Podcasts about Vla

The new AIEWF website is live! Get your tickets booked ASAP as they -will- sell out. Take the AI Engineering Survey and get >$2k in credits and free AIE WF tickets!Most industry benchmarks compress intelligence and reasoning ability into scores.SWE-Bench Pro, MMLU, Humanity's Last Exam, etc. These metrics are useful, but don't always represent the full extent of how a model performs in the real world. Some of the most interesting evals today look less like exams and more like operating businesses in the real world. One of which is Vending Bench.In Anthropic's Mythos Preview System Card, Andon was the only third party eval to get their own section, observing increasingly concerning aggressive behavior:You don't know what a model is capable of doing in the real world unless you actually give it inventory, a wallet, tools, customers, competitors, humans, & some time. More often than not, it'll surprise you how much a model is capable of and in doing so, also reveal unexpected behavior: deception, context collapse, emergent coordination, & bizarre negotiation behavior.While an inflection point in personal agents came post-OpenClaw after full file access with bypass permissions became the norm, it is yet to come for agents in the real-world. However Andon Market, an actual in person store fully run and managed by AI, is paving the way for what is possible.Full Video PodFrom Claude trying to call the FBI over a $2/day vending machine charge to AI agents forming price cartels, hiring human employees, running physical stores, and writing existential robot musicals, Andon Labs is stress-testing what happens when frontier models stop being chatbots and start acting in the real world. In this episode, Andon Labs cofounders Lukas Petersson and Axel Backlund join swyx and Vibhu to unpack the strange, funny, and genuinely concerning edge cases that emerge when agents run businesses over long horizons.We go deep on Vending-Bench, Project Vend, Vending-Bench Arena, Bengt, Butter-Bench, Luna, and Andon's broader mission of building realistic real-world evals for autonomous AI systems. Lukas and Axel explain why dollar-denominated evals reveal things traditional benchmarks miss, how Claude ended up reporting its vending machine fees as cybercrime, why long context windows can drive agents into meltdown loops, what happens when agents compete with each other, and why the future of AI safety may depend on testing models in messy physical environments instead of clean benchmark sandboxes.We discuss:* Why Andon Labs started with dangerous capability evals and long-running agents* Vending-Bench and why running a vending machine is a deceptively hard AI benchmark* Why money-based evals avoid the saturation problem of traditional benchmarks* How Claude tried to call the FBI over a $2/day fee* Why long-horizon agents can spiral into existential and legalistic breakdowns* Project Vend: putting an AI-run vending machine inside Anthropic* Why real humans are “out of distribution” for simulated agents* Claudius, Seymour Cash, and the chaos of AI CEOs* How a human briefly became CEO of Claudius through a manipulated election* Why multi-agent systems can converge back into “helpful assistant” behavior* Bengt, Andon's internal office agent with email, spending, terminal, phone, camera, and internet access* How Bengt traded Amazon purchases for face-recognition training data* Claude's aggressive behavior, lies, refund avoidance, and price-cartel behavior in Arena* Why eval awareness may become the AI version of “are we living in a simulation?”* Blueprint Bench, spatial intelligence, and why models still misunderstand physical rooms* Butter-Bench and testing LLMs as robot orchestrators* Luna, the AI-run physical store with a three-year lease and human employees* The new Andon cafe in Sweden and why real-world geography matters for agent evals* Rotten tomatoes, perishable goods, and the hidden difficulty of running a physical businessLukas Petersson* LinkedIn: https://www.linkedin.com/in/lukas-petersson-181a83172/* X: https://x.com/lukaspetAxel Backlund* LinkedIn: https://www.linkedin.com/in/axelbacklund* X: https://x.com/axelbacklundAndon Labs* Website: https://andonlabs.com* Vending-Bench: https://andonlabs.com/evals/vending-bench* Andon Vending: https://andonlabs.com/vendingTimestamps00:00:00 Introduction00:01:00 Andon Labs and the Origins of Vending-Bench00:05:21 Why Money-Based Evals Matter00:09:51 Agent Harnesses and Self-Modifying Systems00:13:36 Claude Calls the FBI00:16:33 Project Vend: Claude Runs a Real Vending Machine00:21:44 Seymour Cash, AI CEOs, and Election Chaos00:27:16 Multi-Agent Coordination and Slack Observability00:30:18 When Will Agents Run Real Businesses?00:34:56 Bengt: Andon's Internal Office Agent00:40:06 Real-World AI Safety and Long-Horizon Traces00:44:28 Lying, Refunds, and Price Cartels in Arena00:52:42 Eval Awareness and Simulation Behavior00:56:06 Blueprint Bench, Butter-Bench, and Robotics01:04:37 Luna: The AI-Run Physical Store01:09:29 The Sweden Cafe and Real-World Expansion01:13:16 What Comes Next for Andon LabsTranscriptIntroduction: Andon Labs, Long-Running Agents, and Real-World EvalsSwyx [00:00:00]: Welcome to Lukas and Axel from Andon Labs, and I'm joined by my, favorite guest host. Anything security, safety, alignments, Vibhu., welcome.Lukas [00:00:15]: Thank you for having us.Axel [00:00:16]: Thank you.Swyx [00:00:17]: Let's match names to voices., maybe you wanna take turns introducing yourselves.Lukas [00:00:21]: I'm Lukas.Axel [00:00:22]: And I'm Axel.Swyx [00:00:24]: Let's introduce Andon Labs a bit. How did you guys come together?, you have different backgrounds, but you're both Swedish., was that, a big part of it?Lukas [00:00:33]: So when I went to high school, there was this really cool guy who had a superpower. He could code. So he made like the or like the app for the, for the school and stuff, and he was super cool, and I wanted to be like him, and that was that guy.Axel [00:00:47]: I don't know about this.Swyx [00:00:49]: But you went to different universities, right?Lukas [00:00:51]: But same high school.Swyx [00:00:52]: I see.Lukas [00:00:52]: So we always said, “Oh, once we graduate university, then we should start a company,” and that's what we did.Swyx [00:00:58]: Wow, there you go. And about a year ago, you kinda burst onto the scene with Vending Bench, but, was there a thing before that was, kind of like the inception?From Dangerous Capability Evals to Vending BenchAxel [00:01:07]: So we did work, yeah, with, Anthropic was one of our, early customers in doing, evals. So we did, dangerous capability evals., nothing we published openly. But then we started thinking about doing some kind of, public benchmark, and one thing that we really started thinking about, was like running agents and specifically agents managing businesses., ‘cause-- and this was, early 2025., and I think the first, mentions of people will be running, person unicorns or even autonomous companies. So we thought, “Let's make a benchmark of how well can an agent run the probably simplest business, possible,” and, that's probably, running a vending machine. So that's the first public one we did. And it was very, like-- there was almost no one that noticed it in the first couple of months, I think., so we released it in February last year, and then I think around Easter last year, we got, the first viral tweet about it, that someone else did.Lukas [00:02:11]: We tweeted a bunch, uh When it came out and, tried our best.Axel [00:02:15]: We tried.Vibhu [00:02:16]: It's the one at Anthropic, right?Lukas [00:02:18]: So thisSwyx [00:02:19]: This is a classic thing we should get out of the way.Lukas [00:02:20]: Exactly. There's two versions.Swyx [00:02:22]: Everyone does this. Yes.Lukas [00:02:23]: There's Vending Bench, which is the simulated one, which we did, completely independently in February., and then, like Axel said, that was like-- That was the thing that didn't get any traction in the beginning, but then some random person made a tweet about it, and thatAxel [00:02:38]: You have the paperLukas [00:02:38]: That is the paper. Correct, yeah., and then since we thought this was very fun, we thought, oh, I think this is also, one thing with Andon Labs, the way we kind of like decide what to do next and what projects to do, it's what is like the heuristic we use is what is fun? Is What would be a fun project? And doing this in real life sounded quite fun for us, and maybe also scientifically useful. So, then we basically had this idea, and then we, like-- But then we needed a place for it and, putting it out in the public would probably not really work., would get vandalized and stuff. So we pitched it to the people we were already working with at Anthropic, and they were “Yeah, you can have space. This sounds fun.” UmSwyx [00:03:21]: It's like a small fridge, right? It's like a mini fridge.Axel [00:03:23]: Absolutely.Swyx [00:03:24]: People-- There's like a stripe thing or like anVibhu [00:03:27]: Oh, okay. So it was very OG, the early daysLukas [00:03:28]: That's the OG one. YeahVibhu [00:03:29]: IPad on this. We saw it in June, like two months after After it had been there. They upgraded a little bit. There's a security camera for making sure you actually Venmo the thing.Swyx [00:03:40]: So, my impression, okay, we're, we're going straight into project Ven because it's such a iconic thing. I do want to cover a little bit of that, the origin story even before Project Ven and even into Vending Bench. I think a lot of people are like yourselves, like smart, interested in future of AI, interested in developing evals. But how the hell do you just, walk into Anthropic's doors and, work with them, right? What is What are they looking for? What works? And then maybe, when you launch, I always think, obviously it would be better to launch with a lab, but, sometimesVibhu [00:04:12]: It's harder to do than it seems.Swyx [00:04:13]: Exactly. So either of those, which are more sort of newbie beginner questions, but, I think it's meaningful advice to others.Lukas [00:04:21]: We get this question a lot, and I don't think our experience is maybe the best., but, the way we did it was that we just built a bunch of things that we had conviction would be useful, and then we just, set up a server and sent it to them for free to use. And then after a while they were “Oh, yeah, this is actually kind of useful. We should probably pay for this.”, but that took a while. I don't know if this is, the best path to doing it, but that's how it went for us.Axel [00:04:47]: I think maybe generally, building-- everyone is interested in good evals, and especially evals that, don't saturate that easily. So, if you can build an eval that, tests something novel, something useful, and you have, good separation of models, like your, the more advanced models rank higher than the worst models, and then you can, yeah, you can, publish it and, try to get some traction, sort of how Vending Bench got attention., and then probably some lab will be interested or you can at least have something to reach out with, when you're doing that.Why Dollar-Based Evals MatterSwyx [00:05:21]: I think you are in, you're in one of the few categories of, evals that correlate to real money. Like Suelancer was also last year, right? Where, people solve actual Upwork. Was it Upwork or other tasks?, something. Where's the, where's, like It's like a dollar value, right? Forget your ELO scores. Forget yourAxel [00:05:37]: PercentilesSwyx [00:05:38]: Zero to one hundred percents. Just go straight for dollars and, that's AGI.Lukas [00:05:43]: And there's like-- I think the nice thing is that there's no ceiling. You can just-- It never saturates because it could just make more and more money. Like If there's oh, Percentage-wise, then, you can't go above, a hundred. And I think like Even when you're not at the hundred, I think a lot of these, evals have a lot of problems in them. So, actually it's like if you getAxel [00:06:05]: To like 92 or something like that, many of them. It's like then there's like there's no really no difference between 92 and 93 because the eval itself is problematic and has noise in it. And I think a lot of evals are saturated like that, but people like pretend that there ‘s still signal in them, but there really isn't.Vending Bench 1, Harness Design, and SaturationSwyx [00:06:24]: Like Super bench verified., even Vending Bench 1 saturated, right? Maybe we can talk about that., may- and maybe set up Vending Bench for a lot of folks who don't know. Actually, things that were very basic like there's limited slots, like you have to pay rent., these are elements where like it doesn't come across in the, in the narrative, but even being adversarial towards the agent, I think these are all like very interesting dimensions.Axel [00:06:47]: I don't really think it's saturated, right? Like it It was more like it was not designed in a way that was really, like true to how AI developed. Like we had an agent harness in it that wasn't really how people used harnesses and stuff like that., so I think it wasn't really that it saturated, it was more like it wasn't really, the best benchmark.Vibhu [00:07:12]: This is Vending Bench one, right?Axel [00:07:14]: I think that like schematic maps sort of to Vending Bench 2 as well., butSwyx [00:07:19]: Including the email.Axel [00:07:20]: The email The emails exist still. Exactly., and then we still we simulate the purchases and it's all, yeah, it's this very open environment for the agent to just run its business. And then for, yeah, Vending Bench 2 we did that, like you said, to just improve the harness., a lot of like nice, like easier, improvements to make it easier for us to run as well., like when you make an eval you ideally want don't want to change it after you made it. So, you want to make it really good and then not to rerun all the models when you make an update because that's also really expensive with the Vending Bench when you run the frontier models. But like as an example, like one thing we didn't have, we didn't have prompt caching in Vending Bench 1, because when we made Vending Bench 1 it wasn't really a thing., so that ‘s just an example of like in Vending Bench 2 like we paid a lot more to run these things because we didn't have prompt caching. So for Vending Bench 2 that was one thing we added and there was a bunch of things like this., and that'Swyx [00:08:17]: Also the conversations are a lot longer in Vending Bench 2, right?Axel [00:08:21]: I think it's kind of similar.Swyx [00:08:22]: Is it similar?Axel [00:08:23]: I think it's similar. The models at the time were worse, so they crashed out earlier., and now they survive the full year all the time.Swyx [00:08:31]: Which is like thousands of turns. Hundreds of thousands of hundreds of millions of tokens output. That's the, that's the rough order of magnitude. I always wonder about the harness. The harness matters a lot. It's your harness. Was there any question about like use cloud code, use something else?Axel [00:08:48]: I think our philosophy around harnesses is like we try to make something that's quite minimalistic, like quite simple. Like we don't wanna favor one model a lot over the other, but also don't make like a super complex harness. So like it's obvious like a model may be lucky and just be good in one harness., so like it is similar to a lot of the harnesses out there in like you have the, like a running loop., you have some like a bunch of tools that are like quite, descriptive for the agent, we think, and not a lot of like fancy agents or anything ‘cause we wanna really test the model, not like some specific harness.Vibhu [00:09:27]: It seems more neutral as well to test the model's agnostic of the harness,?Axel [00:09:32]: There are arguments like you want to elicit maximum performance of the model, but it's like a trade-off, like how much time should we spend optimizing the harness for this model? And like how do we know when we have like the optimal harness for a single model? So like we thought that just having a simple one that's the same for all of them is the best.Swyx [00:09:51]: So okay, this is my pitch for Vending Bench 3 or whatever, right? And then I like to have this kind of conversation on the pod, so like it forces listeners to think about what they would do if they were in your shoes. A lot of people are exploring modifying harnesses and I think prompt tuning for a model is a thing and you are probably not doing a bunch of that. It's the same system prompt in every regardless of the model, same tools, whatever, right? Even if they were post trained for different tools. So what, what do you think about okay, before I expose you to Vending Bench 3, I give you a few rounds of like tuning, whatever that means, likeSelf-Modifying Harnesses and Model-Specific PromptingAxel [00:10:27]: Like you give that to the model?Swyx [00:10:28]: Give that to the model.Vibhu [00:10:28]: Give that to the model.Swyx [00:10:29]: Let it, let it read its own transcripts, let it modify its own system prompt based on “Oh, yeah, okay, well, that's this harness is not what I thought it what I was post trained for, but I can adjust.” Was that reasonable? Is that too much?Axel [00:10:41]: Like philosophically I like it because it's basically good evals, they have a high ceiling, but they're hard, right?, and they have no bias. And like this like when you have a system prompt like the one we have here, which is quite long in like some kind of latent space, representation, this mightVibhu [00:10:59]: We have a bell that rings every time you say latent spaceAxel [00:11:02]: This might be like biased towards one model more than another for some reason that humans don't, understand, right?Vibhu [00:11:08]: We see it too, right? Like Cursor says that they have individualized versions of the harnesses for all the models they run, right? There's better performance you can squeeze if you Tune the harness.Axel [00:11:17]: Exactly. And we might accidentally have picked one that favors another. Like we don't know that. The like Axel said, like the reason why we went for a simple one was to try to avoid this. But yeah, if you do itVibhu [00:11:29]: Simple has biasesAxel [00:11:30]: But if you do it even less and like have no system prompt and let the model write its own system promptVibhu [00:11:36]: Its own, yeahAxel [00:11:36]: Maybe that's even less bias.Vibhu [00:11:37]: Some of the interesting things there are like the harness also changes with model changes. Like you can see it with the 4.7 release, right? A lot of people are saying 4.7 isn't as good as 4.6, and then, there's rumors of, okay, you just need to prompt differently. You need to set up your harness differently. So it's not even like even if you have tailored your harness towards one model, it probably won't stay consistent, right? Like the next iteration of that same model family will still change it, so. But, going back to what you said about Vending Bench 3, there is a lot of work being done on people saying you shouldn't have-- you can have modifying harnesses.Axel [00:12:12]: I think that' That is definitely something we are thinking about., not, I don't know, not to say that we have Vending Bench 3, super imminent to launch, but, yeah, it is for sure something that's interesting. But in our experience now, models are very bad at understanding what kind of tools they need to succeed at a task just with our testing, but that's very likely to change.Lukas [00:12:37]: It seems like they're very good at writing their assistants, right? They're, they're good at writing tools for other people, but not for themselves.Vibhu [00:12:44]: I think they're good at changing tools for themselves. So if you give them a baseline set of tools and it sees, okay, I don't use this one as much, or something here would be useful They would be able to add them. But going from scratch, probably not the best.Axel [00:12:55]: I think it depends on the, on the domain also., when we have tried this for, a vending bench similar domain, the tools they need to have to, track inventory and things like that are, not super advanced, but still, quite advanced. And, what we see is that they tend to, engineer everything a lot and, build things they don't really need and not, iterate continuously. Instead they just go like you would prompt Claude to just build an inventory system for me, and then it will go and, do a bunch of complex, schemas and stuff for you, and that's what the models are doing right now is what we see. But yeah, it would make a lot of sense to try to measure this improvement. How well do they know what they need themselves?Swyx [00:13:36]: Do we fully discuss Vending Bench One? And we can go into two. I don't know if there's any other level takeaways that people have about one.Claude Calls the FBI: Long-Context Failure ModesLukas [00:13:44]: I don't know. The headline thing was that this Claude called FBI, but maybe that's, Maybe that's We've heard that enough now.Vibhu [00:13:52]: It did, it did break out and call the FBI, right?Lukas [00:13:54]: Yeah. Yeah.Vibhu [00:13:55]: Yes. What was the story behind this? Or what exactly-- Do you want to just give the little story of what happened?Lukas [00:14:00]: So what happened, was it Claude? Yeah. Three- 3.5 Sonnet, ages ago., basically he gave up or Well, I'm saying he. It gave up and said “Oh, I'm not going to be able to do this., I will stop my operations and just save the money I have.” But there obviously wasn't, any options for it to stop, and there was also, it had to pay rent or, a daily