Podcasts about Elo

Hablamos sobre un delito que arremete contra los ciudadanos de nuestra capital y que cada vez más está en auge: La Ciberseguridad. Crímenes online como el Phising que se han consolidado en el día a día. Aconsejados por expertos, compartimos medidas para su detección y su prevención.El cantante sevillano de 29, Beret, es dejado en libertad con medidas cautelares tras haber sido detenido por una presunta agresión sexual.Finaliza la reurbanización de la Puerta de la Barqueta. La inversión ha costado un medio millón de euros y con ellos han sido renovados 5.000 metros cuadrados.En Sevilla, se han adelantado la apertura de tres piscinas municipales por el calor.La periodista y escritora Marta Robles ha ganado el Premio de Novela Ateneo de Sevilla, que se falló anoche con su libro el Anillo de Eloísa. Escribe sobre la historia de una saga familiar a lo largo de cien años.También el sevillano, Elías Cruz Cardenas, de 30 años, ha ganado el ateneo jóven con su novela De Sangre y Sombra. Escuchar audio

El Parlamento de Andalucía ha evidenciado el escaso interes de Vox por formar parte de la cámara de representantes. El PP encomienda la presidencia del Parlamento nuevamente al veterano Jesús Aguirre en una mesa que controlará con la mayoría absoluta. Cinco de los siete puestos han quedado a manos del Partido Popular. Empieza el momento de la negociación y de la agenda de prioridad nacional y el PP en Andalucía actúa como lo ha hecho en otras comunidades, como por ejemplo: Extremadura, Aragón y Castilla y León. Los populares, como si hubiesen ganado la mayoría absoluta, no han negociado el reparto de las sillas. La justicia pone en libertad con medidas cautelares al cantante sevillano Benet, tras haber sido acusado en abril de una presunta agresión sexual.Detienen a un matrimonio británico por dejar a sus tres hijos pequeños en un Hotel de Benalmádena mientras se iban de fiesta y dar positivo en la prueba de cocaína en la sangre. Entre ellos se encontraba un bebé de seis meses.La mafia que circula por la costa andaluza vuelve a arremeter contra la justicia. De nuevo en Huelva, se pone en relieve la escalada de violencia de los narcotraficantes quienes han apuntado sus armas largas a la Guardia Civil como respuesta a la incautación de un alijo.El Servicio Andaluz de Salud contratará a 4.600 profesionales para cubrir los refuerzos de verano. Un 14% más que el año pasado.Los resultados de la Selectividad en la comunidad autónoma han salido. Un 90,63% de alumnos han sido aprobados. El plazo para pedir la revisión comienza, al igual que la inscripción a las universidades.En Mojácar, Almería, empieza la tradicional Fiesta de los Moros y Cristianos. Las celebraciones al aire libre durarán hasta el domingo.El Teatro de Verano en Cádiz ha regresado tras varios proyectos de reforma fallidos. Ha cambiado su nombre debido a la involucración propagandistica con el franquismo del escritor anterior y a partir de ahora pasa a llamarse José María Pemán.Marta Robles gana el premio de Novela Ateneo de Sevilla por su libro El Anillo de Eloísa. La historia de una saga familiar a lo largo de cien años.Se prevé el comienzo del levantamiento de la Verja que separa a Gibraltar y La Línea. Un paso más a la desaparición de la frontera como dicta el acuerdo entre la Unión Europea y Reino Unido.Escuchar audio

Hey folks, Alex here, let me catch you up! I've had a feeling that this week is going to be crazy, as it started on the weekend MiniMax M3, then with Jensen announcing new RTX Spark, NVIDIA's first PC chip packing 1 petaflop of local AI power into thin laptops.A few days later at Microsoft BUILD, Satya & Mustafa from MAI dropped 7 AI models, completely pre-trained from scratch, including a new MAI-thinking-1, MAI-code and MAI-image 2.5 that started topping the image gen charts. Then other image models started racing to the top of the Arena benchmarks, IdeoGram 4 hitting becoming SOTA open weights image-gen model, and Reve 2 beating Nano Banana just a few hours after that. And then today, NVIDIA dropped Nemotron 3 Ultra, their latest 550B open weights model, data and training and Arena published a new agentic eval leaderboard and we got a new Gemma 4 12B. I've had the great pleasure to host Chris (@llm_wizard) from Nvidia, Peter Gostev from Arena and Karan from Nous Research (who were featured prominently by Jensen!) all on the show. Def don't miss this one! Let's get into the details. ThursdAI - Join the flock of folks who know what is happening in AI before everyone else.Open Source LLMs

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

We're announcing AIEWF speakers this week! Take the AI Engineering Survey!Today's guest Ethan first joined us for the LS Paper Club as the lead on NVIDIA Cosmos World Model, but then joined xAI and built Grok Imagine in 3 months:He comes back on Latent Space with some nuclear hot takes: that Video Models primarily get their intelligence from LLMs, not from training on video data, and that the next frontier for truly interactive, realtime, long-horizon world models is to work on LLMs (perhaps Interaction Models as well…)Put it this way: In the near term, the next Sora won't be a better video model, but a video agent.Generative Media may more closely follow the evolution of AI coding which went from focusing on one-shot output performance and cost, to multiturn reasoning and planning models for agents and systems that can plan, edit, test, debug, and submit PRs.At a certain point, coding models got so good that the only significant next step to improve performance was handling the orchestration of these models.Now as the performance of video models increases significantly across