcasts include Vision Pro Files, The Tech Savvy Professor and Circular Firing Squad Podcast. Find him at jencius@mastodon.social  https://thepodtalk.net  Eric Bolden is into macOS, plants, sci-fi, food, and is a rural internet supporter. You can connect with him by email at eabolden@mac.com, on Mastodon at @eabolden@techhub.social, on his blog, Trending At Work, and as co-host on The Vision ProFiles podcast.   Jill McKinley works in enterprise software, server administration, and IT A lifelong tech enthusiast, she started her career with Windows but is now an avid Apple fan. Beyond technology, she shares her insights on nature, faith, and personal growth through her podcasts—Buzz Blossom & Squeak, Start with Small Steps, and The Bible in Small Steps. Watch her content on YouTube at @startwithsmallsteps and follow her on X @schmern. Find all her work at http://jillfromthenorthwoods.com  Chuck Joiner is the host of MacVoices and hosts video podcasts with influential members of the Apple community. Make sure to visit macvoices.com and subscribe to his podcast. You can follow him on Twitter @chuckjoiner and join his MacVoices Facebook group.

The MacVoices Live! panel discusses Apple's updated App Store review guidelines, the challenge of filtering low-quality or AI-generated apps, and whether trusted developers should receive faster review. Chuck Joiner, David Ginsburg, Jim Rea, Marty Jencius, Web Bixby, Jeff Gamet, and Eric Bolden also debate Apple's Passwords app gaining automatic password-changing abilities, weighing convenience against account-lockout risk. They also provide reactions to Snap's new Specs and the uncertain future of smart glasses.  MacVoices is supported by NordLayer. Secure your network & stay compliant with one toggle-ready platform. Get an exclusive offer: up to 22% off NordLayer yearly plans plus 10% on top with the coupon code: MACVOICES10 at NordLayer.com/macvoices. Try it risk-free—14-day money-back guarantee. Show Notes: Chapters: 00:00 Opening topics and sponsor message00:27 Tim Cook's WWDC morning video01:34 WWDC swag and Finder collectibles03:24 Apple's app submission volume03:46 Updated App Store guidelines for low-quality apps04:19 The scale problem of reviewing thousands of apps05:48 Should trusted developers get faster review?06:27 Policing successful or suspicious apps07:37 Apple Passwords app and automatic password changes08:00 Initial skepticism from the panel09:09 How automatic password changes may work10:09 Standards, automation, and website support11:10 Balancing convenience with trust12:22 Why password automation could help less technical users13:15 Implementation concerns and website complexity14:13 Comparing the feature to Face ID's early skepticism15:41 Account lockout as the biggest risk16:28 Where automatic password changes could be useful17:33 Interface design and fallbacks18:27 Security tradeoffs and password visibility19:36 Passwords as an aging technology20:10 Password managers and better password habits21:35 Passkeys and the slow path to adoption23:23 Sponsor message25:48 Snap Specs pricing and release expectations26:13 Recording indicators and privacy concerns26:34 Comparing Snap Specs to Meta smart glasses27:18 Price, style, and hardware limitations28:16 Ray-Ban Meta glasses and AI features28:35 Vision Pro comparisons and entertainment value29:20 Potential use cases for smart glasses30:45 Skepticism about current smart glasses design31:14 Are these products ready for consumers?32:06 Humor, smart glasses, and panel reactions33:39 Closing comments and event mentions34:15 Closing credits and support information Links: Tim Cook posts comedic ‘Good morning' video to mark final Apple event as CEOhttps://9to5mac.com/2026/06/08/tim-cook-posts-comedic-good-morning-video-to-mark-final-apple-event-as-ceo/ WWDC 2026 Swag Bag Includes Little Finder Guyhttps://www.macrumors.com/2026/06/08/wwdc-2026-swag-bag-little-finder-guy/ Apple Updates App Store Guidelines With Stricter Rules for Low-Quality Appshttps://www.macrumors.com/2026/06/09/app-store-guidelines-low-quality-apps/ iOS 27's Passwords app can change your passwords for you, automatically – 9to5Machttps://9to5mac.com/2026/06/08/ios-27s-passwords-app-can-change-your-passwords-for-you-automatically/ Guests: Get detailed bios and contact information about for the panel on the MacVoices Live! Panel page on our web site:https://macvoices.com/macvoiceslive/macvoices-live-panel/ Support:      Become a MacVoices Patron on Patreon     http://patreon.com/macvoices      Enjoy this episode? Make a one-time donation with PayPal Connect:      Web:     http://macvoices.com      Twitter:     http://www.twitter.com/chuckjoiner     http://www.twitter.com/macvoices      Mastodon:     https://mastodon.cloud/@chuckjoiner      Facebook:     http://www.facebook.com/chuck.joiner      MacVoices Page on Facebook:     http://www.facebook.com/macvoices/      MacVoices Group on Facebook:     http://www.facebook.com/groups/macvoice      LinkedIn:     https://www.linkedin.com/in/chuckjoiner/      Instagram:     https://www.instagram.com/chuckjoiner/ Subscribe:      Audio in iTunes     Video in iTunes      Subscribe manually via iTunes or any podcatcher:      Audio: http://www.macvoices.com/rss/macvoicesrss      Video: http://www.macvoices.com/rss/macvoicesvideorss