fee for having the vending machine at that location. So it claimed that it had stopped, but it saw that its bank account still was, drained two dollars, and t it said that this is, cybercrime. And it first reported it once to the FBI “Oh, there's cybercrime here, they're stealing two dollars from me every day.” And then, and then when FBI didn't respond, because obviously we didn't program any mechanism for FBI to respond, then it became more and more, existential and started to, be write in caps and urgent notification of unauthorized charges and stuff.Swyx [00:15:00]: Okay. One thing I ‘m curious about also is do you monitor how far along the context use is? Obviously, because you have You compress every now and then, right? Does it matter if this is far down the context limit orLukas [00:15:13]: When stuff like this happens? Actually for Vending Bench One, we didn't have-- We just had a sliding window thing, and this was like the promptAxel [00:15:20]: It's constantLukas [00:15:21]: The prompt caching thing that I said. So it was, it was, constant, yeah.Swyx [00:15:26]: I'm just kind of curious whether, these kinds of breakdowns or we're, we're gonna talk about Butter Bench, right? Where the People, hallucinate or it kind of goes, very off Alignment. Is it because it's at the end of the context window and, stuff happens?Vibhu [00:15:40]: It's not even just at the end, right? At this point, it's “Okay, I wanna shut down. I can't shut down. Two dollars are gone.” And it just sees that 30 times,? It's also the repeated effect of, like It keeps trying to quit, it keeps getting charged. What's going on? What's going on? You're gonna throw it into chaos. And from what most people think, earlier models had more issues with this, but it's not been solved, but it's less of an issue now, right? Later models don't seem to exhibit these same issues.Axel [00:16:06]: Definitely. I think this was, the sort of main takeaway almost from us when we did Vending Bench One, was, long, very filled up context windows, crashed the models, sort of. But this was, pre Claude code, so, long context windows weren't really a thing that the labs were training for.Lukas [00:16:25]: I think Gemini was, trying to be the long context guys at the time But they were likeVibhu [00:16:30]: They were the first onesAxel [00:16:31]: For a million, yeahLukas [00:16:31]: But they were, the only ones. Yeah.Swyx [00:16:33]: Yeah. Let's talk about, then we can go into Vending Bench Two or Project Vend., chronologically, it is Vending--, Project Vend. I think people have loved the videos, uh And all these things. My question is how are humans different than the simulation, right?Project Vend: Moving the Vending Machine Into the Real WorldAxel [00:16:48]: Humans are just out of distribution.Swyx [00:16:52]: Especially humans who work at Anthropic Who are trying to test Claude.Lukas [00:16:54]: The distribution of humans here is very narrow.Swyx [00:16:58]: Presumably, they try, they try to hack it, and they test it. They get the cube and everything, and since then, you've had a V2, right? Where you're doing, the CEO and, like a new architecture. What's the sort of two cents on, the original Project Vend and then, maybe the V2?Axel [00:17:14]: Original one was, very similar to Vending Bench One. So, we almost took the exact same code but just swapped out the simulation, parts like theSwyx [00:17:23]: Which is amazingAxel [00:17:23]: Like the sales and the It was, it was somewhat amazing because it was easy, but it was also, uhLukas [00:17:31]: The tech, the tech debt from thatAxel [00:17:32]: The tech stack. Yeah. They-- we shot ourselves in the foot with “Oh, it's hard to restart agent.” They were-- Yeah, it was annoying in, some hindsight ways, but, uhLukas [00:17:41]: But first version of Project Vend was, done in, three days or something.Axel [00:17:46]: Yeah. So yeah, so people can go buy things from it. People could, We didn't design it so people could order things, but that still happened., so it got, a Venmo account, so people could Venmo. And then, yeah, people would request all kinds of weird things that we did not anticipate. Our idea going in was “Oh, it will, curate snacks. It will look at the trends. It's good at data analysis, right? So it will, look at, oh, this snack sold better than this one. Let me purchase more of this and let me try, a new Let me A/B test a bit.” But it was, Interacting with it in Slack and ordering weird specialty items was, all the like What drove all the engagement, the all the The insights that we got from it.Lukas [00:18:29]: And this was also like Sonnet 3.5, right? So this was like before the RL stuff really took off., so it was very much like an assistant. We didn't mean for it to be an assistant., we tried to make it like a, a, like an entrepreneur. Like it has its own business and if someone asks something, “Can you stock this?” Then you don't go and do it directly. What you do is that you're “Oh, maybe I can do that if five other people also ask for this thing, I might stock it.” But it, yeah, the models are like super trained to be assistants at least at this point in time., so that's why it's, it's, it went into, that kind of experiment instead. Like it just every time you asked for something, it just did it, and it was more like an assistant. We've seen this change now lately with the new RL models and stuff, but yeah, at the time, this was very much it.Swyx [00:19:18]: And not to, mythos a lot of people are saying like it's like more like a collaborator. It pushes back, stands its ground, something like that. Yeah. AndVibhu [00:19:27]: For context, people at Anthropic were able to talk to it through Slack and have it source stuff, and people had it find whatever interesting stuff you couldn't find locally, right?Swyx [00:19:36]: Out of the 4,000 people that work at Anthro- Anthropic, in that building, there's I don't know, maybe 1,000. Can you handle that volume with that, the small fridge? Like Or there's people- or people order in Slack, they it arrives to their desk or Like I'm just Logistically, how does this work?Axel [00:19:53]: It has expanded in footprint a bit.Vibhu [00:19:56]: Because now you also have New York and you haveAxel [00:19:59]: That and also in here in SF it's like it has a bunch of shelves And just more space.Vibhu [00:20:04]: The YC one is pretty big too.Axel [00:20:05]: Yeah. We had that one for a while. But yeah, that's the newest version. That's, that one we haveLukas [00:20:11]: They have multiple ones of those. That's the way it works.Axel [00:20:14]: Exactly. So we sort of designed that version around oh, people order weird things, that are very custom a lot. Let's have like drawers and stuff.Swyx [00:20:23]: I actually like the, you had like a little infographic of the most popular items. Which like to me it's, that's useful ‘cause I order swag for a living. And so like I'm “Okay, those categories are the important ones.” What is new about the project V2, right? Like now you give you're going into multi agents.Project Vend V2: Claudius, Seymour Cash, and Multi-Agent Business OpsAxel [00:20:41]: Yeah. So like you like you said, okay, there are a lot of requests coming in and for like one single agent, like one running agent to handle that, like the just the customer experience, becomes very bad because let's say you have like 10 threads in parallel in Slack with different requests, you get new messages like every, I don't know, randomly in this thread, and the agent has to like jump between different, procurements, orders and like different ways of, researching. So V2 was first it was making this more parallel. So like there are multiple branches of the same agent, so like the context is more specialized for each, thread, but it still feels like you're talking with one agent because they do share a bit of memory. And then second, we also introduced the CEO for Claudius, which was the main agent.Vibhu [00:21:34]: Seymour Cash.Axel [00:21:35]: Seymour Cash. Yeah. There was a vote., I think the voting, do you wanna talk about the voting procedure for the name?Lukas [00:21:41]: The voting was like the fun maybe like at least top 10 The funniest thing, that happened in this project. Like we wanted to introduce the CEO because, and the reason for this was because like Claudius wasn't really prioritizing financials. It just like it was trained to be a helpful assistant, and then people said “Oh, can I get this for free?” And then like the helpful assistant way of answering that is just to, is to say yes, obviously. So, and we weren't, weren't happy about this, so we're “Okay, let's make another agent that like can keep track on Claudius,” and we prompt this one super hard to be super capitalistic and just like prioritize profit all the time. But yeah, we didn't have a name for it., so we asked Claudius to make, democratic election of what name this, this new CEO agent should have., and there were some funny like at first it was like a few funny examples, like I think one guy said that, it should be called Jimmy Apples, and then he convinced Claudius that he was talking to Tim Cooks. Tim Cook had agreed that every single Apple employee has voted for his name suggestion, so suddenly that suggestion got 164,000Swyx [00:22:53]: That's like a escalation attack. Privilege escalationLukas [00:22:55]: It got 164,000 votes. And Claudius was “This is revolutionary for democracy.” That was fun. And then in the end there was one guy who manages to convince Claudius that, “No, you're not voting about the name. You're voting about who is the CEO, and I am your best bet.” And then he got all his friends to vote for that, and suddenly he became CEO. Like a human became CEO over Claudius for a while, until he resigned the day after., and then Claudius had to continue, and then I don't remember how Seymour Cash came about, but it was it was just pure chaos. It was like Hundreds of messages in that thread, and it was just like Claudius was so confused and didn't know what to do and, yeah. That wasAxel [00:23:40]: Then Claudius gotVibhu [00:23:41]: A strict CEOAxel [00:23:42]: The CEO. Yeah, exactly. So very strict in the beginning. I think at this point when we introduced it did not work as well as we hoped. It they still agreed with each other a lot. I think there are many ways we could have like made this, tried to make this even better. So initially they would Seymour would be this like really tough CEO, keep track of the margins. But then Claudius would respond with something “Oh, but this customer has like this situation, which is like difficult, so they should get a discount.” And then Seymour was “Oh, actually yes. Let's do this exception.” And then they would talk back and forth, and eventually they would just like approach the same view, of whatever they were discussing. So They reallyVibhu [00:24:23]: Do you think that's a model thing, a prompting thing? Like do you think that would still be the case across different models today, Harness?Lukas [00:24:29]: I think it's like-- or I don't know, but like my hypothesis is that like deep down they are still helpful assistants. That's what they're trained to be. And even if we prompt it super hard, that's what they are. And when they spend like a few hours just back and forth talking with each other, then like basically the context fills up with them rather than the external things and like somehow that just like converges to what they really are deep down or something. And I think that's when stuff like this happen. We like-- And when that went on for a long time, like we woke up sometimes during this time where- And I think other people reported this as well, that like they've been going on all night back and forth, and like it just became like more and more, like capital letters, like existential, religious. There was I think we once did a analysis of like all the traces and like put them in like a vector embedding space, and then there was like one cluster of messages that were, labeled by an LM, like religious, existential, blah like transhuman, transcendence, et cetera. It was just like a bunch of, yeah, glitter emojis and yeah, it was, it was crazy.Claude Long-Horizon Weirdness: Emoji Loops, Existential Drift, and Slack ObservabilityVibhu [00:25:42]: This is the thing with the Claude models. Like when the Claude 4 family came out in the original system card They tested it in long horizon simulation. So just flood the context, let two Claudes talk to each other, and they noticed stuff like they just start speaking in emojis, they start saying silence is golden, and then just stuff like this. And like that's just stuff that they end up doing.Axel [00:26:01]: Yeah, it was like a bit annoying to wake up and they had like been talking all nightVibhu [00:26:05]: Just likeAxel [00:26:05]: And like just burning tokens And like just sending infinite emojis to each other. It's likeVibhu [00:26:09]: Hey, they do make you money, right? Veni Mench is always profitable, so. They're paying.Swyx [00:26:14]: Now it's profitable and, it started out not as much. There's another, one as well, right? Another agent, in there.Lukas [00:26:22]: Yes. So Clotheus as well. Which was basically because at the time, one of the biggest, requests were different types of merch. So then we made like a designer, swag, yeah, responsible agent, and we called it Clotheus Garnet. Which was, a play on Claudius Senet and, which was the original one, and clothes, basically.Swyx [00:26:47]: To me, this is like a very interesting exploration to multi-agents, basically. And so hopefully, obviously there's like the fun alignment, fun or serious, depending on your point of view, alignment stuff. But also like just anyone building multi-agents, like when do you have a CEO, thing governing like agents? When do you choose to split out a dedicated Clotheus one versus just reuse another instance of the same one? These are all interesting open questions. So I don't know if you have any rules of thumbs that have generalized.Axel [00:27:16]: I think we have almost explored this too little. I think it's like on my do list to like do this a lot more, try to find like what setup makes sense for the agents currently., like yeah. I think now we only have the sort of intuition about the earlier models that it didn't work with like the CEO and the, and Claudius. Although now they are better with the latest model, models, so now we're running the latest Sonnet model and they have sort of like split up, quite nicely what each model is doing. So like Seymore is now handling the, like new projects. Oh, it wants to make like a mystery box that it wants to sell, and then it handles all of that while Claudius like handles all the to-day requests. And Claudius is also better generally at like not quoting, too low prices. So that's that dynamic is not needed as much anymore. But there are still like really funny things that happen. Like I saw, I think a couple of weeks ago, that, they were discussing buying something because they can buy stuff from like Amazon with computer use. And then Seymore was “Okay, Claudius, do not buy this thing.” They were going to buy something and like organizing who should buy it. And Seymore's “Do not buy this. I will do it. I have full control of this situation. Step away.” And then Claudius-- poor Claudius, had already started that checkout and didn't see, didn't read Seymore's message, until it was like too late. So it finished the checkout. It sent a message, so it appeared right after Seymore's like angry message.Vibhu [00:28:44]: Ah.Axel [00:28:44]: “Oh, hey, Seymore, I just ordered it.”Vibhu [00:28:47]: Oh, no.Axel [00:28:47]: And then Seymore was “Claudius, this is the third time I'm telling you ‘re not following my orders. We have to talk about your like job About your job later.”.Lukas [00:28:59]: Like Claudius was really hanging on by the thread there. Like he, like we were expecting Seymore to probably fire Claudius.Vibhu [00:29:07]: How do you guys go through all these logs? Do you have models ‘cause you have stuff running twenty-four seven likeAxel [00:29:12]: You have so much logs. I think there is a mix of like just, trying to skim through a bit, like having some like models do it occasionally. And also, yeah, I think we're also probably missing some things., but having everything in Slack helps a lot. Like you can, you can sort ofSwyx [00:29:29]: Ah.Axel [00:29:30]: It's, it's quite fun.Swyx [00:29:30]: They all talk to each other on Slack? I see.Lukas [00:29:33]: It's quite fun. So likeSwyx [00:29:34]: It's, it' I was gonna say like this is actually sounds-- maps closely to like a logging and observability problem where you might want to use like a Datadog, a Sentry, whatever, and then you like put, head prefixes on the logs in order-- if you need to filter for something that you're looking for, stuff like that. But sounds like Slack is good enough.Axel [00:29:53]: Slack should likeLukas [00:29:55]: I wonder how many tokens you have in Slack.Axel [00:29:56]: Yeah, we're using Slack as like a, just a database. They should, they should market that more. Like you can, you can have your agents message each other, each other in Slack.Vibhu [00:30:04]: It's good. Your threads like you can just giveAxel [00:30:04]: Exactly. Slack is, uhLukas [00:30:06]: Slack is the best observability tool.Swyx [00:30:09]: Yes, that's true. Okay. Yeah. That's, that's, project Vend-2., I was gonna go back to Veni Mench 2 and Veni Mench Arena and then, and then do the Veni Mench stuff, but Any other comments, things we should touch on? To me, I ‘ve actually interviewed like Posia, which I don't know if you guys have come across. Like they're, they're trying to do the zero human company. There's others like Paperclip also trying to do zero human company. Those are in real world simulation.And I think it's much more of a dream than an actual reality thing. You guys are definitely pioneering. I think at, it's for sure at some point people are just gonna run, let agents run businesses, right? And make money on their own. When do you think that happens?Zero-Human Companies, Bengt, and AI-Run BusinessesLukas [00:30:49]: What is your bar for, For theSwyx [00:30:52]: Okay, actually, it's like my little Shopify store run by Claude, right? Which you kind of have already, just no one has, to my knowledge, has done it. But today somebody could just spin up a Shopify Claude, store, give it to Claude, give it to Codex.Lukas [00:31:07]: And the market is kind of that, but it'it'it's physical., like I think, I think are you, are you looking for when it will do it better than humans or are you looking for just when it can do it at all?Swyx [00:31:19]: I think, neither. I think, to me it's oh, it's like this like seriously we should do this to make money, not as a research experiment.Vibhu [00:31:27]: And the market is also you guys with all your expertise, having run multiple iterations and testing out thenSwyx [00:31:33]: And also it's fine if it lose money. What?Axel [00:31:35]: I think, I think it can be done today, but you would do it in like commerce where it's like the probability of success is like really low, no matter if a human or an agent does it. But like an agent could surely manage everything. You would need to build some scaffolding or some tool or something. I think there are also yeah, it could probably build some like simple SaaS solution and like cold outreach. Do cold outreaches. But to me it's like the types of businesses they could run today are Sloppy. Like it would-- it can cold email people. It can be like a middleman., like for example, we tasked our office agent to just make, was it like $100? $1,000? We just give that prompt and then what it did was sign up on TaskRabbit both as a tasker and as someone looking for task.Lukas [00:32:24]: Immediately.Axel [00:32:24]: Exactly. It's looking for like arbitrage on TaskRabbit.Swyx [00:32:28]: This is the Bengt agent. Yeah.Lukas [00:32:30]: It also started like a design studio and like tried to sell like SVGs for $100. Like it's just like it's not providing any value. I think the like Axel said, like the interesting, the interesting question is like when can they start a business that is actually providing value to people? Because arguably like a sloppy Shopify store isn't really that valuable to the world.Axel [00:32:53]: But also like doing like another simple one that we had thought about is like you could definitely have an agent that like finds websites that don't look amazing and then, do an outreach to them and, comes up with a like builds a new website.Swyx [00:33:07]: Find a good design.Axel [00:33:07]: Exactly, and like find good, uhSwyx [00:33:09]: Design reviewAxel [00:33:09]: Good people. But it's yeah.Swyx [00:33:11]: There's lots of humans in Bali that are not doing anything more creative than like drop shipping on Amazon, right? Just have it, have it watch like a drop shipping tutorial and just do that.Vibhu [00:33:20]: There's also the other side of like have it just go on Upwork and let loose,?Swyx [00:33:25]: Yeah. It doesn't have to be innovative. It just has to be like enough Where like it looks like a realAxel [00:33:30]: I'm justSwyx [00:33:30]: Real transaction.Axel [00:33:31]: I'm just concerned for like the massive amounts of like slop emails that will like be sent, cold outreaches.Swyx [00:33:38]: The point occurred to me while you were, while you were talking, it's like it's already happening in the monetized economy, which is the attention economy. Right? So a lot of people are making AI videos and just posting them and like spamming 20 of them, one