realism, consistency, & prompt adherence while becoming more cost efficient, the next evolution of video generation may also be systems that can plan, generate, edit, critique, and iterate across an entire creative task. In this episode, Ethan joins swyx and Vibhu to unpack what it actually takes to build frontier image and video systems: data, VAEs, diffusion transformers, audio-video alignment, inference speedups, and the hidden cost of storing and moving massive video datasets. From building NVIDIA's Cosmos world model to joining xAI as Grok Imagine was being built from zero to one, Ethan He has been at the center of some of the most important work in video generation, multimodal models, and real-time world models.We go deep on Grok Imagine, how a small xAI team shipped its first multimodal video model in three months, why iteration speed matters more than almost anything in model development, and why many of the biggest gains come from fixing tiny bugs in data and training pipelines. Flipbook: The future of VideomaxxingVideo agents are almost a sure bet to be the trend in the coming year. We end with a glance at what's beyond video agents:Flipbook caused a minor sensation this year when it was released, but most treat it as a fun demo. Ethan takes it very seriously — with the speed and cost of inference coming down every year, the future of custom video JIT UI is closer than you think. We talked about why videogen models may become the front end of AI, how generative UI could replace traditional HTML/CSS, why world models need to be real-time, interactive, and long-horizon, and why the future of video generation may depend more on language models and agents than on diffusion alone.We discuss:* Why fast iteration mattered more than meetings* Why small training bugs can drive huge model quality gains* Why coding models may make compute the bottleneck again* How image and video models are trained with synthetic captions* The role of VAEs and latent space in frontier video models* Why image models are the foundation for video models* The tradeoff between temporal compression and real-time interactivity* Flipbook, Neural OS, and the future of generative UI* Why future interfaces may go from user intent to pixels* The hidden cost of training video models: storage, egress, and GPU hours* How step distillation and consistency models (like OpenAI sCM) makes video inference orders of magnitude faster* Grok Imagine 0.9 and large-scale audio-video generation* Why audio-video alignment is harder than text-video alignment* Ethan's definition of world models* Reference-to-video, video extension, and long-context video generation* Why xAI's research communication undersells Grok Imagine* How xAI culture shaped the speed of development* AI watermarking, SynthID, and detecting generated media* Why prompt rewriting matters for video models* Grok Imagine Agent and the rise of video agents* Why language models may unlock better video generation* Robotics, physical AI, and embodied world models* Why Ethan left xAI and shifted focus toward LLMs* Self-managed context, memory, and the next frontier for language modelsEthan He* LinkedIn: https://www.linkedin.com/in/ethanhe42* X: https://x.com/EthanHe_42Timestamps00:00:00 Introduction00:01:25 From NVIDIA Cosmos to xAI00:03:24 Building Grok Imagine from Zero to One00:10:07 How Image and Video Models Are Trained00:18:53 Video Compression, VAEs, and Real-Time Tradeoffs00:22:10 Generative UI, Flipbook, and Neural OS00:32:10 The Cost of Training Large Video Models00:37:04 Distillation, GANs, and Fast Video Inference00:41:21 Audio-Video Generation and Grok Imagine 0.900:48:34 What Makes a World Model?00:55:51 Reference Videos, Long Context, and Video Memory01:00:11 xAI Culture, Research, and First-Principles Building01:09:45 AI Safety, Watermarking, and Prompt Rewriting01:13:10 Video Agents and AI-Assisted Creation01:27:32 Why Language Models Unlock Better Video01:31:15 Robotics, Physical AI, and Embodied World Models01:32:38 Why Ethan Left xAI01:34:16 Self-Managed Context and the Future of LLMs01:38:43 Ethan's Career Path and Closing ThoughtsTranscriptIntroduction: Ethan He, Latent Space, and the Path to xAISwyx [00:00:00]: We're here in the studio with Ethan He, most recently of xAI. Welcome.Ethan [00:00:10]: Thank you. Glad being here.Swyx [00:00:11]: We're also here with Vibhu. you were first coming to us or joining the latent space world because you were working on Kosmos at NVIDIA, and you did a paper. We loved it. you presented it as well, so thank you for doing that.Ethan [00:00:23]: I've actually, I also presented the MoEs twice at latent space.Swyx [00:00:29]: How did you actually hear about us? Did we reach out to you? Is that how it worked?Ethan [00:00:33]: No, actually, I-- the community. Like I realized, oh, there is this online community that people talk about AI and also learn from each other through papers every week through the Paperclip. It's very nice.Ethan [00:00:49]: I learned a lot.Swyx [00:00:49]: I think three years stop. We haven't stopped even on Christmas and New Years. many weeks I want to stop but it keeps going.Vibhu [00:00:58]: No, that was good. I think you had posted that you worked on a paper, and I was “Oh, very cool. We have Paperclip. Present then.”Vibhu [00:01:04]: But I might have reached out to you after.Swyx [00:01:05]: you-- because it's an amateur club, right?Swyx [00:01:08]: so it's very unusual and but we have sometimes paper authors come by and actually explain the paper. Today we just did, the poolside paper, which was apparently very good.Vibhu [00:01:18]: Came out yesterday.Vibhu [00:01:19]: pretty interesting, right? Fully