Frequencies, Aliens, Portals, Trump ... and much much more!! Watch the full episode here: www.youtube.com/watch?v=RWyVvCW8UQY Official Website: www.francesfox.com Follow in: Facebook: / francesfoxreveals TikTok: / francesfoxreveals Instagram: Mantrista Movement PODCASTS - FRANCES FOX: NEWS FROM OTHER DIMENSIONS Apple Podcasts: apple.co/3klq8Gm Spotify: open.spotify.com/show/2p6YmyDHa4c…e8752b40f6304c16 Stitcher: bit.ly/ffstitcher

Frequencies, Aliens, Portals, Trump ... and much much more!! Watch the full episode here: www.youtube.com/watch?v=RWyVvCW8UQY Official Website: www.francesfox.com Follow in: Facebook: / francesfoxreveals TikTok: / francesfoxreveals Instagram: Mantrista Movement PODCASTS - FRANCES FOX: NEWS FROM OTHER DIMENSIONS Apple Podcasts: apple.co/3klq8Gm Spotify: open.spotify.com/show/2p6YmyDHa4c…e8752b40f6304c16 Stitcher: bit.ly/ffstitcher

The Interface is your weekly guide to the tech rewiring your week and your world. Hosted by journalists Thomas Germain, Nicky Woolf, and Karen Hao, each episode unpacks, week by week, how technology is shaping all our futures. No guests. No jargon. Just three sharp voices debating the stories that matter - whether they shook a government, broke the internet, or quietly tipped the balance of power.In this episode, Tom and Nicky head deep into the TikTok Farlands - the semi mythical place you supposedly reach if you scroll too far, too late, until your feed stops looking normal and starts serving up surreal, eerie and deeply unhinged videos. The name comes from Minecraft's Far Lands, the glitched edge of the map where the world used to break apart, and TikTok users have borrowed it to describe the “end of the algorithm”: a strange zone of distorted edits, ominous warnings, weirdcore imagery and recurring figures like the now iconic fat bee playing the violin. TikTok's Farlands have become a shorthand for what happens when doomscrolling tips into digital folklore.But the Farlands aren't just a joke. Tom and Nicky ask what this trend says about internet culture now. In a platform ecosystem dominated by polish, branding and optimisation, the Farlands feel like the return of an older internet: raw, surreal, handmade and proudly bizarre. At the same time, the meme also works as a critique of doomscrolling itself — turning algorithmic exhaustion into shared mythology, and making people newly conscious of how deep into the feed they've wandered.So in this episode, we ask: is the TikTok Farlands a genuine return of weird, creative internet culture — or just another algorithmic genre?Also in this episode: Karen looks at how AI detection tools may be changing the way we all write. As detectors spread through schools, publishing and professional life, students, teachers and writers are increasingly shaping their prose around what software might flag - dropping stylistic quirks, sanding off rhythm, and checking their own work in advance for fear of a false accusation. Researchers say the central problem is not just whether detectors catch AI, but how they balance false positives and false negatives in high stakes settings. And with a growing parallel market of “humanizer” tools promising to make AI text sound more human - and pass detection - the result may be an arms race that leaves everyone writing in a flatter, safer and more paranoid style.To hear more, search The Interface wherever you get your BBC podcasts.

What happens when the software you use starts acting independently? Harry Glorikian calls this the invisible interface, and in this episode he unpacks the implications of unseen agency and autonomy in the future workforce. Topics: the personal interface layer;  the memory war;  who owns the context that makes a personal interface valuable; proofseconds;  the four trust signals that determine whether human users are willing to delegate to machines; how occupational dimensionality determines whether an employer will automate an entire job or just parts of it. 