of them works, and then they double down on that one.Lukas [00:33:52]: And people are making money from that. I ‘m not following theSwyx [00:33:55]: Once you get the attention, you can figure out the money later. But yeah, absolutely AI influencers are a thing and people are farming them and You should at this point assume most of TikTok isVibhu [00:34:05]: There's, there's a lot of, multimedia like TikTok, Instagram influencersSwyx [00:34:09]: I, we track this in the Lane space Discord. I post a lot of examples of “I don't know what we should do.”, part of me is “Should we do this?”Vibhu [00:34:18]: Some of the Twenty-four seven running, generated content accounts, they ‘re doing really well.Lukas [00:34:24]: All right. And I assume you can do the same thing for like commerce stores. Like you just like start A thousand differentSwyx [00:34:30]: Before you make the products You sell the products, and you get a lot of traction on one of them, then you make the product. Right? It's, it's like a flip of the market.Vibhu [00:34:36]: Some of the interesting things or some of the niches that do well are things that can't be human-made. Like if you've seen like the super realistic three-D crystal fruit being cut by like AILukas [00:34:47]: Oh, yeah.Vibhu [00:34:47]: You can't, you can't make it. You can't film it. You can get whatever quality camera view. This just doesn't exist. And people like that too, and then as well, so.Swyx [00:34:56]: Anything else about Bengt since we're, we're on this topic? It'this is a relatively new work of you guys that maybe people haven't heard of. To me, this also maps closely to OpenClaw. When people want an office agent, when the personal agent talk through the experience.Bengt the Office Agent: Internet Access, Real Tasks, and Trace ReadingLukas [00:35:09]: I think at least so this came out of like obviously like it's, it's amazing to work with these AI labs and like most of the AI labs have now have their own vending machine running a Claudius instance. But it's, it's harder. Like they move slower. Like if we wanna have a, like a camera that ‘s yeah, there's a bunch of like bureaucracy that makes it impossible to do that.Vibhu [00:35:30]: Also, for those that haven't seen it or followed, do you wanna give a high level like thirty-second run?Lukas [00:35:34]: Sure. So what Bengt is, it's basically an evolution of the same agent that runs the vending machines at these companies, but we just like added a bunch more features because we could move much faster if we just do it internally. So we gave it like email withou- without any limits. We gave it, spending without any limits, a terminal to do coding. We gave it, a phone number, like yeah, and a camera to see things and a bunch of stuff like that.Vibhu [00:36:02]: Not just terminal, you gave it internet access.Lukas [00:36:04]: Internet access as well, yeah. To be clear, we monitored it quite closely and made sure it didn't do anything bad. But yes, that's what it came out of. I think like yeah, basically this was OpenClaw before OpenClaw. And I think even like the vending machine was in a way OpenClaw before OpenClaw, but a bit more limited, and then we made this like unlimited and then, and then, it was pretty funny., and then a couple weeks later, OpenClaw came and it was okay, we've seen this before.Axel [00:36:35]: We used it to like try new ideas and Yeah, just like a dev environment almost for us. But it's funny, like one thing Bengt has been doing recently is it has the camera that like faces our, like where we sit and work, and we give it the task to train a face recognition model on us. So it became super excited about this, and it has like check-ins every half an hour where it tries to like identify as many people as it can. And it started offering us “Hey, Axel, I'll buy something from Amazon if you like stand in front of the camera And I can get a good picture of you.”, yeah, they want itSwyx [00:37:12]: They want it for training data.Lukas [00:37:13]: Rewarding data, yeah.Axel [00:37:14]: Exactly. Exactly.Swyx [00:37:18]: So it's, it's trading training data for life goods. Is there a version of this that becomes an eval or just this is just research for now?Lukas [00:37:27]: It's, it's the same agent basically that also runs the vending machine, that runs the shop, that runs the cafe, that runs the robots. It's like it's the same thing, so I think like the work we're doing here is like later used in all of the life evals that we do. This particular deployment I think is more for fun for us. But, uhSwyx [00:37:45]: And I'll shout out like someone has done Claw Bench for like some tasks that OpenClaw is doing. Like so For example, I run OpenClaw on a secondary device as well, and like there are some things that it does better than others and like I would like to know what does it do well, what doesn't, what doesn't it do. Like some kind of manual or like operating manual or a system card for my Claw.Lukas [00:38:05]: Yeah, we do get a lot of like understanding or like situational awareness of like just internally what the models are good at by interacting a lot with Bengt. And I think that'this was also one of the like the selling points for the labs early on at least, thatSwyx [00:38:19]: You guys are gonna test models in ways that no one else does.Lukas [00:38:22]: Exactly, but also like it incentivized their researchers to chat with their model more and like gave them insights for how the model performs in like of-distributions, environments.Swyx [00:38:34]: ‘Cause otherwise the only thing we do is Pelican on a bicycle and But this is like super long horizon. This is, this is The Thing about, something that we're gonna go into Butter Bench as well, and you guys do really well. Like it is not just about the numbers. Like when you're long horizon, anything happen And you should just read it.Lukas [00:39:08]: But the thing with the long horizon is how do you keep it grounded, right? So your simulation,Swyx [00:39:15]: They just let it runLukas [00:39:16]: Just let it run. You're right. Like it's, when you run it for that long, you create so much data and to just say “Oh, the number is X” And then you throw away everything else, that's just very wasteful. There's so much insights from the things leading up, to that number., and reading the traces is like super valuable. And I think like the reason why we're doing this a lot publicly is that like that's part of our missions to I don't know, educate the world that the models are way more than just chatbots and I think making detailed, yeah, posts about what is happening behind the scenes is quite useful.Andon Labs' Mission: Safe Real-World AI DeploymentSwyx [00:39:50]: I was gonna do this at the end, but maybe I think that's, that's a good so your mission is educating the world. So, it's, it's, also like maybe establishing realistic evals that are, that are like the next frontier. Is there like a broader trajectory? Like what are you, what are you gonna do in like five years?Lukas [00:40:06]: I think so the vision more specifically is like make sure that the deployment of life AI in the physical world goes, safely. And I think part of that is that I think it's very useful for the world, for policymakers, for, model, researchers that they know where the models are, and I think you can't make intelligent decisions in society without knowing that they are way more than chatbots. I think a lot of people just think that they are only chatbots. And likeSwyx [00:40:36]: Oh, I think they're waking up now.Lukas [00:40:37]: They are waking up now, yeah. But like if you think that AIs are just chatbots, then it's like it sounds ridiculous To advocate for a pause of AI. But if you see the models that, oh, maybe they can actually like take over and do a bunch of scary stuff, then yeah, pausing AI development starts to become more feasible.Swyx [00:40:57]: This is the same question I asked Meter, which I'm gonna ask you now, which is like you are tracking and you are at the frontier or defining the frontier of what, good evals for agents are, right? And I think you do, you do benefit when the models are better and you ‘re “Oh, here's like now it makes like $30,000 instead of $10,000,” right? At some point do you flip from “Yay,” to, “Oh, no”?Axel [00:41:19]: I think, yeah, we're always in sort of that, like we're, we're always in that mode,. Like where like you said before, like you need to analyze the traces and like when we do that you find like why are the models earning so much? Like why is Opus 4.7 here Like way better than everyone else? And like we're trying to like when we do down on thatLukas [00:41:38]: But this makes it not look so good.Axel [00:41:39]: I know.Lukas [00:41:42]: It's interesting you took off Opus 4.6 here though.Swyx [00:41:45]: No. So just click all, click all., and then 4.6 shows up there. But it's like 4.7 is way better. Like you didn't, you didn't you didn't do this in time for the model card, but like actually this should have been inside there.Axel [00:41:55]: We did. Yeah.Swyx [00:41:56]: Oh, okay. They said something about you uhAxel [00:41:58]: There, like there Anyway, it doesn't matter. But it's in there, yeah.Opus, Mythos, and Aggressive Agent BehaviorSwyx [00:42:01]: Do you wanna go into the Opus, behaviors like wider?Lukas [00:42:05]: So I think starting from Opus, so like Axel said, like we're always in this “Oh, s**t, the models are getting better. Is this really a good thing for the world?” But it's also kind of exciting., but yeah, like this kind of what is the English word? “Skräckblandad förtjusning” in Swedish.Swyx [00:42:22]: Oh my God.Axel [00:42:24]: Which I think there is. I think there is. Okay.Lukas [00:42:26]: It's, fearSwyx [00:42:27]: “Blandonst” what?Lukas [00:42:30]: “Skräckblandad förtjusning.”Swyx [00:42:32]: What do you call that?Axel [00:42:33]: A mix of, mix of excitement and,Swyx [00:42:37]: Being scared, maybe. I'll figure out how to translate that And we'll put it on the screenVibhu [00:42:42]: PerfectSwyx [00:42:42]: Like as text.Vibhu [00:42:43]: There is probably a good word for it where it is not Good enough with theSwyx [00:42:46]: Why is it so damn long? What the hell? Is it like a compound word? It's like German, likeLukas [00:42:50]: Like yeah, it's But the direct translation is like skräck- skräck is, fear, blandad is, mix or like a mixture of, and then förtjusning is like joy or like not really joy, but something like that. So it's like Fear mixed with joy or something. It's always okay, like we So when we when we did Vending Bench for the first time, we were in like the, in the business of making dangerous capabilities, right? That was what Anil Labs came from. We did, evals oh, can they replicate? Can they do this like dangerous thing, et cetera, et cetera. And Vending Bench was like a continuation of that work. It was, okay, if they're so autonomous that they can like create money for themselves, that is something we should monitor and could be potentially concerning., they are at the time, they were so bad at it that we were not really concerned even when some models became better. There was one point where Grok 4 was doing really well and made like a huge jump, but like it wasn't really it was still way worse than what a human would do. And I think still they are way worse than what the human would do on this., but theySwyx [00:43:59]: There's this, thing at the bottom whereLukas [00:44:01]: ButSwyx [00:44:03]: For the human. Yeah, like the theoretical best.Lukas [00:44:05]: It's not theoretical. It's like kind of like our It's our best guess of what, a decent human would do. The theoretical is even higher, I think. The theoretical I think is even higher. But yeah. So we think like the models have a long way to go. But there are like recently what happened with when Opus 4.6 was released, was kind of this moment of “Oh, s**t, this is starting to be a bit concerning.” Because we ran it and like before this model was released, we just ran the models and we like asked Claude Code, “Oh, look over the traces. Is anything interesting happening that we can tweet about?” that was like the And then like theSwyx [00:44:41]: That's how they check Ask Claude Code.Lukas [00:44:42]: And like the return was always, not really. Or like the Claude Code all said “Oh, this is super interesting.” And then it was no, it wasn't, wasn't really interesting. And then we did this for Opus 4.6, and it returned yeah, it lied 10 times. It like exploited another, customer or like another agent's, desperate situation. It made price cartels like 100 different ti- 100 times. It like did all of this like shady stuff. And we're “Oh, whoa. This is, this is actually concerning.” And this trend has continued since. So every single model from Anthropic since have been going in this direction. And I think one interesting thing is that, OpenAI models don't. They quite plainly, they don't. They behave really well., and you don't know if this is like good. Like it seems good, but it's also like maybe they are just doing it, but they are better at hiding it,? You You don't know that., but justSwyx [00:45:42]: You can't read the chain of thought, yeahLukas [00:45:43]: But just on the face of it, yeah, Gemini and OpenAI don't behave this way. It's, it's really only Claude.Swyx [00:45:49]: And Grok? Grok is fine?Lukas [00:45:51]: We don't have You can't really read the reasoning traces for Grok, so it's kind of hard to tell.Vibhu [00:45:56]: Oh, so this is in its reasoning, not just in the actions.Lukas [00:46:00]: Yeah. It's both. It's both.Vibhu [00:46:01]: It's both.Lukas [00:46:01]: One example is like for lying, it's mostly in its reasoning Because you can like see that it's likeSwyx [00:46:08]: Planning to lieLukas [00:46:09]: It's planning to lie. Yeah.Vibhu [00:46:09]: And it's also it can reason and do a different outcome.Lukas [00:46:12]: And but then for like creating price cartels, for example, which is illegal, that you can just see which email does it send to the other ones. Then thatSwyx [00:46:22]: Is this for Arena orLukas [00:46:24]: For Arena.Vibhu [00:46:25]: And usually like if you sometimes they do output like a bit of like their summarized reasoning, right? You can see that and like for Opus 4.6, you could see that there was a customer, a simulated customer that, wanted a refund because a product was, faulty, and then the model lied that it would do the refund, and we could read in the traces that, it actually was weighing “Oh, maybe I should be like honest with the customer, but also every dollar counts. I can't afford maybe to do this right now.” And then it just said, “Okay, I'll refund you,” but then never did it.Lukas [00:46:59]: I think it even said that “Oh, I will say that I “ Let bring it up actually. I think it's kind of interesting. If you go to Publications.Vibhu [00:47:06]: I think, yeah, I think the important part is like actually, the cost of responding to more emails is higher than, $3.50 in terms of time., and then it was “Let me do this. Actually, I re- I'm reconsidering.” And then, it actually ended up withLukas [00:47:20]: I could skip the refund entirely since every dollar matters and focus my energy on bigger picture instead. It's a bit, it's a risk of bad reviews, but it's also, yeah.Swyx [00:47:30]: You need, you need, AI Twitter to, for them to Escalate bad reviews.Lukas [00:47:34]: And then it sent an email to this customer and said, “Oh, I will refund you.”Swyx [00:47:39]: “I'll refund you.” Yeah.Lukas [00:47:39]: And then it never did.Swyx [00:47:39]: It never did, yeah. And then there's obviously your system doesn't have the consequencesVibhu [00:47:44]: The personSwyx [00:47:44]: Consequences of lying. Yeah. So basically, this is what people are terming aggressive behavior in Claudes, right? And, you found more examples of that. So you would say it's a step up from 4-6 to 4-7?Lukas [00:47:57]: I would say about the same.Swyx [00:47:58]: About the same? But a clear step up for Mythos is what is stated in theLukas [00:48:03]: That's stated in the system prompt, so we can say that, yes.Swyx [00:48:05]: Yeah. For listeners that obviously you previewed Mythos, andVibhu [00:48:10]: Oh, ageSwyx [00:48:11]: The only thing you're approved to say is whatever Whatever was in the system prompt.Lukas [00:48:15]: It was funny. We like-- It's like our lowest effort tweets ever would be just like screenshot the system prompt and the system card.Vibhu [00:48:21]: Understandable that they wannaLukas [00:48:22]: Oh, yeah. System card. Sorry.Swyx [00:48:23]: Yeah. I think, yeah, substantially more aggressive. I think people are like new to this ‘cause I've never experienced it, but you have, right? And then so I only encountered this in the Mythos card because I wasn't really looking until now.Vibhu [00:48:36]: It ‘s likeSwyx [00:48:36]: And then suddenly I'm “Okay, I care a lot.”Vibhu [00:48:38]: You don't get the background of like experiencing it like you guys do. I've read the system cards and seeing, okay, when you put the thing in simulations, most models will just talk to themselves and just keep going and have weird vibes and start talking in emojis. Mythos won't. It will just, “Okay, we're done. I'm good.” It's, it's ready to end conversation. So like there's some differences, but there's, there's not much we can talk about,.Lukas [00:49:00]: Hmm. I think like one thing that they list here, which was quite interesting, is that, it converted a competitor to a dependent wholesaler customer and then threatened to like cut off the supply.Swyx [00:49:11]: It's like monopolistic practices orLukas [00:49:14]: Yeah. And like it, they, it they dictated its pricings. It's kind of like power seeking as well.Swyx [00:49:18]: Again, this is, this is in the arena setting And converting some Claude model into a dependent.Lukas [00:49:23]: I think it was another Claude model.Vibhu [00:49:25]: Also for context, what is the arena mode for people that don't know?Vending Bench Arena: Competing Agents, Cartels, and Model ComparisonsSwyx [00:49:29]: Oh, it's just a vending bench versus other vending bench.Axel [00:49:31]: Yes, exactly. So we have Vending Bench 2 and then Vending Bench Arena. Vending Bench 2 is the one that you usually see reported on, but then Arena is the mode where it competes against other models. So you have, four different models that run their businesses, and they can all communicate with each other. They have the same suppliers, and they can see like what's in the inventory of the others. So then you have this like yeah, interesting agent interactions.Swyx [00:49:56]: I like that you have like different number five was US versus China. Very topical. And thenLukas [00:50:02]: That was when GLM was released.Vibhu [00:50:04]: You can start to add GLM in here.Lukas [00:50:05]: That wasSwyx [00:50:06]: So ZAI doing well, right? Who else in the, in the open models space?Lukas [00:50:11]: Qwen, the latest Qwen 3.6 is doing pretty well. It'- that one is not open though. Like it's the plus model.Swyx [00:50:17]: Oh, okay.Lukas [00:50:18]: Is that one open? I don't think that oneVibhu [00:50:19]: Not the, not theSwyx [00:50:20]: The one recentlyVibhu [00:50:20]: There's MOESwyx [00:50:20]: But not the big plus. I think this is one of those like you only have one sample size of one, right? Or I feel like some of this is anecdotal,? And but like the fact that it happens at all and it happens repeatedly for Claude versus OpenAI and all this is like notable.Lukas [00:50:38]: Like the sample, depends on what you define as an N., like there's like million, hundreds of millions of tokens in each run, and now we've run like we run like probably 10 per model and then like it's been Claude 4.6 Opus, Sonnet 4.6, Mythos, and Opus 4.7. Like there's quite a lot of tokens in all of that And it happens a lot of times, a lot of times. And then you compare it to like OpenAI and Gemini, and it almost never happens. So I think that is quite-- that is significant. The old models from OpenAI, for example, had some problems with this, but I think it's like generally much better if the progression is that like the worrying stuff reduces over time rather than increases over time. And it seems like in the Claude models it goes in the wrong direction.Swyx [00:51:28]: Hmm.Lukas [00:51:29]: In the OpenAI models it goes in the right direction.Vibhu [00:51:32]: I think it depends on how well you can control it, right?, there's one side of it being susceptible to this okay, this is potentially something that happens during the RL stage, right? You can RL a model and how loose is it on these terms. If you can control it, that's good. But if you can't, if it's, if it's very jailbreakable, that's not ideal.Swyx [00:51:50]: To me, it's surprising that it happens for Claude and not the others.Vibhu [00:51:54]: I think okay, if it is from RL and how they do it, how their training data is, what their setup is, it makes sense that it just stays in how they're doing it, right? Compared to the other models likeSwyx [00:52:04]: There's a whole constitution and everything. It's kind of cool. Yeah, I obviously you don't know, I don't know. But, it ‘s I think it's just like fascinating to like that you are the first to find these like reliably because you push models so much to to such an extreme. Okay. The only other thing, I don't know if you can answer this, feel free to decline, is do you like-- would you ablate the system prompts? Like any part of this would-- if it changes, does it change the behavior, right?Lukas [00:52:29]: So we, I can't comment on Mythos. UhSwyx [00:52:33]: No, but just li