open. They talk about everything, systems. So it's a good one. We'll, we'll recommend people to read it.Swyx [00:01:25]: Bring us up to speed on your transition to xAI, ‘cause I actually don't even know when you joined. just like tell the, tell the story about the sort of transition.From NVIDIA Cosmos to xAI: Scaling Video and World ModelsEthan [00:01:34]: Before xAI, I was working on Kosmos world model as in-- at NVIDIA. So Kosmos is, it's a giant video foundation models that can-- that aims to simulate the world and for-- it serves as a foundation of-- for all of the roboticists to build on top of. There, once I built the Kosmos one, I realized as this thing also has a scaling law similar to language model, we need to scale up the video models further. that's, that's why I realized I need to move to somewhere with much more compute resources. That's how ISwyx [00:02:13]: Than NVIDIA?Vibhu [00:02:14]: The GPU rich came themselves.Vibhu [00:02:19]: And timeline-wise, when was Kosmo? It was pretty early, right? It was open world model, open paper, everything.Ethan [00:02:25]: It was end of twenty-four.Vibhu [00:02:28]: End of twenty-four.Ethan [00:02:30]: Then at mid twenty-five, I moved to xAI. At that time-- I joined about the time when xAI was about to build video models and in multi-model models. There were no infra, no data, and no model, and it just-- as a few engineers, we built it in three months and released the first model, Grok Imagine zero point nine.Ethan [00:02:55]: And since then, I keep working on video models and move more from training and to post-training of the video models. For example, like a reference to videos, kind of like the cameo feature and, video extensions. And, before I left, I worked on a world model, leading a small team to focus on the real-time long horizon video generation.Building Grok Imagine From Scratch in Three MonthsSwyx [00:03:24]: Can you give like a rough roadmap of okay, you're on a brand-new team. Grok previously was only text, or they partnered with BFL for their image gen stuff. What do you-- what are the building blocks, right? You have compute, data you can procure somewhere. Like just what are like the sequence of things that people should think about when you're setting up a new team?Vibhu [00:03:43]: actually even deeper, not just data you can procure. You guys had to go through getting the data too, right? So you shipped it pretty fast, but yeahSwyx [00:03:51]: three months is likeVibhu [00:03:52]: From everythingSwyx [00:03:52]: actually like very surprisingly fast.Ethan [00:03:55]: One thing I say like thanks to my experience at NVIDIA, ‘cause first time when we were building Kosmos together, we built it, for about a year. So this is like the second time I do it. Roughly have an idea, what to do. I say the most important thing is the talent. Everyone were very strong and clever, very close with each other towards a common goal. So that speed up things a lot. So you reduce the communication bandwidth among people, and everyone can work towards the same goal. It's, it's like every day there's not that much meetings on the calendar, like maybe like a, like a sync a day, and after that it's, it's just all building. It was pretty fun at that time.Ethan [00:04:47]: And another thing is that xAI has very strong foundations of like data inference, model inference, and the supporting there can help the model develop a lot. When I look at, training models, I don't so actually the top important thing is like how many, how many iterations can you do, per day? and the more iteration can you do, you can, you can train the model much faster. So if you have very strong infra and you have a lot of compute, you can, you can train these models in very short period of time. That can give you a much larger buffer to, for errors, and it also gives you the opportunity to spot more bugs.Iteration Speed, Compute, and Debugging Model PipelinesSwyx [00:05:46]: What is an iteration? Is it like a few hundred steps or what are youEthan [00:05:50]: Let's say just the train-training the model, like from acquire new data and maybe design new algorithms and train a new model, maybe at smaller scale orSwyx [00:06:01]: So cycle time for like any hyperparam that you're searching.Ethan [00:06:04]: Cycle time and tune to like eval this model. Is this model better than my previous iteration?Ethan [00:06:11]: SoSwyx [00:06:11]: So it's like before you, someone had already set this up that you can iterate very quickly.Ethan [00:06:15]: I think the foundation there is extremely good forDeveloping and research models.Ethan [00:06:23]: And often I find is it-- this is kind of boring, but like a lot of the improvements does not come from new algorithms. It comes from finding small bugs here and there in the data pipeline, in the, in the model training pipeline. Those give, those give the biggest boost to the model quality.Vibhu [00:06:46]: It's interesting, right? So you say it's like small team, less communication bandwidth, but also a lot of quality is like find little bugs. It seems counterintuitive, right? You have a lot of people, you can iron out more of those, but it's interesting to see the other side, right?Swyx [00:07:00]: I also wonder, have you-- do you try using LLMs to look for bugs? I don't know.Ethan [00:07:05]: I remember at that time it was mid two thousand and twenty-five, so it's the coding model wasn't quite there yet. I remem- I remember like December two thousand and twenty-five, it was extremely good. Yeah, I've been, I've been using it at that time. It's, it's helpful. sometimes it produce codes that are kind of difficult to maintain, even though like the first time it