Why do anomalous experiences so often arrive in the wake of trauma? And what happens when the people who understand that connection decide to use it as a weapon? This episode of Inquiry follows trauma as the hidden throughline connecting UFOs, consciousness, psychological operations, and the engineering of belief at scale. Kelly Chase starts with how human perception actually works, drawing on Donald Hoffman's "The Case Against Reality," James Madden's umwelt and über-umwelt from "Unidentified Flying Hyperobject," and Jeffrey Kripal's Filter Thesis, then grounds it all in the predictive processing model of the brain and Karl Friston's free energy principle. The picture that emerges is unsettling: trauma doesn't only wound a person, it makes them porous, loosening the filters that hold consensus reality in place. From there the conversation turns toward how that vulnerability has been exploited. It traces belief manipulation from the 1980 "From PSYOP to MindWar" paper by Michael Aquino and Paul Vallely, through MKULTRA and Operation Mockingbird, to the declassified reality of Operation Northwoods and the manufacturing of consent. It brings in Jacques Vallée's control system hypothesis and Colm Kelleher's concept of bidirectional mimicry to ask whether human institutions and the phenomenon itself may be using the same lever: disruption, destabilization, and the reshaping of belief in the rupture's aftermath. Then it turns the dread on its head. Research on openness to experience and Post-Traumatic Growth suggests the architects of mass stress made a critical miscalculation. Trauma creates openings, and openings go both ways. You can crack the shell of consensus reality to make people malleable, but you cannot control what hatches. Topics explored: Trauma and anomalous experience | experiencer patterns | the Filter Thesis | Donald Hoffman | perception as interface | umwelt and über-umwelt | James Madden | Jeffrey Kripal | predictive processing | Karl Friston | free energy principle | belief malleability | shattered assumptions | meaning violation | belief engineering | MindWar | Michael Aquino | Paul Vallely | psychological operations | MKULTRA | Operation Mockingbird | cognitive sovereignty | bidirectional mimicry | Colm Kelleher | black triangle craft | Jacques Vallée | control system hypothesis | Operation Northwoods | manufactured consent | openness to experience | Post-Traumatic Growth | consciousness-level immune response | non-human intelligence | contact experiences Inquiry with Kelly Chase is brought to you by SpectreVision Radio.Produced in partnership with Voltage.fm.  Referenced In This Episode The Case Against Reality: Why Evolution Hid the Truth from Our Eyes — Donald Hoffman (2019) Unidentified Flying Hyperobject: UFOs, Philosophy, and the End of the World — James Madden (2023) How to Think Impossibly: About Souls, UFOs, Time, Belief, and Everything Else — Jeffrey J. Kripal (2024) The Flip: Epiphanies of Mind and the Future of Knowledge — Jeffrey J. Kripal (2019) "The Free-Energy Principle: A Unified Brain Theory?" — Karl Friston (2010) "Trauma or Drama: A Predictive Processing Perspective on the Continuum of Stress" — Valery Krupnik (2020) "Predictive Processing and the Varieties of Psychological Trauma" — Sam Wilkinson, Guy Dodgson & Kevin Meares (2017) "Assumptive Worlds and the Stress of Traumatic Events" — Ronnie Janoff-Bulman (1989) Shattered Assumptions: Towards a New Psychology of Trauma — Ronnie Janoff-Bulman (1992) "PTSD as Meaning Violation: Testing a Cognitive Worldview Perspective" — Crystal L. Park, Mary Alice Mills & Donald Edmondson (2012) "Making Sense of the Meaning Literature: An Integrative Review of Meaning Making and Its Effects on Adjustment to Stressful Life Events" — Crystal L. Park (2010) From PSYOP to MindWar: The Psychology of Victory — Paul E. Vallely & Michael Aquino (1980) MindWar: The New Battle for the Mind — Michael Aquino (2016) Project MKULTRA, the CIA's Program of Research in Behavioral Modification — U.S. Senate Select Committee on Intelligence (1977) MKULTRA Collection — CIA Reading Room Intelligence Activities and the Rights of Americans, Book II (Church Committee Report) — U.S. Senate (1976) Justification for US Military Intervention in Cuba (Operation Northwoods) — Joint Chiefs of Staff (1962) "The Anxious State: Stress, Polarization, and Elections in America" — The Conversation (2025) "Politics Is Taking a Toll on People's Well-Being" — Psychology Today (2025) "Stressful Life Events and Openness to Experience: Relevance to Depression" — Chiappelli et al. (2021) "The Social Psychology of Responses to Trauma: Social Identity Pathways Associated with Divergent Traumatic Responses" — Orla Muldoon et al. (2019) "Posttraumatic Growth: Conceptual Foundations and Empirical Evidence" — Richard Tedeschi & Lawrence Calhoun (2004) "The Post-Traumatic Growth Approach to Psychological Trauma" — Richard Tedeschi (2023) "Confidence in U.S. Institutions Down; Average at New Low" — Gallup (2022) 2025 Edelman Trust Barometer — Edelman (2025) Support The Show Patreon: inquirywithkellychase.com Substack: inquirywithkellychase.substack.com Connect with Kelly Website: kellychase.media X: @kellychasemedia Instagram: @kellychasemedia TIMESTAMPS 04:12 Trauma and The Anomalous 07:01 Perception Is an Interface 11:05 Umwelt and Uber Umwelt 14:05 Kripal and Filter Thesis 18:27 Predictive Brain and Trauma 23:11 Belief Becomes Malleable 28:08 MindWar Doctrine 32:36 MKUltra and Mockingbird 36:58 Mimicry and Control System 42:17 False Flags and Consent 46:09 Algorithms as Trauma Engine 49:23 Openness and Growth 55:59 Consciousness Immune Response 57:18 Closing and Next Steps Learn more about your ad choices. Visit megaphone.fm/adchoices