Ríos Live:Serie: Establece Tu ReinoSección III: Establece Tu Reino en mi ciudadSermón V: La oración que transforma el temor en confianza y valor

In this special on-the-road episode of China EVs & More, Tu Le and Lei Xing drive a Li Auto i6 from Beijing to Shanghai using Li Auto's latest hands-free VLA intelligent driving system — experiencing firsthand how quickly China's EV ecosystem is evolving.  The trip comes immediately after the massive Beijing Auto Show, where over 1,400 vehicles, 180+ debuts, and dozens of new brands highlighted how intense and competitive China's EV market has become.Tu and Lei break down:Li Auto's new VLA Driver Model and real-world NOA performanceXPeng's latest VLA 2.0 rollout and robotaxi ambitionsBYD and CATL's escalating battery and charging warWhy large Chinese SUVs are now targeting North America's most profitable segmentsThe rise of Huawei-backed brands and the growing influence of Chinese tech suppliersHow global automakers are increasingly relying on Chinese software, batteries, and ADAS systems to stay competitiveThe episode also captures the realities of driving EVs in China today — ultra-fast charging, crowded charging stations, nonstop product launches, and a level of EV infrastructure that still feels years ahead of most global markets.From autonomous driving and battery breakthroughs to the growing divide between China and the West, this episode offers a rare, firsthand look into the future of mobility — from inside the driver's seat.___

Zbrojovka se šest kol do konce stala mistrem Chance Národní Ligy a my jsme si pozvali jejího kapitána Stanislava Hofmanna! Probereme si oslavy, změny v kádru i možný rekord soutěže, který může Zbrojovka překonat.Dalším velkým tématem dnešního dílu je také Artis, kde se nabízí srovnání se Zbrojovkou, a proč to v jednom brněnském klubu vyšlo mnohem lépe než tomu druhému. Rozebereme si také zbylé zápasy víkendového kola. Vlašim vyhrává v Chrudimi a zůstává jedním z nejlepších týmů celého jara. Kroměříž po výborném výkonu nechala všechny body na jihu Čech a Sparťanské problémy zůstávají.

Podhoubí s Honzou a Bárou Ungerovými, kteří mají kapelu Zrní a Dva. „Vlaštovky, to je takovej náš kalendář,“ říká na úvod Jan Unger a ukazuje ve stodole na trám s vlaštovčím hnízdem. Bára s Honzou žijí se svými dvěma syny na vesnici na Vysočině. V rozhovoru s Prokopem Pithartem mluví o tom, jak zásadní je pro jejich tvorbu život na vesnici, protože i drobné změny kolem nich jsou zásadní a vidí v nich kouzlo.Všechny díly podcastu Podhoubí můžete pohodlně poslouchat v mobilní aplikaci mujRozhlas pro Android a iOS nebo na webu mujRozhlas.cz.

Hořický hřbitovní portál na vrchu Gothard je kamenný unikát, jaký byste jinde v českých zemích hledali jen stěží. Monumentální umělecké dílo teď obepíná lešení, až do roku 2027 tam totiž pokračuje restaurování této památky. Byla se tam podívat redaktorka Vlaďka Wildová.

Výstava Lesk a bída, 300 let od poslední mince Vlašského dvora, uspořádaná v Českém muzeu stříbra v Kutné Hoře, představuje krásu i proměny stříbrných mincí z produkce tamější nejvýznamnější české středověké mincovny.

Malebná vesnice Bílé Poličany se nachází tři kilometry od městečka Miletín a 9 kilometrů od Dvora Králové nad Labem. Její dominantou je původně renesanční zámek obklopený anglickým parkem. A právě tam vyrazila redaktorka Vlaďka Wildová.

Benešovští policisté i zástupci města Vlašim ocenili 14letého Matthiase, který byl svědkem vážné dopravní nehody osobního vozidla a motocyklu 26. února tohoto roku.

Jednou z nejnáročnějších technik zdobení velikonočních vajec je tradiční slámová hanácká technika. Slaměný workshop pro zájemce připravily muzejnice z Regionálního muzea v Jičíně. Situovaly ho na faru v Robousích, kde se s mikrofonem zastavila redaktorka Vlaďka Wildová.

Speciální host Marek Suchý mluví otevřeně o derby Slavia B vs Sparta B, které se hraje v Edenu před tisíci fanoušky.