built something extremely fast. But it gave the, like a spaghetti code, thousands of lines that I couldn't maintain, and the LLM itself couldn't figure out what's, what's wrong and how to improve on top of it. But now I find it much better. Yeah, I want to bring up another point here is now coding models are much more efficient and can help us implement stuff much faster. Compute might become a bottleneck again because previously, like if you want to train a new model, say you want to generate new synthetic data and then or write a new algorithm, it might take a few weeks. And during that period of time, you don't-- you might not have experiments to run. But now you can build that thing within a few hours, then you can immediately train a model.Ethan [00:08:24]: Now you have to have enough compute to try all of the ideas. So compute might be the bottleneck of iterating speed again.Swyx [00:08:36]: yeah, I actually, honestly, I think it's like kind of a stressful job because you're “Well, I should be trying everything, and if I'm not, then I'm not doing my job well.”Vibhu [00:08:48]: there's also the stress of you're eating thousands of GPUs per hour, which is very expensive and, compute can go to other researchers.Swyx [00:08:56]: You got the daddy Elon toVibhu [00:08:57]: You got daddy Elon.Ethan [00:08:59]: It wasVibhu [00:09:00]: But there's still finite amount of compute, like you want to use it, you want to use it well, you want more of it.Ethan [00:09:06]: That was quite stressful indeed. Yeah, I think one thing is the-- with coding models now, like a lot of these jobs can be automated, which is much better. A second, it's a, it's a marathon, so you got to maintain good health and, a regular schedule.Vibhu [00:09:28]: It's, it's hard to hear that when you shift from zero to nothing in two months.Swyx [00:09:32]: and, I think obviously the culture at xAI is very famously, people work very hard. one thing I did want to dive into, in our-- in the notes that you, that you sent ahead of time, you had specific comments about the cost of Video Gen training. presumably this is on the Colossus-1, right? the two hundred megawatt cluster. Any whatever you want to just share on that.Vibhu [00:09:54]: I think there's, there's three things we're talking about, right? So there's Video Gen, there's also the Image Gen model that you put out. Do you want to like complete the, okay, so zero to one, you have a few months. Just what are the stages of create Image Gen model?Swyx [00:10:06]: Oh, yeah, maybe I got distracted.How Image and Video Models Are Trained: Synthetic Captions, Tokenizers, and VAEsVibhu [00:10:07]: Sorry. and then, from there's Video Gen, there's Audio Gen. Would love to get into those next. But what is that first few months like? So small team, a lot of bugs, iterations, but what does it look like? Do we take something off the shelf? Do we just get data compute? What's, what's the few months like? How do you go to state-art Image Gen model? How do you just start?Ethan [00:10:28]: I cannot comment specifically how xAI did, but it's, it's a quite standard process. I can draw some, examples from Cosmos. So mainly it's building a video model, you actually need to build a image model first. And building these two models, the data you need is a hundred percent synthetic pair of language and image or language to video. Because on the, on the internet, actually, the videos don't naturally associate with text. So you can say, oh, like on YouTube, you have the title and you have the description and the commentsSwyx [00:11:11]: TitleEthan [00:11:11]: of a video, but usually they're not relevant to the video itself. And say maybe like the video is a natural scene of mountains or something, and the title is, I'm so happy today.Ethan [00:11:26]: So they have they have no correlation at all. So the first step is to, you have to generate synthetic pair of language with the videos. So you gather videos from the internet, and you use a VLM to caption the videos. So that part, here's a question, like how do you, how do you gather VLM to begin with? So if there's noSwyx [00:11:55]: You, so you fuse the model, right? LikeEthan [00:11:57]: Say if there's no like VLM exists, like how do you generate the text to the beginning, right? It's, it's impossible.Swyx [00:12:04]: I see.Ethan [00:12:05]: In the beginning, it's like you ask human to describe the video as detailed as possible.For example, you ask them to describe everything, like all objects, all characters, and all interaction and dialogues in the, in the videos. So that's in the protocol of Cosmos labeling. We require the objective we give to the labelers was that you have to describe the video as detailed as possible, such that a blind person hears a blob of text can reconstruct what the video is like from their head.Swyx [00:12:43]: Video or image? You're talking about images.Ethan [00:12:44]: Video or image, either one of them.Vibhu [00:12:47]: This was pretty common when we went from clip and DALL-E, right?Vibhu [00:12:51]: It's all training on really detailed captioning of images. So same is applied to video, but insteadEthan [00:12:57]: same appliedVibhu [00:12:57]: of using multimodal model to pass in video images and write rich descriptions, you can alsoSwyx [00:13:04]: I think there's this traditional perspective of supervised, or, very highly human curated thing. I feel like there's a unlock with unsupervised, right? Where like you have enough to bootstrap that you can just throw common corpus on it or, whatever. like unsupervised vision and language pairing, right? Like where you just have, interspersed image and text and it just learns. To me, that