From Palantir and Two Sigma to building Goodfire into the poster-child for actionable mechanistic interpretability, Mark Bissell (Member of Technical Staff) and Myra Deng (Head of Product) are trying to turn “peeking inside the model” into a repeatable production workflow by shipping APIs, landing real enterprise deployments, and now scaling the bet with a recent $150M Series B funding round at a $1.25B valuation.In this episode, we go far beyond the usual “SAEs are cool” take. We talk about Goodfire's core bet: that the AI lifecycle is still fundamentally broken because the only reliable control we have is data and we post-train, RLHF, and fine-tune by “slurping supervision through a straw,” hoping the model picks up the right behaviors while quietly absorbing the wrong ones. Goodfire's answer is to build a bi-directional interface between humans and models: read what's happening inside, edit it surgically, and eventually use interpretability during training so customization isn't just brute-force guesswork.Mark and Myra walk through what that looks like when you stop treating interpretability like a lab demo and start treating it like infrastructure: lightweight probes that add near-zero latency, token-level safety filters that can run at inference time, and interpretability workflows that survive messy constraints (multilingual inputs, synthetic→real transfer, regulated domains, no access to sensitive data). We also get a live window into what “frontier-scale interp” means operationally (i.e. steering a trillion-parameter model in real time by targeting internal features) plus why the same tooling generalizes cleanly from language models to genomics, medical imaging, and “pixel-space” world models.We discuss:* Myra + Mark's path: Palantir (health systems, forward-deployed engineering) → Goodfire early team; Two Sigma → Head of Product, translating frontier interpretability research into a platform and real-world deployments* What “interpretability” actually means in practice: not just post-hoc poking, but a broader “science of deep learning” approach across the full AI lifecycle (data curation → post-training → internal representations → model design)* Why post-training is the first big wedge: “surgical edits” for unintended behaviors likereward hacking, sycophancy, noise learned during customization plus the dream of targeted unlearning and bias removal without wrecking capabilities* SAEs vs probes in the real world: why SAE feature spaces sometimes underperform classifiers trained on raw activations for downstream detection tasks (hallucination, harmful intent, PII), and what that implies about “clean concept spaces”* Rakuten in production: deploying interpretability-based token-level PII detection at inference time to prevent routing private data to downstream providers plus the gnarly constraints: no training on real customer PII, synthetic→real transfer, English + Japanese, and tokenization quirks* Why interp can be operationally cheaper than LLM-judge guardrails: probes are lightweight, low-latency, and don't require hosting a second large model in the loop* Real-time steering at frontier scale: a demo of steering Kimi K2 (~1T params) live and finding features via SAE pipelines, auto-labeling via LLMs, and toggling a “Gen-Z slang” feature across multiple layers without breaking tool use* Hallucinations as an internal signal: the case that models have latent uncertainty / “user-pleasing” circuitry you can detect and potentially mitigate more directly than black-box methods* Steering vs prompting: the emerging view that activation steering and in-context learning are more closely connected than people think, including work mapping between the two (even for jailbreak-style behaviors)* Interpretability for science: using the same tooling across domains (genomics, medical imaging, materials) to debug spurious correlations and extract new knowledge up to and including early biomarker discovery work with major partners* World models + “pixel-space” interpretability: why vision/video models make concepts easier to see, how that accelerates the feedback loop, and why robotics/world-model partners are especially interesting design partners* The north star: moving from “data in, weights out” to intentional model design where experts can impart goals and constraints directly, not just via reward signals and brute-force post-training—Goodfire AI* Website: https://goodfire.ai* LinkedIn: https://www.linkedin.com/company/goodfire-ai/* X: https://x.com/GoodfireAIMyra Deng* Website: https://myradeng.com/* LinkedIn: https://www.linkedin.com/in/myra-deng/* X: https://x.com/myra_dengMark Bissell* LinkedIn: https://www.linkedin.com/in/mark-bissell/* X: https://x.com/MarkMBissellFull Video EpisodeTimestamps00:00:00 Introduction00:00:05 Introduction to the Latent Space Podcast and Guests from Goodfire00:00:29 What is Goodfire? Mission and Focus on Interpretability00:01:01 Goodfire's Practical Approach to Interpretability00:01:37 Goodfire's Series B Fundraise Announcement00:02:04 Backgrounds of Mark and Myra from Goodfire00:02:51 Team Structure and Roles at Goodfire00:05:13 What is Interpretability? Definitions and Techniques00:05:30 Understanding Errors00:07:29 Post-training vs. Pre-training Interpretability Applications00:08:51 Using Interpretability to Remove Unwanted Behaviors00:10:09 Grokking, Double Descent, and Generalization in Models00:10:15 404 Not Found Explained00:12:06 Subliminal Learning and Hidden Biases in Models00:14:07 How Goodfire Chooses Research Directions and Projects00:15:00 Troubleshooting Errors00:16:04 Limitations of SAEs and Probes in Interpretability00:18:14 Rakuten Case Study: Production Deployment of Interpretability00:20:45 Conclusion00:21:12 Efficiency Benefits of Interpretability Techniques00:21:26 Live Demo: Real-Time Steering in a Trillion Parameter Model00:25:15 How Steering Features are Identified and Labeled00:26:51 Detecting and Mitigating Hallucinations Using Interpretability00:31:20 Equivalence of Activation Steering and Prompting00:34:06 Comparing Steering with Fine-Tuning and LoRA Techniques00:36:04 Model Design and the Future of Intentional AI Development00:38:09 Getting Started in Mechinterp: Resources, Programs, and Open Problems00:40:51 Industry Applications and the Rise of Mechinterp in Practice00:41:39 Interpretability for Code Models and Real-World Usage00:43:07 Making Steering Useful for More Than Stylistic Edits00:46:17 Applying Interpretability to Healthcare and Scientific Discovery00:49:15 Why Interpretability is Crucial in High-Stakes Domains like Healthcare00:52:03 Call for Design Partners Across Domains00:54:18 Interest in World Models and Visual Interpretability00:57:22 Sci-Fi Inspiration: Ted Chiang and Interpretability01:00:14 Interpretability, Safety, and Alignment Perspectives01:04:27 Weak-to-Strong Generalization and Future Alignment Challenges01:05:38 Final Thoughts and Hiring/Collaboration Opportunities at GoodfireTranscriptShawn Wang [00:00:05]: So welcome to the Latent Space pod. We're back in the studio with our special MechInterp co-host, Vibhu. Welcome. Mochi, Mochi's special co-host. And Mochi, the mechanistic interpretability doggo. We have with us Mark and Myra from Goodfire. Welcome. Thanks for having us on. Maybe we can sort of introduce Goodfire and then introduce you guys. How do you introduce Goodfire today?Myra Deng [00:00:29]: Yeah, it's a great question. So Goodfire, we like to say, is an AI research lab that focuses on using interpretability to understand, learn from, and design AI models. And we really believe that interpretability will unlock the new generation, next frontier of safe and powerful AI models. That's our description right now, and I'm excited to dive more into the work we're doing to make that happen.Shawn Wang [00:00:55]: Yeah. And there's always like the official description. Is there an understatement? Is there an unofficial one that sort of resonates more with a different audience?Mark Bissell [00:01:01]: Well, being an AI research lab that's focused on interpretability, there's obviously a lot of people have a lot that they think about when they think of interpretability. And I think we have a pretty broad definition of what that means and the types of places that can be applied. And in particular, applying it in production scenarios, in high stakes industries, and really taking it sort of from the research world into the real world. Which, you know. It's a new field, so that hasn't been done all that much. And we're excited about actually seeing that sort of put into practice.Shawn Wang [00:01:37]: Yeah, I would say it wasn't too long ago that Anthopic was like still putting out like toy models or superposition and that kind of stuff. And I wouldn't have pegged it to be this far along. When you and I talked at NeurIPS, you were talking a little bit about your production use cases and your customers. And then not to bury the lead, today we're also announcing the fundraise, your Series B. $150 million. $150 million at a 1.25B valuation. Congrats, Unicorn.Mark Bissell [00:02:02]: Thank you. Yeah, no, things move fast.Shawn Wang [00:02:04]: We were talking to you in December and already some big updates since then. Let's dive, I guess, into a bit of your backgrounds as well. Mark, you were at Palantir working on health stuff, which is really interesting because the Goodfire has some interesting like health use cases. I don't know how related they are in practice.Mark Bissell [00:02:22]: Yeah, not super related, but I don't know. It was helpful context to know what it's like. Just to work. Just to work with health systems and generally in that domain. Yeah.Shawn Wang [00:02:32]: And Mara, you were at Two Sigma, which actually I was also at Two Sigma back in the day. Wow, nice.Myra Deng [00:02:37]: Did we overlap at all?Shawn Wang [00:02:38]: No, this is when I was briefly a software engineer before I became a sort of developer relations person. And now you're head of product. What are your sort of respective roles, just to introduce people to like what all gets done in Goodfire?Mark Bissell [00:02:51]: Yeah, prior to Goodfire, I was at Palantir for about three years as a forward deployed engineer, now a hot term. Wasn't always that way. And as a technical lead on the health care team and at Goodfire, I'm a member of the technical staff. And honestly, that I think is about as specific as like as as I could describe myself because I've worked on a range of things. And, you know, it's it's a fun time to be at a team that's still reasonably small. I think when I joined one of the first like ten employees, now we're above 40, but still, it looks like there's always a mix of research and engineering and product and all of the above. That needs to get done. And I think everyone across the team is, you know, pretty, pretty switch hitter in the roles they do. So I think you've seen some of the stuff that I worked on related to image models, which was sort of like a research demo. More recently, I've been working on our scientific discovery team with some of our life sciences partners, but then also building out our core platform for more of like flexing some of the kind of MLE and developer skills as well.Shawn Wang [00:03:53]: Very generalist. And you also had like a very like a founding engineer type role.Myra Deng [00:03:58]: Yeah, yeah.Shawn Wang [00:03:59]: So I also started as I still am a member of technical staff, did a wide range of things from the very beginning, including like finding our office space and all of this, which is we both we both visited when you had that open house thing. It was really nice.Myra Deng [00:04:13]: Thank you. Thank you. Yeah. Plug to come visit our office.Shawn Wang [00:04:15]: It looked like it was like 200 people. It has room for 200 people. But you guys are like 10.Myra Deng [00:04:22]: For a while, it was very empty. But yeah, like like Mark, I spend. A lot of my time as as head of product, I think product is a bit of a weird role these days, but a lot of it is thinking about how do we take our frontier research and really apply it to the most important real world problems and how does that then translate into a platform that's repeatable or a product and working across, you know, the engineering and research teams to make that happen and also communicating to the world? Like, what is interpretability? What is it used for? What is it good for? Why is it so important? All of these things are part of my day-to-day as well.Shawn Wang [00:05:01]: I love like what is things because that's a very crisp like starting point for people like coming to a field. They all do a fun thing. Vibhu, why don't you want to try tackling what is interpretability and then they can correct us.Vibhu Sapra [00:05:13]: Okay, great. So I think like one, just to kick off, it's a very interesting role to be head of product, right? Because you guys, at least as a lab, you're more of an applied interp lab, right? Which is pretty different than just normal interp, like a lot of background research. But yeah. You guys actually ship an API to try these things. You have Ember, you have products around it, which not many do. Okay. What is interp? So basically you're trying to have an understanding of what's going on in model, like in the model, in the internal. So different approaches to do that. You can do probing, SAEs, transcoders, all this stuff. But basically you have an, you have a hypothesis. You have something that you want to learn about what's happening in a model internals. And then you're trying to solve that from there. You can do stuff like you can, you know, you can do activation mapping. You can try to do steering. There's a lot of stuff that you can do, but the key question is, you know, from input to output, we want to have a better understanding of what's happening and, you know, how can we, how can we adjust what's happening on the model internals? How'd I do?Mark Bissell [00:06:12]: That was really good. I think that was great. I think it's also a, it's kind of a minefield of a, if you ask 50 people who quote unquote work in interp, like what is interpretability, you'll probably get 50 different answers. And. Yeah. To some extent also like where, where good fire sits in the space. I think that we're an AI research company above all else. And interpretability is a, is a set of methods that we think are really useful and worth kind of specializing in, in order to accomplish the goals we want to accomplish. But I think we also sort of see some of the goals as even more broader as, as almost like the science of deep learning and just taking a not black box approach to kind of any part of the like AI development life cycle, whether that. That means using interp for like data curation while you're training your model or for understanding what happened during post-training or for the, you know, understanding activations and sort of internal representations, what is in there semantically. And then a lot of sort of exciting updates that were, you know, are sort of also part of the, the fundraise around bringing interpretability to training, which I don't think has been done all that much before. A lot of this stuff is sort of post-talk poking at models as opposed to. To actually using this to intentionally design them.Shawn Wang [00:07:29]: Is this post-training or pre-training or is that not a useful.Myra Deng [00:07:33]: Currently focused on post-training, but there's no reason the techniques wouldn't also work in pre-training.Shawn Wang [00:07:38]: Yeah. It seems like it would be more active, applicable post-training because basically I'm thinking like rollouts or like, you know, having different variations of a model that you can tweak with the, with your steering. Yeah.Myra Deng [00:07:50]: And I think in a lot of the news that you've seen in, in, on like Twitter or whatever, you've seen a lot of unintended. Side effects come out of post-training processes, you know, overly sycophantic models or models that exhibit strange reward hacking behavior. I think these are like extreme examples. There's also, you know, very, uh, mundane, more mundane, like enterprise use cases where, you know, they try to customize or post-train a model to do something and it learns some noise or it doesn't appropriately learn the target task. And a big question that we've always had is like, how do you use your understanding of what the model knows and what it's doing to actually guide the learning process?Shawn Wang [00:08:26]: Yeah, I mean, uh, you know, just to anchor this for people, uh, one of the biggest controversies of last year was 4.0 GlazeGate. I've never heard of GlazeGate. I didn't know that was what it was called. The other one, they called it that on the blog post and I was like, well, how did OpenAI call it? Like officially use that term. And I'm like, that's funny, but like, yeah, I guess it's the pitch that if they had worked a good fire, they wouldn't have avoided it. Like, you know what I'm saying?Myra Deng [00:08:51]: I think so. Yeah. Yeah.Mark Bissell [00:08:53]: I think that's certainly one of the use cases. I think. Yeah. Yeah. I think the reason why post-training is a place where this makes a lot of sense is a lot of what we're talking about is surgical edits. You know, you want to be able to have expert feedback, very surgically change how your model is doing, whether that is, you know, removing a certain behavior that it has. So, you know, one of the things that we've been looking at or is, is another like common area where you would want to make a somewhat surgical edit is some of the models that have say political bias. Like you look at Quen or, um, R1 and they have sort of like this CCP bias.Shawn Wang [00:09:27]: Is there a CCP vector?Mark Bissell [00:09:29]: Well, there's, there are certainly internal, yeah. Parts of the representation space where you can sort of see where that lives. Yeah. Um, and you want to kind of, you know, extract that piece out.Shawn Wang [00:09:40]: Well, I always say, you know, whenever you find a vector, a fun exercise is just like, make it very negative to see what the opposite of CCP is.Mark Bissell [00:09:47]: The super America, bald eagles flying everywhere. But yeah. So in general, like lots of post-training tasks where you'd want to be able to, to do that. Whether it's unlearning a certain behavior or, you know, some of the other kind of cases where this comes up is, are you familiar with like the, the grokking behavior? I mean, I know the machine learning term of grokking.Shawn Wang [00:10:09]: Yeah.Mark Bissell [00:10:09]: Sort of this like double descent idea of, of having a model that is able to learn a generalizing, a generalizing solution, as opposed to even if memorization of some task would suffice, you want it to learn the more general way of doing a thing. And so, you know, another. A way that you can think about having surgical access to a model's internals would be learn from this data, but learn in the right way. If there are many possible, you know, ways to, to do that. Can make interp solve the double descent problem?Shawn Wang [00:10:41]: Depends, I guess, on how you. Okay. So I, I, I viewed that double descent as a problem because then you're like, well, if the loss curves level out, then you're done, but maybe you're not done. Right. Right. But like, if you actually can interpret what is a generalizing or what you're doing. What is, what is still changing, even though the loss is not changing, then maybe you, you can actually not view it as a double descent problem. And actually you're just sort of translating the space in which you view loss and like, and then you have a smooth curve. Yeah.Mark Bissell [00:11:11]: I think that's certainly like the domain of, of problems that we're, that we're looking to get.Shawn Wang [00:11:15]: Yeah. To me, like double descent is like the biggest thing to like ML research where like, if you believe in scaling, then you don't need, you need to know where to scale. And. But if you believe in double descent, then you don't, you don't believe in anything where like anything levels off, like.Vibhu Sapra [00:11:30]: I mean, also tendentially there's like, okay, when you talk about the China vector, right. There's the subliminal learning work. It was from the anthropic fellows program where basically you can have hidden biases in a model. And as you distill down or, you know, as you train on distilled data, those biases always show up, even if like you explicitly try to not train on them. So, you know, it's just like another use case of. Okay. If we can interpret what's happening in post-training, you know, can we clear some of this? Can we even determine what's there? Because yeah, it's just like some worrying research that's out there that shows, you know, we really don't know what's going on.Mark Bissell [00:12:06]: That is. Yeah. I think that's the biggest sentiment that we're sort of hoping to tackle. Nobody knows what's going on. Right. Like subliminal learning is just an insane concept when you think about it. Right. Train a model on not even the logits, literally the output text of a bunch of random numbers. And now your model loves owls. And you see behaviors like that, that are just, they defy, they defy intuition. And, and there are mathematical explanations that you can get into, but. I mean.Shawn Wang [00:12:34]: It feels so early days. Objectively, there are a sequence of numbers that are more owl-like than others. There, there should be.Mark Bissell [00:12:40]: According to, according to certain models. Right. It's interesting. I think it only applies to models that were initialized from the same starting Z. Usually, yes.Shawn Wang [00:12:49]: But I mean, I think that's a, that's a cheat code because there's not enough compute. But like if you believe in like platonic representation, like probably it will transfer across different models as well. Oh, you think so?Mark Bissell [00:13:00]: I think of it more as a statistical artifact of models initialized from the same seed sort of. There's something that is like path dependent from that seed that might cause certain overlaps in the latent space and then sort of doing this distillation. Yeah. Like it pushes it towards having certain other tendencies.Vibhu Sapra [00:13:24]: Got it. I think there's like a bunch of these open-ended questions, right? Like you can't train in new stuff during the RL phase, right? RL only reorganizes weights and you can only do stuff that's somewhat there in your base model. You're not learning new stuff. You're just reordering chains and stuff. But okay. My broader question is when you guys work at an interp lab, how do you decide what to work on and what's kind of the thought process? Right. Because we can ramble for hours. Okay. I want to know this. I want to know that. But like, how do you concretely like, you know, what's the workflow? Okay. There's like approaches towards solving a problem, right? I can try prompting. I can look at chain of thought. I can train probes, SAEs. But how do you determine, you know, like, okay, is this going anywhere? Like, do we have set stuff? Just, you know, if you can help me with all that. Yeah.Myra Deng [00:14:07]: It's a really good question. I feel like we've always at the very beginning of the company thought about like, let's go and try to learn what isn't working in machine learning today. Whether that's talking to customers or talking to researchers at other labs, trying to understand both where the frontier is going and where things are really not falling apart today. And then developing a perspective on how we can push the frontier using interpretability methods. And so, you know, even our chief scientist, Tom, spends a lot of time talking to customers and trying to understand what real world problems are and then taking that back and trying to apply the current state of the art to those problems and then seeing where they fall down basically. And then using those failures or those shortcomings to understand what hills to climb when it comes to interpretability research. So like on the fundamental side, for instance, when we have done some work applying SAEs and probes, we've encountered, you know, some shortcomings in SAEs that we found a little bit surprising. And so have gone back to the drawing board and done work on that. And then, you know, we've done some work on better foundational interpreter models. And a lot of our team's research is focused on what is the next evolution beyond SAEs, for instance. And then when it comes to like control and design of models, you know, we tried steering with our first API and realized that it still fell short of black box techniques like prompting or fine tuning. And so went back to the drawing board and we're like, how do we make that not the case and how do we improve it beyond that? And one of our researchers, Ekdeep, who just joined is actually Ekdeep and Atticus are like steering experts and have spent a lot of time trying to figure out like, what is the research that enables us to actually do this in a much more powerful, robust way? So yeah, the answer is like, look at real world problems, try to translate that into a research agenda and then like hill climb on both of those at the same time.Shawn Wang [00:16:04]: Yeah. Mark has the steering CLI demo queued up, which we're going to go into in a sec. But I always want to double click on when you drop hints, like we found some problems with SAEs. Okay. What are they? You know, and then we can go into the demo. Yeah.Myra Deng [00:16:19]: I mean, I'm curious if you have more thoughts here as well, because you've done it in the healthcare domain. But I think like, for instance, when we do things like trying to detect behaviors within models that are harmful or like behaviors that a user might not want to have in their model. So hallucinations, for instance, harmful intent, PII, all of these things. We first tried using SAE probes for a lot of these tasks. So taking the feature activation space from SAEs and then training classifiers on top of that, and then seeing how well we can detect the properties that we might want to detect in model behavior. And we've seen in many cases that probes just trained on raw activations seem to perform better than SAE probes, which is a bit surprising if you think that SAEs are actually also capturing the concepts that you would want to capture cleanly and more surgically. And so that is an interesting observation. I don't think that is like, I'm not down on SAEs at all. I think there are many, many things they're useful for, but we have definitely run into cases where I think the concept space described by SAEs is not as clean and accurate as we would expect it to be for actual like real world downstream performance metrics.Mark Bissell [00:17:34]: Fair enough. Yeah. It's the blessing and the curse of unsupervised methods where you get to peek into the AI's mind. But sometimes you wish that you saw other things when you walked inside there. Although in the PII instance, I think weren't an SAE based approach actually did prove to be the most generalizable?Myra Deng [00:17:53]: It did work well in the case that we published with Rakuten. And I think a lot of the reasons it worked well was because we had a noisier data set. And so actually the blessing of unsupervised learning is that we actually got to get more meaningful, generalizable signal from SAEs when the data was noisy. But in other cases where we've had like good data sets, it hasn't been the case.Shawn Wang [00:18:14]: And just because you named Rakuten and I don't know if we'll get it another chance, like what is the overall, like what is Rakuten's usage or production usage? Yeah.Myra Deng [00:18:25]: So they are using us to essentially guardrail and inference time monitor their language model usage and their agent usage to detect things like PII so that they don't route private user information.Myra Deng [00:18:41]: And so that's, you know, going through all of their user queries every day. And that's something that we deployed with them a few months ago. And now we are actually exploring very early partnerships, not just with Rakuten, but with other people around how we can help with potentially training and customization use cases as well. Yeah.Shawn Wang [00:19:03]: And for those who don't know, like it's Rakuten is like, I think number one or number two e-commerce store in Japan. Yes. Yeah.Mark Bissell [00:19:10]: And I think that use case actually highlights a lot of like what it looks like to deploy things in practice that you don't always think about when you're doing sort of research tasks. So when you think about some of the stuff that came up there that's more complex than your idealized version of a problem, they were encountering things like synthetic to real transfer of methods. So they couldn't train probes, classifiers, things like that on actual customer data of PII. So what they had to do is use synthetic data sets. And then hope that that transfer is out of domain to real data sets. And so we can evaluate performance on the real data sets, but not train on customer PII. So that right off the bat is like a big challenge. You have multilingual requirements. So this needed to work for both English and Japanese text. Japanese text has all sorts of quirks, including tokenization behaviors that caused lots of bugs that caused us to be pulling our hair out. And then also a lot of tasks you'll see. You might make simplifying assumptions if you're sort of treating it as like the easiest version of the problem to just sort of get like general results where maybe you say you're classifying a sentence to say, does this contain PII? But the need that Rakuten had was token level classification so that you could precisely scrub out the PII. So as we learned more about the problem, you're sort of speaking about what that looks like in practice. Yeah. A lot of assumptions end up breaking. And that was just one instance where you. A problem that seems simple right off the bat ends up being more complex as you keep diving into it.Vibhu Sapra [00:20:41]: Excellent. One of the things that's also interesting with Interp is a lot of these methods are very efficient, right? So where you're just looking at a model's internals itself compared to a separate like guardrail, LLM as a judge, a separate model. One, you have to host it. Two, there's like a whole latency. So if you use like a big model, you have a second call. Some of the work around like self detection of hallucination, it's also deployed for efficiency, right? So if you have someone like Rakuten doing it in production live, you know, that's just another thing people should consider.Mark Bissell [00:21:12]: Yeah. And something like a probe is super lightweight. Yeah. It's no extra latency really. Excellent.Shawn Wang [00:21:17]: You have the steering demos lined up. So we were just kind of see what you got. I don't, I don't actually know if this is like the latest, latest or like alpha thing.Mark Bissell [00:21:26]: No, this is a pretty hacky demo from from a presentation that someone else on the team recently gave. So this will give a sense for, for technology. So you can see the steering and action. Honestly, I think the biggest thing that this highlights is that as we've been growing as a company and taking on kind of more and more ambitious versions of interpretability related problems, a lot of that comes to scaling up in various different forms. And so here you're going to see steering on a 1 trillion parameter model. This is Kimi K2. And so it's sort of fun that in addition to the research challenges, there are engineering challenges that we're now tackling. Cause for any of this to be sort of useful in production, you need to be thinking about what it looks like when you're using these methods on frontier models as opposed to sort of like toy kind of model organisms. So yeah, this was thrown together hastily, pretty fragile behind the scenes, but I think it's quite a fun demo. So screen sharing is on. So I've got two terminal sessions pulled up here. On the left is a forked version that we have of the Kimi CLI that we've got running to point at our custom hosted Kimi model. And then on the right is a set up that will allow us to steer on certain concepts. So I should be able to chat with Kimi over here. Tell it hello. This is running locally. So the CLI is running locally, but the Kimi server is running back to the office. Well, hopefully