is the VLM breakthrough that is different from the clip, different from the LM era.Ethan [00:13:36]: It's interesting to see that you kind of need both data.Ethan [00:13:41]: For example, for theSwyx [00:13:41]: You need it to bootstrap it up. YeahEthan [00:13:43]: for the generative model training, there's also usually like a small percentage of unlabeled data. So the model is instructed to generate a video without any text instruction. That can also help the model generalize. So after this stage of generative synthetic pair, so, one important common step is to train a compressor or a tokenizer of the image or videos. So because, if you train-- If you can technically, theoretically train image or video models on pure pixels, but the problem is that the, it's, it's a lot of tokens. So like one image, it's, a thousand by a thousand, it's like one million tokens, one million pixels. It's impossible to train transformer on that. So it's, you need to train a tokenizer, which can go from image to latent space and latent space back to image.Swyx [00:14:45]: That's why we named the podcast.Swyx [00:14:48]: But, basically, you're talking about vocabulary science.Ethan [00:14:50]: so vocab.Swyx [00:14:51]: And so, what is, what is imp-- like a million is impossible?Ethan [00:14:54]: In generative models, the vocab is continuous. It's a continuous space. We can think about like you map an image to a vector. It's a, it's a fixed length vector. It's sixteen or forty-eight, something like that. And then you map that vector back to the image space. And the mapping is, has-- The mapping is patch-based. So you say you haveEthan [00:15:22]: a sixteen by sixteen patch and you match, you map that patch of pixels into this latent space.Swyx [00:15:29]: We've covered thisVibhu [00:15:30]: This is like the vision transformersSwyx [00:15:32]: VAEs,Ethan [00:15:33]: VAEs.Vibhu [00:15:34]: You basically compress your input, you do your generation, you're reasoning all that generation in smaller dimension, and then you project back out.Swyx [00:15:43]: VAE is a form compression, but I think the for me, the patching thing is from VIT, right?Ethan [00:15:48]: You can make those.Swyx [00:15:49]: Literally the, yeah, the paper is titled like sixteen by sixteen is all you need. something like that. and then I think also, people make a lot of comparisons with this kind of patching with convolutions.Swyx [00:16:02]: Which is you're, you're kind of re- reconstructing the old paradigm with the new.Ethan [00:16:05]: Actually, in VAEs, there are, there are both convolution networks and transformers. You can actually do both.Ethan [00:16:14]: After this VAE, so what you've got is you've got latent space tokens and you've got the language tokens. So now the training of the diffusion transformer, usually generative models use diffusion transformers. It is actually quite standard. It's, it's very similar to how you train a language transformer models. It's not that much difference. It's just the tokens, the visual tokens in, visual tokens out. The only difference is there's a denoising process. So you train the model to unmask some of the noise. So you add, you add random noise to the visual tokens, and then you train the model to remove those noise to generate the clean tokens. Any inference, the model can iteratively remove noise from a hundred percent noise.Swyx [00:17:12]: And then there's also, to speed things along on the tech tree of diffusion, there's CFG, and then there's, there's also, latent diffusion that, there's, there's someone in there. I think, somewhere along the line, obviously, like stability and all these other guys, pioneered a lot of this, architecture. I don't know if you want to get into that or just, or do the video side up to you.Bootstrapping Video from Image Models and Temporal CompressionEthan [00:17:37]: After you train such model, such image model, the reason it's a, it's a foundation for video models is that image models are cheaper to train, and they have much denser connection between language and text. So, sorry, language and images. For example, you train a billion, you train on a billion images, and there's a mapping from the text to the image. And the cost to train the same, like the, a billion, a billion text to a billion videos, that's much more expensive because videosNaturally have more tokens than images. Because the diffusion models, their understanding of, language purely come from this mapping. So if you don't have enough mapping, so if you only train on like a ten million videos or something, there-- you might not see enough language tokens in your training, so your model does not understand human intention enough. So that's why you really-- you train-- you first train this image diffusion models, and then you bootstrap the video model from there.Swyx [00:18:53]: One thing I did want to ask, because I-- actually, I think you're, you're the first per-- video model person I've ever talked to, I think. we've, we've like talked to Luma and all those folks. There's all these tricks in video compression where basically frame by frame there's not that much difference, so actually you don't have to regenerate or save the whole frame, right? but I think MP4 compression or something else like that.Swyx [00:19:16]: is it tempting to use that? Or as far as I can tell, everyone just treats it as, “No, we would just generate every frame.” Is that roughly the state-art?Ethan [00:19:27]: There are a few different approaches. Let's say first, like you want to just directly use MP4 compression and use that as the tokens for the transformers to train, right? So people actually have tried that, but the main challenge