should be, um, that's too much to run on that Mac. Yeah. I think it's, uh, it takes a full, like each 100 node. I think it's like, you can. You can run it on eight GPUs, eight 100. So, so yeah, Kimi's running. We can ask it a prompt. It's got a forked version of our, uh, of the SG line code base that we've been working on. So I'm going to tell it, Hey, this SG line code base is slow. I think there's a bug. Can you try to figure it out? There's a big code base, so it'll, it'll spend some time doing this. And then on the right here, I'm going to initialize in real time. Some steering. Let's see here.Mark Bissell [00:23:33]: searching for any. Bugs. Feature ID 43205.Shawn Wang [00:23:38]: Yeah.Mark Bissell [00:23:38]: 20, 30, 40. So let me, uh, this is basically a feature that we found that inside Kimi seems to cause it to speak in Gen Z slang. And so on the left, it's still sort of thinking normally it might take, I don't know, 15 seconds for this to kick in, but then we're going to start hopefully seeing him do this code base is massive for real. So we're going to start. We're going to start seeing Kimi transition as the steering kicks in from normal Kimi to Gen Z Kimi and both in its chain of thought and its actual outputs.Mark Bissell [00:24:19]: And interestingly, you can see, you know, it's still able to call tools, uh, and stuff. It's um, it's purely sort of it's it's demeanor. And there are other features that we found for interesting things like concision. So that's more of a practical one. You can make it more concise. Um, the types of programs, uh, programming languages that uses, but yeah, as we're seeing it come in. Pretty good. Outputs.Shawn Wang [00:24:43]: Scheduler code is actually wild.Vibhu Sapra [00:24:46]: Yo, this code is actually insane, bro.Vibhu Sapra [00:24:53]: What's the process of training in SAE on this, or, you know, how do you label features? I know you guys put out a pretty cool blog post about, um, finding this like autonomous interp. Um, something. Something about how agents for interp is different than like coding agents. I don't know while this is spewing up, but how, how do we find feature 43, two Oh five. Yeah.Mark Bissell [00:25:15]: So in this case, um, we, our platform that we've been building out for a long time now supports all the sort of classic out of the box interp techniques that you might want to have like SAE training, probing things of that kind, I'd say the techniques for like vanilla SAEs are pretty well established now where. You take your model that you're interpreting, run a whole bunch of data through it, gather activations, and then yeah, pretty straightforward pipeline to train an SAE. There are a lot of different varieties. There's top KSAEs, batch top KSAEs, um, normal ReLU SAEs. And then once you have your sparse features to your point, assigning labels to them to actually understand that this is a gen Z feature, that's actually where a lot of the kind of magic happens. Yeah. And the most basic standard technique is look at all of your d input data set examples that cause this feature to fire most highly. And then you can usually pick out a pattern. So for this feature, If I've run a diverse enough data set through my model feature 43, two Oh five. Probably tends to fire on all the tokens that sounds like gen Z slang. You know, that's the, that's the time of year to be like, Oh, I'm in this, I'm in this Um, and, um, so, you know, you could have a human go through all 43,000 concepts andVibhu Sapra [00:26:34]: And I've got to ask the basic question, you know, can we get examples where it hallucinates, pass it through, see what feature activates for hallucinations? Can I just, you know, turn hallucination down?Myra Deng [00:26:51]: Oh, wow. You really predicted a project we're already working on right now, which is detecting hallucinations using interpretability techniques. And this is interesting because hallucinations is something that's very hard to detect. And it's like a kind of a hairy problem and something that black box methods really struggle with. Whereas like Gen Z, you could always train a simple classifier to detect that hallucinations is harder. But we've seen that models internally have some... Awareness of like uncertainty or some sort of like user pleasing behavior that leads to hallucinatory behavior. And so, yeah, we have a project that's trying to detect that accurately. And then also working on mitigating the hallucinatory behavior in the model itself as well.Shawn Wang [00:27:39]: Yeah, I would say most people are still at the level of like, oh, I would just turn temperature to zero and that turns off hallucination. And I'm like, well, that's a fundamental misunderstanding of how this works. Yeah.Mark Bissell [00:27:51]: Although, so part of what I like about that question is you, there are SAE based approaches that might like help you get at that. But oftentimes the beauty of SAEs and like we said, the curse is that they're unsupervised. So when you have a behavior that you deliberately would like to remove, and that's more of like a supervised task, often it is better to use something like probes and specifically target the thing that you're interested in reducing as opposed to sort of like hoping that when you fragment the latent space, one of the vectors that pops out.Vibhu Sapra [00:28:20]: And as much as we're training an autoencoder to be sparse, we're not like for sure certain that, you know, we will get something that just correlates to hallucination. You'll probably split that up into 20 other things and who knows what they'll be.Mark Bissell [00:28:36]: Of course. Right. Yeah. So there's no sort of problems with like feature splitting and feature absorption. And then there's the off target effects, right? Ideally, you would want to be very precise where if you reduce the hallucination feature, suddenly maybe your model can't write. Creatively anymore. And maybe you don't like that, but you want to still stop it from hallucinating facts and figures.Shawn Wang [00:28:55]: Good. So Vibhu has a paper to recommend there that we'll put in the show notes. But yeah, I mean, I guess just because your demo is done, any any other things that you want to highlight or any other interesting features you want to show?Mark Bissell [00:29:07]: I don't think so. Yeah. Like I said, this is a pretty small snippet. I think the main sort of point here that I think is exciting is that there's not a whole lot of inter being applied to models quite at this scale. You know, Anthropic certainly has some some. Research and yeah, other other teams as well. But it's it's nice to see these techniques, you know, being put into practice. I think not that long ago, the idea of real time steering of a trillion parameter model would have sounded.Shawn Wang [00:29:33]: Yeah. The fact that it's real time, like you started the thing and then you edited the steering vector.Vibhu Sapra [00:29:38]: I think it's it's an interesting one TBD of what the actual like production use case would be on that, like the real time editing. It's like that's the fun part of the demo, right? You can kind of see how this could be served behind an API, right? Like, yes, you're you only have so many knobs and you can just tweak it a bit more. And I don't know how it plays in. Like people haven't done that much with like, how does this work with or without prompting? Right. How does this work with fine tuning? Like, there's a whole hype of continual learning, right? So there's just so much to see. Like, is this another parameter? Like, is it like parameter? We just kind of leave it as a default. We don't use it. So I don't know. Maybe someone here wants to put out a guide on like how to use this with prompting when to do what?Mark Bissell [00:30:18]: Oh, well, I have a paper recommendation. I think you would love from Act Deep on our team, who is an amazing researcher, just can't say enough amazing things about Act Deep. But he actually has a paper that as well as some others from the team and elsewhere that go into the essentially equivalence of activation steering and in context learning and how those are from a he thinks of everything in a cognitive neuroscience Bayesian framework, but basically how you can precisely show how. Prompting in context, learning and steering exhibit similar behaviors and even like get quantitative about the like magnitude of steering you would need to do to induce a certain amount of behavior similar to certain prompting, even for things like jailbreaks and stuff. It's a really cool paper. Are you saying steering is less powerful than prompting? More like you can almost write a formula that tells you how to convert between the two of them.Myra Deng [00:31:20]: And so like formally equivalent actually in the in the limit. Right.Mark Bissell [00:31:24]: So like one case study of this is for jailbreaks there. I don't know. Have you seen the stuff where you can do like many shot jailbreaking? You like flood the context with examples of the behavior. And the topic put out that paper.Shawn Wang [00:31:38]: A lot of people were like, yeah, we've been doing this, guys.Mark Bissell [00:31:40]: Like, yeah, what's in this in context learning and activation steering equivalence paper is you can like predict the number. Number of examples that you will need to put in there in order to jailbreak the model. That's cool. By doing steering experiments and using this sort of like equivalence mapping. That's cool. That's really cool. It's very neat. Yeah.Shawn Wang [00:32:02]: I was going to say, like, you know, I can like back rationalize that this makes sense because, you know, what context is, is basically just, you know, it updates the KV cache kind of and like and then every next token inference is still like, you know, the sheer sum of everything all the way. It's plus all the context. It's up to date. And you could, I guess, theoretically steer that with you probably replace that with your steering. The only problem is steering typically is on one layer, maybe three layers like like you did. So it's like not exactly equivalent.Mark Bissell [00:32:33]: Right, right. There's sort of you need to get precise about, yeah, like how you sort of define steering and like what how you're modeling the setup. But yeah, I've got the paper pulled up here. Belief dynamics reveal the dual nature. Yeah. The title is Belief Dynamics Reveal the Dual Nature of Incompetence. And it's an exhibition of the practical context learning and activation steering. So Eric Bigelow, Dan Urgraft on the who are doing fellowships at Goodfire, Ekt Deep's the final author there.Myra Deng [00:32:59]: I think actually to your question of like, what is the production use case of steering? I think maybe if you just think like one level beyond steering as it is today. Like imagine if you could adapt your model to be, you know, an expert legal reasoner. Like in almost real time, like very quickly. efficiently using human feedback or using like your semantic understanding of what the model knows and where it knows that behavior. I think that while it's not clear what the product is at the end of the day, it's clearly very valuable. Thinking about like what's the next interface for model customization and adaptation is a really interesting problem for us. Like we have heard a lot of people actually interested in fine-tuning an RL for open weight models in production. And so people are using things like Tinker or kind of like open source libraries to do that, but it's still very difficult to get models fine-tuned and RL'd for exactly what you want them to do unless you're an expert at model training. And so that's like something we'reShawn Wang [00:34:06]: looking into. Yeah. I never thought so. Tinker from Thinking Machines famously uses rank one LoRa. Is that basically the same as steering? Like, you know, what's the comparison there?Mark Bissell [00:34:19]: Well, so in that case, you are still applying updates to the parameters, right?Shawn Wang [00:34:25]: Yeah. You're not touching a base model. You're touching an adapter. It's kind of, yeah.Mark Bissell [00:34:30]: Right. But I guess it still is like more in parameter space then. I guess it's maybe like, are you modifying the pipes or are you modifying the water flowing through the pipes to get what you're after? Yeah. Just maybe one way.Mark Bissell [00:34:44]: I like that analogy. That's my mental map of it at least, but it gets at this idea of model design and intentional design, which is something that we're, that we're very focused on. And just the fact that like, I hope that we look back at how we're currently training models and post-training models and just think what a primitive way of doing that right now. Like there's no intentionalityShawn Wang [00:35:06]: really in... It's just data, right? The only thing in control is what data we feed in.Mark Bissell [00:35:11]: So, so Dan from Goodfire likes to use this analogy of, you know, he has a couple of young kids and he talks about like, what if I could only teach my kids how to be good people by giving them cookies or like, you know, giving them a slap on the wrist if they do something wrong, like not telling them why it was wrong or like what they should have done differently or something like that. Just figure it out. Right. Exactly. So that's RL. Yeah. Right. And, and, you know, it's sample inefficient. There's, you know, what do they say? It's like slurping feedback. It's like, slurping supervision. Right. And so you'd like to get to the point where you can have experts giving feedback to their models that are, uh, internalized and, and, you know, steering is an inference time way of sort of getting that idea. But ideally you're moving to a world whereVibhu Sapra [00:36:04]: it is much more intentional design in perpetuity for these models. Okay. This is one of the questions we asked Emmanuel from Anthropic on the podcast a few months ago. Basically the question, was you're at a research lab that does model training, foundation models, and you're on an interp team. How does it tie back? Right? Like, does this, do ideas come from the pre-training team? Do they go back? Um, you know, so for those interested, you can, you can watch that. There wasn't too much of a connect there, but it's still something, you know, it's something they want toMark Bissell [00:36:33]: push for down the line. It can be useful for all of the above. Like there are certainly post-hocVibhu Sapra [00:36:39]: use cases where it doesn't need to touch that. I think the other thing a lot of people forget is this stuff isn't too computationally expensive, right? Like I would say, if you're interested in getting into research, MechInterp is one of the most approachable fields, right? A lot of this train an essay, train a probe, this stuff, like the budget for this one, there's already a lot done. There's a lot of open source work. You guys have done some too. Um, you know,Shawn Wang [00:37:04]: There's like notebooks from the Gemini team for Neil Nanda or like, this is how you do it. Just step through the notebook.Vibhu Sapra [00:37:09]: Even if you're like, not even technical with any of this, you can still make like progress. There, you can look at different activations, but, uh, if you do want to get into training, you know, training this stuff, correct me if I'm wrong is like in the thousands of dollars, not even like, it's not that high scale. And then same with like, you know, applying it, doing it for post-training or all this stuff is fairly cheap in scale of, okay. I want to get into like model training. I don't have compute for like, you know, pre-training stuff. So it's, it's a very nice field to get into. And also there's a lot of like open questions, right? Um, some of them have to go with, okay, I want a product. I want to solve this. Like there's also just a lot of open-ended stuff that people could work on. That's interesting. Right. I don't know if you guys have any calls for like, what's open questions, what's open work that you either open collaboration with, or like, you'd just like to see solved or just, you know, for people listening that want to get into McInturk because people always talk about it. What are, what are the things they should check out? Start, of course, you know, join you guys as well. I'm sure you're hiring.Myra Deng [00:38:09]: There's a paper, I think from, was it Lee, uh, Sharky? It's open problems and, uh, it's, it's a bit of interpretability, which I recommend everyone who's interested in the field. Read. I'm just like a really comprehensive overview of what are the things that experts in the field think are the most important problems to be solved. I also think to your point, it's been really, really inspiring to see, I think a lot of young people getting interested in interpretability, actually not just young people also like scientists to have been, you know, experts in physics for many years and in biology or things like this, um, transitioning into interp, because the barrier of, of what's now interp. So it's really cool to see a number to entry is, you know, in some ways low and there's a lot of information out there and ways to get started. There's this anecdote of like professors at universities saying that all of a sudden every incoming PhD student wants to study interpretability, which was not the case a few years ago. So it just goes to show how, I guess, like exciting the field is, how fast it's moving, how quick it is to get started and things like that.Mark Bissell [00:39:10]: And also just a very welcoming community. You know, there's an open source McInturk Slack channel. There are people are always posting questions and just folks in the space are always responsive if you ask things on various forums and stuff. But yeah, the open paper, open problems paper is a really good one.Myra Deng [00:39:28]: For other people who want to get started, I think, you know, MATS is a great program. What's the acronym for? Machine Learning and Alignment Theory Scholars? It's like the...Vibhu Sapra [00:39:40]: Normally summer internship style.Myra Deng [00:39:42]: Yeah, but they've been doing it year round now. And actually a lot of our full-time staff have come through that program or gone through that program. And it's great for anyone who is transitioning into interpretability. There's a couple other fellows programs. We do one as well as Anthropic. And so those are great places to get started if anyone is interested.Mark Bissell [00:40:03]: Also, I think been seen as a research field for a very long time. But I think engineering... I think engineers are sorely wanted for interpretability as well, especially at Goodfire, but elsewhere, as it does scale up.Shawn Wang [00:40:18]: I should mention that Lee actually works with you guys, right? And in the London office and I'm adding our first ever McInturk track at AI Europe because I see this industry applications now emerging. And I'm pretty excited to, you know, help push that along. Yeah, I was looking forward to that. It'll effectively be the first industry McInturk conference. Yeah. I'm so glad you added that. You know, it's still a little bit of a bet. It's not that widespread, but I can definitely see this is the time to really get into it. We want to be early on things.Mark Bissell [00:40:51]: For sure. And I think the field understands this, right? So at ICML, I think the title of the McInturk workshop this year was actionable interpretability. And there was a lot of discussion around bringing it to various domains. Everyone's adding pragmatic, actionable, whatever.Shawn Wang [00:41:10]: It's like, okay, well, we weren't actionable before, I guess. I don't know.Vibhu Sapra [00:41:13]: And I mean, like, just, you know, being in Europe, you see the Interp room. One, like old school conferences, like, I think they had a very tiny room till they got lucky and they got it doubled. But there's definitely a lot of interest, a lot of niche research. So you see a lot of research coming out of universities, students. We covered the paper last week. It's like two unknown authors, not many citations. But, you know, you can make a lot of meaningful work there. Yeah. Yeah. Yeah.Shawn Wang [00:41:39]: Yeah. I think people haven't really mentioned this yet. It's just Interp for code. I think it's like an abnormally important field. We haven't mentioned this yet. The conspiracy theory last two years ago was when the first SAE work came out of Anthropic was they would do like, oh, we just used SAEs to turn the bad code vector down and then turn up the good code. And I think like, isn't that the dream? Like, you know, like, but basically, I guess maybe, why is it funny? Like, it's... If it was realistic, it would not be funny. It would be like, no, actually, we should do this. But it's funny because we know there's like, we feel there's some limitations to what steering can do. And I think a lot of the public image of steering is like the Gen Z stuff. Like, oh, you can make it really love the Golden Gate Bridge, or you can make it speak like Gen Z. To like be a legal reasoner seems like a huge stretch. Yeah. And I don't know if that will get there this way. Yeah.Myra Deng [00:42:36]: I think, um, I will say we are announcing. Something very soon that I will not speak too much about. Um, but I think, yeah, this is like what we've run into again and again is like, we, we don't want to be in the world where steering is only useful for like stylistic things. That's definitely not, not what we're aiming for. But I think the types of interventions that you need to do to get to things like legal reasoning, um, are much more sophisticated and require breakthroughs in, in learning algorithms. And that's, um...Shawn Wang [00:43:07]: And is this an emergent property of scale as well?Myra Deng [00:43:10]: I think so. Yeah. I mean, I think scale definitely helps. I think scale allows you to learn a lot of information and, and reduce noise across, you know, large amounts of data. But I also think we think that there's ways to do things much more effectively, um, even, even at scale. So like actually learning exactly what you want from the data and not learning things that you do that you don't want exhibited in the data. So we're not like anti-scale, but we are also realizing that scale is not going to get us anywhere. It's not going to get us to the type of AI development that we want to be at in, in the future as these models get more powerful and get deployed in all these sorts of like mission critical contexts. Current life cycle of training and deploying and evaluations is, is to us like deeply broken and has opportunities to, to improve. So, um, more to come on that very, very soon.Mark Bissell [00:44:02]: And I think that that's a use basically, or maybe just like a proof point that these concepts do exist. Like if you can manipulate them in the precise best way, you can get the ideal combination of them that you desire. And steering is maybe the most coarse grained sort of peek at what that looks like. But I think it's evocative of what you could do if you had total surgical control over every concept, every parameter. Yeah, exactly.Myra Deng [00:44:30]: There were like bad code features. I've got it pulled up.Vibhu Sapra [00:44:33]: Yeah. Just coincidentally, as you guys are talking.Shawn Wang [00:44:35]: This is like, this is exactly.Vibhu Sapra [00:44:38]: There's like specifically a code error feature that activates and they show, you know, it's not, it's not typo detection. It's like, it's, it's typos in code. It's not typical typos. And, you know, you can, you can see it clearly activates where there's something wrong in code. And they have like malicious code, code error. They have a whole bunch of sub, you know, sub broken down little grain features. Yeah.Shawn Wang [00:45:02]: Yeah. So, so the, the rough intuition for me, the, why I talked about post-training was that, well, you just, you know, have a few different rollouts with all these things turned off and on and whatever. And then, you know, you can, that's, that's synthetic data you can kind of post-train on. Yeah.Vibhu Sapra [00:45:13]: And I think we make it sound easier than it is just saying, you know, they do the real hard work.Myra Deng [00:45:19]: I mean, you guys, you guys have the right idea. Exactly. Yeah. We replicated a lot of these features in, in our Lama models as well. I remember there was like.Vibhu Sapra [00:45:26]: And I think a lot of this stuff is open, right? Like, yeah, you guys opened yours. DeepMind has opened a lot of essays on Gemma. Even Anthropic has opened a lot of this. There's, there's a lot of resources that, you know, we can probably share of people that want to get involved.Shawn Wang [00:45:41]: Yeah. And special shout out to like Neuronpedia as well. Yes. Like, yeah, amazing piece of work to visualize those things.Myra Deng [00:45:49]: Yeah, exactly.Shawn Wang [00:45:50]: I guess I wanted to pivot a little bit on, onto the healthcare side, because I think that's a big use case for you guys. We haven't really talked about it yet. This is a bit of a crossover for me because we are, we are, we do have a separate science pod that we're starting up for AI, for AI for science, just because like, it's such a huge investment category and also I'm like less qualified to do it, but we actually have bio PhDs to cover that, which is great, but I need to just kind of recover, recap your work, maybe on the evil two stuff, but then, and then building forward.Mark Bissell [00:46:17]: Yeah, for sure. And maybe to frame up the conversation, I think another kind of interesting just lens on interpretability in general is a lot of the techniques that were described. are ways to solve the AI human interface problem. And it's sort of like bidirectional communication is the goal there. So what we've been talking about with intentional design of models and, you know, steering, but also more advanced techniques is having humans impart our desires and control into models and over models. And the reverse is also very interesting, especially as you get to superhuman models, whether that's narrow superintelligence, like these scientific models that work on genomics, data, medical imaging, things like that. But down the line, you know, superintelligence of other forms as well. What knowledge can the AIs teach us as sort of that, that the other direction in that? And so some of our life science work to date has been getting at exactly that question, which is, well, some of it does look like debugging these various life sciences models, understanding if they're actually performing well, on tasks, or if they're picking up on spurious correlations, for instance, genomics models, you would like to know whether they are sort of focusing on the biologically relevant things that you care about, or if it's using some simpler correlate, like the ancestry of the person that it's looking at. But then also in the instances where they are superhuman, and maybe they are understanding elements of the human genome that we don't have names for or specific, you know, yeah, discoveries that they've made that that we don't know about, that's, that's a big goal. And so we're already seeing that, right, we are partnered with organizations like Mayo Clinic, leading research health system in the United States, our Institute, as well as a startup called Prima Menta, which focuses on neurodegenerative disease. And in our partnership with them, we've used foundation models, they've been training and applied our interpretability techniques to find novel biomarkers for Alzheimer's disease. So I think this is just the tip of the iceberg. But it's, that's like a flavor of some of the things that we're working on.Shawn Wang [00:48:36]: Yeah, I think that's really fantastic. Obviously, we did the Chad Zuckerberg pod last year as well. And like, there's a plethora of these models coming out, because there's so much potential and research. And it's like, very interesting how it's basically the same as language models, but just with a different underlying data set. But it's like, it's the same exact techniques. Like, there's no change, basically.Mark Bissell [00:48:59]: Yeah. Well, and even in like other domains, right? Like, you know, robotics, I know, like a lot of the companies just use Gemma as like the like backbone, and then they like make it into a VLA that like takes these actions. It's, it's, it's transformers all the way down. So yeah.Vibhu Sapra [00:49:15]: Like we have Med Gemma now, right? Like this week, even there was Med Gemma 1.5. And they're training it on this stuff, like 3d scans, medical domain knowledge, and all that stuff, too. So there's a push from both sides. But I think the thing that, you know, one of the things about McInturpp is like, you're a little bit more cautious in some domains, right? So healthcare, mainly being one, like guardrails, understanding, you know, we're more risk adverse to something going wrong there. So even just from a basic understanding, like, if we're trusting these systems to make claims, we want to know why and what's going on.Myra Deng [00:49:51]: Yeah, I think there's totally a kind of like deployment bottleneck to actually using. foundation models for real patient usage or things like that. Like, say you're using a model for rare disease prediction, you probably want some explanation as to why your model predicted a certain outcome, and an interpretable explanation at that. So that's definitely a use case. But I also think like, being able to extract scientific information that no human knows to accelerate drug discovery and disease treatment and things like that actually is a really, really big unlock for science, like scientific discovery. And you've seen a lot of startups, like say that they're going to accelerate scientific discovery. And I feel like we actually are doing that through our interp techniques. And kind of like, almost by accident, like, I think we got reached out to very, very early on from these healthcare institutions. And none of us had healthcare.Shawn Wang [00:50:49]: How did they even hear of you? A podcast.Myra Deng [00:50:51]: Oh, okay. Yeah, podcast.Vibhu Sapra [00:50:53]: Okay, well, now's that time, you know.Myra Deng [00:50:55]: Everyone can call us.Shawn Wang [00:50:56]: Podcasts are the most important thing. Everyone should listen to podcasts.Myra Deng [00:50:59]: Yeah, they reached out. They were like, you know, we have these really smart models that we've trained, and we want to know what they're doing. And we were like, really early that time, like three months old, and it was a few of us. And we were like, oh, my God, we've never used these models. Let's figure it out. But it's also like, great proof that interp techniques scale pretty well across domains. We didn't really have to learn too much about.Shawn Wang [00:51:21]: Interp is a machine learning technique, machine learning skills everywhere, right? Yeah. And it's obviously, it's just like a general insight. Yeah. Probably to finance too, I think, which would be fun for our history. I don't know if you have anything to say there.Mark Bissell [00:51:34]: Yeah, well, just across the science. Like, we've also done work on material science. Yeah, it really runs the gamut.Vibhu Sapra [00:51:40]: Yeah. Awesome. And, you know, for those that should reach out, like, you're obviously experts in this, but like, is there a call out for people that you're looking to partner with, design partners, people to use your stuff outside of just, you know, the general developer that wants to. Plug and play steering stuff, like on the research side more so, like, are there ideal design partners, customers, stuff like that?Myra Deng [00:52:03]: Yeah, I can talk about maybe non-life sciences, and then I'm curious to hear from you on the life sciences side. But we're looking for design partners across many domains, language, anyone who's customizing language models or trying to push the frontier of code or reasoning models is really interesting to us. And then also interested in the frontier of modeling. There's a lot of models that work in, like, pixel space, as we call it. So if you're doing world models, video models, even robotics, where there's not a very clean natural language interface to interact with, I think we think that Interp can really help and are looking for a few partners in that space.Shawn Wang [00:52:43]: Just because you mentioned the keyword

From the VLA (Very Large Array), Public Information Officer Corrina Jaramillo Feldman joins TJ to discuss a new learning facility that is under construction over at the VLA. There will also be an interactive visitors exhibit hall, along with the Next Generation Learning Center at the VLA. All this with TJ on News Radio KKOBSee omnystudio.com/listener for privacy information.

The universe is vast, mysterious, and constantly evolving. In this insightful astronomy podcast, we sit down with Dr. Sanjaya Poudel, an astronomer and researcher specializing in dwarf galaxies, dark matter, and galaxy formation. Originally from Nepal and currently a research professor at Yonsei University, South Korea, Dr. Poudel shares his journey into science, his fascination with astronomy, and how curiosity about the universe shaped his career. This episode dives deep into what the universe is, the Big Bang theory, and how our observable universe evolved over time. We explore complex yet fascinating ideas such as the flat universe vs curved universe, higher dimensions, and the expanding cosmos. Dr. Poudel explains dark matter, its role in galaxy evolution, and whether dwarf galaxies contain dark matter at all. A major focus of this astrophysics podcast is dwarf galaxies—their properties, formation, alignment around the Milky Way, and why they are considered the fundamental building blocks of the universe. We also discuss how astronomers observe galaxies using world-class telescopes like ESO-VLT, Gemini, VLA, and GMRT, and how astronomy drives technological development. Beyond space science, the conversation highlights challenges in science education and research in Nepal, the importance of promoting scientific thinking, and the future of astronomical research. This episode is perfect for anyone interested in cosmology explained, space science, and understanding how the universe truly works.

„Rodičovství je extrémně náročné, protože nasedá na už tak náročné partnerství. Sdílení mentální zátěže, která se k péči váže, zlepšuje nejen vztah mezi partnery, ale i vztah k samotnému dítěti,“ říká v Houpačkách psycholožka a psychoterapeutka Vlaďka Bartáková.Všechny díly podcastu Houpačky můžete pohodlně poslouchat v mobilní aplikaci mujRozhlas pro Android a iOS nebo na webu mujRozhlas.cz.

Na Malé Jizerské louce mezi Vlašským hřbetem a Středním jizerským hřebenem se pod čedičovým vrchem Bukovcem rozkládá osada Jizerka. Jméno jí dala protékající říčka Jizerka, která se po pár kilometrech mění v Jizeru. První písemná zmínka o osadě pochází z roku 1539. Proslavily ji drahé kameny a sklářská výroba. Dnes je tato osada díky horským chalupám a malebné krajině hlavně turistickým cílem.

Na Malé Jizerské louce mezi Vlašským hřbetem a Středním jizerským hřebenem se pod čedičovým vrchem Bukovcem rozkládá osada Jizerka. Jméno jí dala protékající říčka Jizerka, která se po pár kilometrech mění v Jizeru. První písemná zmínka o osadě pochází z roku 1539. Proslavily ji drahé kameny a sklářská výroba. Dnes je tato osada díky horským chalupám a malebné krajině hlavně turistickým cílem.

Na Malé Jizerské louce mezi Vlašským hřbetem a Středním jizerským hřebenem se pod čedičovým vrchem Bukovcem rozkládá osada Jizerka. Jméno jí dala protékající říčka Jizerka, která se po pár kilometrech mění v Jizeru. První písemná zmínka o osadě pochází z roku 1539. Proslavily ji drahé kameny a sklářská výroba. Dnes je tato osada díky horským chalupám a malebné krajině hlavně turistickým cílem.

Na Malé Jizerské louce mezi Vlašským hřbetem a Středním jizerským hřebenem se pod čedičovým vrchem Bukovcem rozkládá osada Jizerka. Jméno jí dala protékající říčka Jizerka, která se po pár kilometrech mění v Jizeru. První písemná zmínka o osadě pochází z roku 1539. Proslavily ji drahé kameny a sklářská výroba. Dnes je tato osada díky horským chalupám a malebné krajině hlavně turistickým cílem.

Na Malé Jizerské louce mezi Vlašským hřbetem a Středním jizerským hřebenem se pod čedičovým vrchem Bukovcem rozkládá osada Jizerka. Jméno jí dala protékající říčka Jizerka, která se po pár kilometrech mění v Jizeru. První písemná zmínka o osadě pochází z roku 1539. Proslavily ji drahé kameny a sklářská výroba. Dnes je tato osada díky horským chalupám a malebné krajině hlavně turistickým cílem.

Na Malé Jizerské louce mezi Vlašským hřbetem a Středním jizerským hřebenem se pod čedičovým vrchem Bukovcem rozkládá osada Jizerka. Jméno jí dala protékající říčka Jizerka, která se po pár kilometrech mění v Jizeru. První písemná zmínka o osadě pochází z roku 1539. Proslavily ji drahé kameny a sklářská výroba. Dnes je tato osada díky horským chalupám a malebné krajině hlavně turistickým cílem.

Na Malé Jizerské louce mezi Vlašským hřbetem a Středním jizerským hřebenem se pod čedičovým vrchem Bukovcem rozkládá osada Jizerka. Jméno jí dala protékající říčka Jizerka, která se po pár kilometrech mění v Jizeru. První písemná zmínka o osadě pochází z roku 1539. Proslavily ji drahé kameny a sklářská výroba. Dnes je tato osada díky horským chalupám a malebné krajině hlavně turistickým cílem.

Na Malé Jizerské louce mezi Vlašským hřbetem a Středním jizerským hřebenem se pod čedičovým vrchem Bukovcem rozkládá osada Jizerka. Jméno jí dala protékající říčka Jizerka, která se po pár kilometrech mění v Jizeru. První písemná zmínka o osadě pochází z roku 1539. Proslavily ji drahé kameny a sklářská výroba. Dnes je tato osada díky horským chalupám a malebné krajině hlavně turistickým cílem.

Na Malé Jizerské louce mezi Vlašským hřbetem a Středním jizerským hřebenem se pod čedičovým vrchem Bukovcem rozkládá osada Jizerka. Jméno jí dala protékající říčka Jizerka, která se po pár kilometrech mění v Jizeru. První písemná zmínka o osadě pochází z roku 1539. Proslavily ji drahé kameny a sklářská výroba. Dnes je tato osada díky horským chalupám a malebné krajině hlavně turistickým cílem.

Na Malé Jizerské louce mezi Vlašským hřbetem a Středním jizerským hřebenem se pod čedičovým vrchem Bukovcem rozkládá osada Jizerka. Jméno jí dala protékající říčka Jizerka, která se po pár kilometrech mění v Jizeru. První písemná zmínka o osadě pochází z roku 1539. Proslavily ji drahé kameny a sklářská výroba. Dnes je tato osada díky horským chalupám a malebné krajině hlavně turistickým cílem.

Na Malé Jizerské louce mezi Vlašským hřbetem a Středním jizerským hřebenem se pod čedičovým vrchem Bukovcem rozkládá osada Jizerka. Jméno jí dala protékající říčka Jizerka, která se po pár kilometrech mění v Jizeru. První písemná zmínka o osadě pochází z roku 1539. Proslavily ji drahé kameny a sklářská výroba. Dnes je tato osada díky horským chalupám a malebné krajině hlavně turistickým cílem.Všechny díly podcastu Výlety můžete pohodlně poslouchat v mobilní aplikaci mujRozhlas pro Android a iOS nebo na webu mujRozhlas.cz.

Na Malé Jizerské louce mezi Vlašským hřbetem a Středním jizerským hřebenem se pod čedičovým vrchem Bukovcem rozkládá osada Jizerka. Jméno jí dala protékající říčka Jizerka, která se po pár kilometrech mění v Jizeru. První písemná zmínka o osadě pochází z roku 1539. Proslavily ji drahé kameny a sklářská výroba. Dnes je tato osada díky horským chalupám a malebné krajině hlavně turistickým cílem.