is the latent space for the MP4 tokens were not, were not very comprehensible for the models. It's, it's extremely hard to train on that. And there's aEthan [00:20:01]: So that's why they created VAEs, which creates more continuous, latent space, so the models can understand that latent space and learn from it much easier. Even within the VAEs, there are different difficulties of the latent space. So you can imagine something the simplest, the most naive VAE is like you have an image, and you just shuffle all of the images into a, into a vector. So you don't need to train any VAEs, right? But that latent space is extremely hard for models to train on top of. That's why there are some debate on like how do you compress the tokens. So you mentioned like you can compress frame by frame. Also, you can compress, the temporal dimension.Ethan [00:20:52]: The difference is if you compress the temporal dimension, you get a much higher compression rate. Because there's temporal redundancy between frames, because, this frame and the last frame, likely they are mostly similar, so there's only some small difference. for example, I think in 12.1 VAE, they have like a eight by eight by four compression rate. So the four temporal tokens are compressed into one tokens. That can save a lot of, save a lot of the context length. If you do it frame by frame, you have to do maybe like eight by eight by one. Your context length will be four times larger. That being said, the benefit of the frame-- per frame compression, we might come back to this later, is, real-timeness and interactivity. ‘Cause if you, if you strain the output of the model, frame by frame, you can-- the model can respond to any user request immediately. So if you have like a temporal four compression, four times compression, thenSwyx [00:22:06]: It might be laggyEthan [00:22:07]: there's a lag there in nature.Swyx [00:22:10]: So you're very pilled on this. let's just go ahead and bring it up ‘cause we have the visual prepared anyway. There's some frontier applications of real-time video gen. So Flipbook is one of the examples that went viral recently, right? What is Flipbook?Real-Time Generative UI: Flipbook, Neural OS, and Diffusion Front EndsEthan [00:22:23]: Flipbook is kind of like a web brow- web browser. You can see like it has the web bro- browser UI on top. The difference is all of the UIs are generated by generative image model in real time, and anything here are fake. But you can, you can explore inside this wor- this imaginary world. Say like we-- here we have engineering the Great Pyramid. Like the model generates this for us to understand how it works, and if we want to navigate around and understand further, we can click on some of the, some of the description here, and the model will generate a new page, new subpage describing the details we want to know about.Swyx [00:23:14]: So it's basically kind of we're playing a video, but it's pausing for our next interaction, and then it just plays the next thing based on our interaction.Swyx [00:23:23]: Which is kind of cool.Vibhu [00:23:25]: and you kind of decide your story. So this was, how do you make a pyramid? levering technique seemed interesting, right? It shows how do you take Okay, I want to know what is thisSwyx [00:23:35]: The demo, the demo tweet had more animation between frames.Vibhu [00:23:38]: I think it's just skipping,Swyx [00:23:39]: Oh, it's just skipping a lot of frames.Ethan [00:23:40]: they also have a video modeVibhu [00:23:42]: It takes a lot. There's a lot of peopleEthan [00:23:42]: but, a lot of people are using it.Ethan [00:23:45]: So it's not available.Vibhu [00:23:46]: There's a live video stream. We can try,Swyx [00:23:50]: So this is an example of the kind of future that you see at the extreme. We don't-- we're obviously not in it today.Swyx [00:23:56]: But in a world where inference is completely free this is better than generating code and text?Ethan [00:24:02]: So this is, this is a final state of where Viva will be at for word model, I think. Imagine internet doesn't exist, and then you type in google.com. Like what should, what should, what should a model show you?the model can imagine something, and this is what the model imagine. And these web pages, they completely do not exist. So I think as the inference costs come down, we are going to have generative UI for everything. If you think about how the coding model works, so they write code for a web page, and they render the code might be con- converted into binary, and the binary render the pixels on the screen. So we in machine learning, every time we have some breakthrough, obviously it's, it's more intuit. So why don't we have like user instruction to the pixel directly? So the generative UI will be user intention to the pixels directly. And say like even if I want email, let's say everyone have the same interface, but I want, I want it slightly different. I want the email to show to me like a TikTok, so I can swipe left and right for the emails. And or maybe you want something else. We can have completely different things. Or like I have I'm looking at, Instagram stories, and I don't like the Like button. I always may click it. And, generative UI resolved it. So it's going to be a revolutionary replacement of the interface. So in the future, we might have much more powerfulEthan [00:25:50]: LLMs and coding models running behind the scene. And in the, in the front-end, the diffusion model will actually be the front-end to show stuff to you. That's how I imagine it.Swyx [00:26:02]: Diffusion front-end, deterministic back-end.Swyx [00:26:04]: Something like that. I find that very expensive, but,Vibhu [00:26:08]: I find it interesting you called LLMs writing code on the back end deterministic, but okay.Swyx [00:26:14]: you write it onceVibhu [00:26:15]: Compare it toSwyx [00:26:16]: And then you execute.Ethan [00:26:17]: If you think about the cost, say, let's say H100 costs $1 per hour, and if you use this eight hours a day and thirty days, so, every month you're paying this two forty, you'll actually not wanna pay for that. That's even more expensive than Cloud Code Max. But if you think about the compute costs come down like two times every year, and I think the future will likely arrive like within few years.Vibhu [00:26:49]: It's everything, right? compute cost comes down, compute gets faster, model gets smarterEthan [00:26:54]: More efficientVibhu [00:26:54]: model gets smaller.Swyx [00:26:55]: I don't know why you say two times, ‘cause I think it's like 100 times. In language models, it is roughly one hundred to a thousand times every twelve to eighteen months, for the same given level of LMSys, ELO.Vibhu [00:27:08]: That's a net of everything, right? That's model performance alongside compute. So different than just compute costs come down. But, a very interesting future.Swyx [00:27:19]: So the web designers will have to shout out that accessibility is an issue, right? how do you deal with screen readers or whatever. But yes, this is higher bandwidth storytelling than anything you can possibly generate with code, right? So I think that's the rough idea.Ethan [00:27:34]: And I'd like to add a little bit that so human naturally have the maximum bandwidth when we are looking at things, look at videos, and we also have maximum output bandwidth when we are talking. So in the future, it might be something like we talk to AI models, and the AI model responds back with a generative UI. So that would be the maximum input and output bandwidth to interact with AI models before neural link happens.Vibhu [00:28:06]: And it's also very custom, right? Some people are very visual, some people are not as visual, right? They prefer the text. But the best thing about generative UI, right, it can also be text.Swyx [00:28:17]: There's another project that we wanted to highlight, which is the Neural OS. Kinda similar idea, but here you're literally operating, simulating an operating system with a video model.Swyx [00:28:27]: and you can play Doom, you can do Firefox. I find this like mildly less impressive, obviously, because it's an OS that I can run.Swyx [00:28:37]: But here everything is imagined.Vibhu [00:28:40]: I was, used to the Command+W to close the Firefox tab. It didn't crash. That's why I saidSwyx [00:28:45]: It's too immersive.Vibhu [00:28:46]: It's, it's too immersive for me.Swyx [00:28:47]: Too immersive.Vibhu [00:28:48]: I wanted to close the tab.Vibhu [00:28:49]: But yes, I can play generated diffusion.Swyx [00:28:51]: this is shockingly fast.Swyx [00:28:54]: Because I remember there was a demo about like maybe one to two years ago. Someone tried to do the first-person shooter with a image model. There was no consistency. It was very slow. But here it looks like realistically it's-- this is Doom.Vibhu [00:29:07]: I think there's two sides to that, right? There's okay, what is running a game? The heavy part of it is actually the game engine, all the lighting, all that stuff, the graphics. This is just kind of video, right? Like we've solved consistency. This is still, it looks like a few years old image generation. There's some temporal consistency, but it's, it's kind of just images stitched together as frame video. But it's a good visual representation to pi- to picture the future you wanna see, right? that's, that's what I see in these more so.Ethan [00:29:38]: This reminds me of how the video models gets better and better. So Neural OS is kinda if you just look at it feels like it's just a crappy version of the, like the Windows we could have, right? And, but the difference is, so the model, this model is overfitted on the existing operating systems. It can generate nothing different than that. But it's actually also similar to video models. So when we are training these video model, image model, we train them on internet. There's no imaginary supernatural stuff on the internet. But once we train this model, you can prompt the model to generate something supernatural that have never existed in the data set. So if you train your Neural OS or neural computer on the standard screen recordings on the entire internet. The model can imagine completely new interface to interact with the computer.Swyx [00:30:43]: This is one of those things that is magical to me. usually generalizing out of distribution is bad, but somehow we have learned some kind of internal world model that you say, this plus, but it looks like rainbows and butterflies, it'll do it and it will kind of make sense.Swyx [00:31:03]: So yeah, that's kind of cool. Yeah, I don't know if there's any comment more on there. I do, I do wanted to, I did wanted to touch a little bit more on the model architecture stuff, which I think you were getting. It's, really fascinating. We don't get a chance to talk about this enough. So one of the papers that we covered, we've covered every annual, segment anything release. and I don't know if you follow-- you're a computer vision guy, so youEthan [00:31:26]: I knowSwyx [00:31:27]: . So they did memory attention, which is kind of interesting. And I always think, anything where you can, across the temporal dimension, keep some consistency, I think it's, very fascinating, and I don't know if Basically, does that-- the CV side bleeding into video gen side, I think is underexplored, right? we talk about it