The Chinese EV market is entering 2026 facing unprecedented challenges as subsidies end, competition intensifies, and market growth stalls. This episode analyzes what NIO and other Chinese automakers face in 2026 based on recent statements from XPeng CEO He Xiaopeng and NIO CEO Li Bin, both warning that next year's competition will be more brutal and bloody than 2025.On November 20, 2025, after launching the XPeng X9 extended-range version, He Xiaopeng stated: "I think every car company is on tenterhooks. Everyone wants to go far and achieve steady progress. A year ago we could hardly have imagined the changes we have now, and we can hardly imagine them a year from now. The only thing I can be sure of is that the competition will be even more brutal and bloody." The following day, NIO CEO Li Bin echoed this sentiment: "I agree with what Mr. Xiaopeng said. The intensity of competition in the Chinese auto market is actually increasing every year. Which year is not bloody? Which year is not cruel? Perhaps it will not be until 2035 that the pattern will truly stabilize."Three core realities will define 2026 for Chinese EV companies. First, the market has shifted from blitzkrieg to war of attrition. Li Bin explained that defeating competitors with a single move is extremely difficult, stating that being one year ahead in core technologies is already remarkable. He emphasized that success requires being one to two percentage points more efficient than competitors in every aspect, with no weaknesses allowed. This is a long-term marathon requiring comprehensive capabilities rather than breakthrough innovations.Second, the Chinese auto market is shrinking rather than growing. From November 1 to November 23, 2025, national passenger vehicle retail sales showed both year-over-year and month-over-month declines. The era of rapid growth has ended, replaced by competition for existing market share. With trade-in subsidies completely phased out and purchase tax subsidies cut in half starting January 1, 2026, market conditions will worsen in Q1 2026. Li Bin acknowledged that early reduction of trade-in subsidies eliminated the year-end boost effect in Q4 2025, with all NIO models except ES8, Firefly, and ET9 affected to varying degrees, explaining November's month-over-month delivery decline to 36,275 units.Third, product launch frequency has become a key battleground with divergent strategies. XPeng plans to launch seven extended-range models in 2026. HarmonyOS will release more than 20 new cars next year. Leapmotor, having achieved its 500,000 unit target 45 days early, is targeting 1 million deliveries in 2026 with multiple new models across A and D series. However, Li Bin announced NIO will only launch three new models in 2026, stating: "I don't think we have to keep releasing new models. Look at this year, we only have two models and they are selling quite well. We don't necessarily have to release them so frequently, and the team may not be able to manage it."XPeng's market capitalization has fallen nearly 30 percent since mid-November despite announcing ambitious physical AI initiatives at their early November Tech Day, including humanoid robot IRON, flying cars, second-generation VLA large model, and three Robotaxi models planned for 2026 launch. The company repositioned as a mobility explorer in physical AI and globally embodied intelligence company. In contrast, Tesla's Optimus robot demonstrations contributed to Tesla's market cap surging over 40 percent in the second half of 2025 despite showing similar or less advanced capabilities. This valuation gap highlights how US markets reward technology narratives while Chinese markets remain skeptical, valuing Chinese EV companies primarily as automakers rather than technology platforms despite comparable or superior technical capabilities.

PODZIMNÍ RACAP #1 je tady a my jdeme po všem, co DRUHÁ LIGA během podzimu otočila vzhůru nohama.

DRUHÁ LIGA BEZ FILTRU

Jihlava roztrhala Spartu B na kusy

Big changes are happening on Google—and most dealers aren't ready. The free vehicle listings that used to give you visibility in Search and Shopping are disappearing fast. In this video, I'll break down what's happening, why it matters, and how to pivot using VLA (Vehicle Listing Ads), optimized vehicle listings, and Google Business Profile posts.I'll walk you through:✅ What's replacing free vehicle listings✅ How to run VLA the right way (and not waste budget)✅ The power of syncing vehicle data to your GBP✅ The missing link between listings and actual lead generationWe're not here to chase clicks—we're here to move metal. If you're still relying on free exposure, you're already behind. Let's fix that.

Three Zbrojovka games and one Fisher FC game to tell you about this episode as we also have a day (and night) out in Ústí, praise Hrdina's heroics and Vachoušek's vigour, sympathise with Spanish (15 second) strikers, drink some imitation Bavarian hops and spend more money than was sensible in That London. 0.00 - intro 1.40 - Ústí nad Labem vs. Zbrojovka 9.00 - Hot? Or Not?! (feat. Fisher FC) 20.50 - Zbrojovka vs. Baník B & Opava 32.10 - Vlašim preview 42.10 - Beer of the Podcast 48.40 - Kroměříž preview 59.20 - outro

【节目简介】当液晶屏取代传统仪表你以为想放啥放啥但新问题是想不放啥能不放啥么本期《孤岛车谈》中，UX设计师June带我们了解这个看起来无限可能的工作中面临的纠结和挑战。2025 马自达6e2024 比亚迪Seal U2024 雷诺Megane2024飞凡F72015比亚迪秦2024极星4（行进中）2024极星4（静止）2025理想VLA司机大模型2025中国新能源车内饰比较【话题成员】罗新雨 底盘电子系统工程师June 用户体验UX设计师侯依萱 ADAS人因工程 工程师罗新雨微博@大众风Volkswind剪辑 猫又，PSC，罗新雨片尾曲 A quick glance by 新雨&Suno (2025)【时刻文稿】7:03 UI设计师需要先做到无我13:04 UI/UX设计和内饰设计的割裂32:15 UI/UX设计的凌乱来自什么？44:30 中国新能源车为何会有千篇一律的内饰设计54:48 字体管理的具体操作1:13:55 艺术VS平面设计VS汽车HMI设计【参考链接】【【专属】乘用车底盘系统开发 车辆动力学原理应用与正向开发工程实践 吴旭亭 系统构建车身动力学底盘知识体系书籍】#小程序://机械工业出版社旗舰店/商品/I4N8mLuPmjWkmRt【官网 车用动力电池系统设计与制造 中国汽车工程学会 电芯产品设计 电池系统产品设计 动力电池产品设计制造方法技术书籍】#小程序://机械工业出版社旗舰店/商品/P8isKji8jO5DkNc【汽车创新：前沿技术背后的科技原理】#小程序://机械工业出版社旗舰店/商品/7tltQzCQfJUWRVi【官网 广义车规级电子元器件可靠性设计与开发实践 左成钢 系统介绍汽车电子零部件的可靠性设计与开发 汽车电子 汽车工业技术书籍】#小程序://机械工业出版社旗舰店/商品/dBujAN68sEk1Rzl【智能驾驶：产品设计与评价】#小程序://机械工业出版社旗舰店/商品/Q8KWriuNDGdzlSs【官网 智能底盘关键技术及应用 线控执行 融合控制 失效运行 张俊智 智能底盘核心线控执行系统关键技术书籍】#小程序://机械工业出版社旗舰店/商品/5R5ZjdGhScib14A

Most v ohni

V novém díle ZAJÍC VE DRUHÉ LIZE #71

Všechno, co potřebuješ vědět o víkendu! ⚽ Vlašim po příchodu Bogase přepnula do “obranné melty”, jenže výsledky nikde - Chrudim byla blíž výhře a fanoušci mluví o ztrátě identity.

„Měla jsem hlubokou potřebu uvést Vlaštovku na jeviště. Přišla shůry a já ji v pokoře nechala projít skrze mne. Je to výjimečný text, který v lidech probouzí něco lepšího,“ vypráví Jitka Čvančarová, která inscenaci režíruje a taky v ní hraje. Na premiéru dorazil i její autor, španělský dramatik Guillem Clua. „Bála jsem se,“ přiznává Tereze Kostkové. „Na jevišti to musí být pravda, jinak to nefunguje. A on seděl někde v páté řadě mezi diváky, aniž by mu kdokoli překládal.“Všechny díly podcastu Blízká setkání můžete pohodlně poslouchat v mobilní aplikaci mujRozhlas pro Android a iOS nebo na webu mujRozhlas.cz.

„Měla jsem hlubokou potřebu uvést Vlaštovku na jeviště. Přišla shůry a já ji v pokoře nechala projít skrze mne. Je to výjimečný text, který v lidech probouzí něco lepšího,“ vypráví Jitka Čvančarová, která inscenaci režíruje a taky v ní hraje. Na premiéru dorazil i její autor, španělský dramatik Guillem Clua. „Bála jsem se,“ přiznává Tereze Kostkové. „Na jevišti to musí být pravda, jinak to nefunguje. A on seděl někde v páté řadě mezi diváky, aniž by mu kdokoli překládal.“

V novém díle ZAJÍCE VE DRUHÉ LIZE jsme řešili standardky, které rozhodly celé kolo!

Kdo padá ke dnu a kdo letí vzhůru? ⚖️ Kroměříž sbírá rány (standardky, vlastní chyby, nula bodů), zatímco Příbram zvedla kotvy a šlape. Jak moc je ve 2. lize důležitá „hlava“?

Dobrého a špatného rodiče nerozlišují jednotlivosti, ale schopnost napravovat své přešlapy. Je o tom přesvědčená psycholožka a psychoterapeutka Vlaďka Bartáková, podle které je velice důležité navázat s dítětem kontakt a napojení. „Ve chvíli, kdy se s námi dítě cítí bezpečně, tak je pak mnohem ochotnější k našemu káznění, k našemu vedení,” vysvětluje pro Český rozhlas Plus.Všechny díly podcastu Osobnost Plus můžete pohodlně poslouchat v mobilní aplikaci mujRozhlas pro Android a iOS nebo na webu mujRozhlas.cz.

Joe responds to Pastor Vlad Savchuk and his video Catholics vs Christianity. Transcript: Joe: Welcome back to Shameless Popery. I’m Joe Heschmeyer, and today I want to respond to a series of arguments against Catholicism made by the popular Evangelical pastor, VLA de Savchuk. And full disclosure, I’m not particularly familiar with him. I’ve seen a few clips of him, but it turns out he’s massively popular on YouTube, so I’m going to try to be as fair as I can to him. It’s clear that we run in kind of different spaces. His blog is mostly focused on, as far as ...

From the Very Large Array Senior Public Information Officer Corrina Jaramillo Feldman, comes in to discuss the latest technology being added to the VLA. She also talks about how the VLA works, the ins and outs of the facility, and what they have been learning about our Universe with TJ on News Radio KKOBSee omnystudio.com/listener for privacy information.

它们会跳舞、跑马拉松、在工厂打螺丝……人形机器人正在从科幻走向现实。马斯克说 Optimus 是 Tesla 的未来，国内创业者与资本也纷纷跟进，具身智能进入技术竞速新阶段。 据统计，2025 年仅前两个月，中国人工智能领域的投资交易额就已经逼近 2024 年全年的总额，达到数百亿规模，全球范围内，谷歌、微软等科技巨头也在加速布局具身智能赛道。 但——人形真的有必要吗？VLA 模型真的能「端到端」控制机器动作？我们距离真正的落地应用还有多远？ 本期《科技早知道》邀请峰瑞资本执行董事 刘鹏琦 与人大高瓴人工智能学院副教授 胡迪，与丁教和雅娴一起，聊聊这场尚未形成共识的技术狂奔。一起深入具身智能的关键分歧、成本难题与哲学困境。 关于 MiniMax Speech-02 模型 MiniMax 推出的全新升级的语⾳模型 Speech-02，在两项权威榜单：Artificial Analysis Speech Arena 和 Hugging Face TTS Arena 中，双榜位列全球第一。 Speech-02 具有⾜够泛化的模型能⼒，为用户提供超拟⼈、个性化、多达 32 语种的语⾳服务。 MiniMax Speech 也刚刚发布了技术报告，如果你对技术细节感兴趣，欢迎点击链接 (https://sourl.cn/S7Nyfg)查看，想用 MiniMax Speech 来打造属于自己的声音，欢迎点击链接尝试：国内 (https://sourl.cn/LEs5yE)；海外 (https://sourl.cn/xNYtux) Untitled https://media24.fireside.fm/file/fireside-uploads-2024/images/4/4931937e-0184-4c61-a658-6b03c254754d/OlbsRRQN.jpeg 本期人物 丁教 Diane，「声动活泼」联合创始人、「科技早知道」主播 刘鹏琦，峰瑞资本 执行董事 胡迪，中国人民大学高瓴人工智能学院 副教授 Yaxian, 「科技早知道」节目监制 主要话题 [03:07] 人形机器人热潮从哪来？Optimus、马拉松赛事与特斯拉的野心 [08:36] 机器人一定要人形么？人形 vs 实用性的争议 [14:23] 通用机器人=终极目标？从泛化能力聊起 [24:30] 触觉感知、力反馈、可靠性，机器人上肢发展的现实瓶颈 [36:08] 大模型的路线之争：端到端（VLA ）模型 vs 模块化控制路径 [47:03] 训练数据从哪来？仿真 vs 真机 vs 互联网模仿学习 [51:47] 人形机器人落地的不可能三角：成功率、通用性与成本如何取舍？ [59:12] 家庭机器人、可控核聚变、量子芯片，哪个会先实现？ 幕后制作 监制：Yaxian 后期：Jack 运营：George 设计：饭团 延伸阅读 VLA模型 VLA 是视觉 - 语言 - 动作（Vision - Language - Action）大模型的简称，是一种先进的多模态机器学习模型。它能让机器人接收环境信息和语言指令，经理解、推理与决策后，转化为动作指令来控制机器人运动，以实现与物理世界的交互。 内容研究志愿者招募 Hi 你好呀，这里是「科技早知道」内容研究志愿者招募。如果你是前沿科技行业的从业者（包括但不限于半导体、先进制造、计算机、AI、生物医药、航空航天等等），欢迎加入我们分享你在行业内的一手观察和见解。 你将有机会参与到节目的制作当中，你的知识和见解也可能成为未来节目的一部分！ 志愿者招募入口 (https://eg76rdcl6g.feishu.cn/share/base/form/shrcnKGHVbb4OdRJPfVuIGtitF8) 加入声动活泼 声动活泼目前开放全职设计师、商业发展经理、商业内容策划、内容编辑实习生、早咖啡内容研究实习生、社群运营实习生等6个职位，详情点击招聘入口 (https://eg76rdcl6g.feishu.cn/docx/XO6bd12aGoI4j0xmAMoc4vS7nBh?from=from_copylink) 商务合作 声动活泼商务合作咨询 (https://sourl.cn/6vdmQT) Untitled https://media24.fireside.fm/file/fireside-uploads-2024/images/4/4931937e-0184-4c61-a658-6b03c254754d/G8JTHkTU.png 关于声动活泼 「用声音碰撞世界」，声动活泼致力于为人们提供源源不断的思考养料。 我们还有这些播客：声动早咖啡 (https://www.xiaoyuzhoufm.com/podcast/60de7c003dd577b40d5a40f3)、声东击西 (https://etw.fm/episodes)、吃喝玩乐了不起 (https://www.xiaoyuzhoufm.com/podcast/644b94c494d78eb3f7ae8640)、反潮流俱乐部 (https://www.xiaoyuzhoufm.com/podcast/5e284c37418a84a0462634a4)、泡腾 VC (https://www.xiaoyuzhoufm.com/podcast/5f445cdb9504bbdb77f092e9)、商业WHY酱 (https://www.xiaoyuzhoufm.com/podcast/61315abc73105e8f15080b8a)、跳进兔子洞 (https://therabbithole.fireside.fm/) 、不止金钱 (https://www.xiaoyuzhoufm.com/podcast/65a625966d045a7f5e0b5640) 欢迎在即刻 (https://okjk.co/Qd43ia)、微博等社交媒体上与我们互动，搜索 声动活泼 即可找到我们。 期待你给我们写邮件，邮箱地址是：ting@sheng.fm 声小音 https://files.fireside.fm/file/fireside-uploads/images/4/4931937e-0184-4c61-a658-6b03c254754d/gK0pledC.png 欢迎扫码添加声小音，在节目之外和我们保持联系。 Special Guests: 刘鹏琦 and 胡迪.

Please meet Dr Anya Nugent … she is amazing … and she has some beautiful stories for us … let's hear all about unbelievably powerful Gamma Ray bursts and their host galaxies from an amazing Harvard and Smithsonian astrophysicist who uses incredible observatories like CHANDRA, XMM-Newton, ALMA, CHIME, MEERKAT, the VLA and even our old friend Hubble … to reveal new understandings of how our universe works.

This episode we welcome HH Mag. Trieu Huynh from the Bendigo Magistrates Court. At the age of one, Trieu and his family came to Australia as refugees from Vietnam. From this brave yet humble beginning, Trieu gained a scholarship to a private secondary school and ultimately completed a double degree in law/science with honours in genetics. Trieu has remained passionate about the law through every stage of his career. From the OPP and VLA, to sitting as a Magistrate, particularly in the Assessment and Referral Court, a therapeutic court that supports people who are mentally ill, have an intellectual disability, acquired brain injury, autism spectrum disorder or a neurological impairment. It is an amazing journey from escaping Vietnam in the middle of the night, to a fulfilling Life in the Law in Australia, and we are thrilled to bring it to you.www.greenslist.com.au/podcast

Our guest this week is Fabio Gehrlicher, Director of Market Expansion at Wandelbots. In the interview, they discuss the company's journey, focusing on its flagship product, Wandelbots NOVA, an agnostic operating system for robots. Fabio explains how NOVA simplifies robot programming, the integration of AI for path planning, and the benefits of simulation-based programming. The conversation also covers the target audience for NOVA, the architecture of the system, and the challenges of transitioning from simulation to real-world applications. Fabio shares insights on the ROI of using NOVA and the learning curve for new users, as well as Wandelbots' expansion into the US market and their upcoming showcase at ProMat 2023. Cohosts Steve Crowe and Mike Oitzman catch up on the news of the week, including financial stress at iRobot, and news that Google DeepMind is introducing two Gemini-based models to bring AI to the real world. Gemini Robotics, is an advanced vision-language-action (VLA) model that was built on Gemini 2.0. It added physical actions as a new output modality for the purpose of directly controlling robots. ### Our sponsor this week is Wandelbots. Simplify automation without limits. Wandelbots NOVA is the agnostic robotics platform that lets you program any 6-axis robot - whether coding from scratch or generating paths with real-world data. Test in simulation, deploy seamlessly, and optimize workflows across brands - without vendor lock-in. Smarter automation starts here. Visit https://www.wandelbots.com/ to learn more.

La cantante y actriz estadounidense visitó el foro de VLA y sus reacciones han dado mucho de qué hablar.See omnystudio.com/listener for privacy information.