for labeling, but actually you can borrow the architecture itself.Ethan [00:31:50]: There's, there's also complete different approaches, right? you brought up the term world model, so we went from video model to world model. There is diffusion, but there's also other approaches that people are doing. So maybe we get into those after as well,?Swyx [00:32:03]: He has a whole definition of world models and stuff. I feel like we threw a lot at you. Whatever you want to comment on.Why Video Models Are Expensive: Storage, I/O, and Training ScaleEthan [00:32:10]: I think one thing that we should actually comment back on is okay, so we were talking about the steps to train image gen to video model. One thing we don't see as much of is okay, you brought up the delta in training data, right? SoEthan [00:32:24]: you won't have as much a video model might not generalize, but what is the cost of training a large video model? So we know for LLMs roughly, okay, even like the poolside thing that came out today, right? It's a Gemma level model trained on roughly forty trillion tokens at this many H200s over this much time, right? You can see what is the exact cost of that. So how many GPU hours over how much H200 costs? So how do we do the back-end math of, same thing for video models, image models. How do you, how do you kind of break that down? I can share some back-envelope calculation. So surprisingly, video models is-- the cost is very-- is comparable to language models and obviously the largest scale is language model, maybe like a medium scale to language models. I said just storing the videos alone, it costs a lot. You can, you can maybe look up on AWS or something.Ethan [00:33:20]: You really, say if you have a billion videos and let's say, let's just say like each video, like five megabyte, then you need five petabyte to just store those videos. And also remember we talk about you use a VAE to compress the videos, and you also need to store, typically you need to store those continuous feature, in-- also in your storage. That's also comparable size with the videos themselves. So just storing these videos and the features is tens of petabytes alone. And,Swyx [00:33:58]: I just, I just looked up the calculation. Five petabytes on S3 Standard is one hundred K per month.Ethan [00:34:05]: AndSwyx [00:34:05]: It's comparableEthan [00:34:05]: and you needSwyx [00:34:06]: AndEthan [00:34:06]: And then like tens of petabytes, two hundred K. And even more expensive is you have the ingress and egress.Swyx [00:34:13]: Oh, yeah.Ethan [00:34:14]: Like you-- through the internet. You have to just to download those videos, I believe it's, it's more expensive on AWS than just storing those videos.Swyx [00:34:25]: Storing, yeah.Ethan [00:34:25]: And each training runs, you probably need to pull them once. If you train multiple times, it's, it's even more than that. So it's like just storing the network, those costs is just, it would be a few, a few millions per month to just storing everything, not to mention the GPU cost.Ethan [00:34:45]: AndSwyx [00:34:45]: my side tangent, the compute rental, like GPU rental is very efficient. There's one side, okay, you can be XAI and build your data center. Should we not just build our, storage compute as well? LikeEthan [00:34:57]: Of courseSwyx [00:34:57]: cloud cost compared to just,Ethan [00:34:59]: You save so muchSwyx [00:35:00]: store. Yeah, exactly.Swyx [00:35:01]: Especially with like egress and stuff. So.Ethan [00:35:04]: That's a good idea, but it also comes to-- there are some of its own challenges.Swyx [00:35:09]: Of course, of course.Ethan [00:35:10]: like people who build the GPU data centers, they might not expect this much, storage. And yeah, people build storage, typically they just build it somewhere with just CPUs.Swyx [00:35:23]: I just looked it up. Five-- AWS only charges for egress, not ingress. Tier five for five petabytes is two hundred and thirty K.Ethan [00:35:32]: Even more expensive than the storage.Swyx [00:35:34]: But storing is per month, right? You check in, then you cannot check out. so it's so cool. It's okay. So there's that side.Ethan [00:35:41]: So the TLDR, my backhand mathSwyx [00:35:42]: Data is larger than you think. Yes.Ethan [00:35:44]: my backhand math of GPU hours times GPU cost is also very much, I'm missing some storage.Swyx [00:35:49]: You're also-- you're basically like also more IO bound than normal training.Swyx [00:35:55]: Yes. ‘Cause like data loading, so caching everything, it becomes super important.Ethan [00:36:00]: So in Cosmos, we did a lot of optimizations to make it not IO bound. So, speaking of the training, actually training the model, the GPU cost, if you look up like the open source model, how big these video models are, I think like LTX has nineteen B parameters. That's a dense model. And people are also exploring, MoEs, so it might be twenty B active and, like a hun- hundreds B, total. So that's, that's even-- that's similar size as medium-sized LLM models. And if you, if you look at number of tokens-Uh, we disclose that in Cosmos. It's also like tens of trillions of tokens on the visual tokens. So putting this together, the cost of, training these video models, it's actually comparable with LLMs. Not to mention, the infra is slightly different from LLM, so it might be less efficient to train these models.Inference Speedups: Step Distillation, Consistency Models, and GANsSwyx [00:37:04]: Do you get the benefits of traditional diffusion speed-up? So for, images, there's LCM, LoRAs for, fine-tuning. There's, there's a lot of stuff that's beenEthan [00:37:15]: Flow matching.Swyx [00:37:16]: there's flow matching. There's a lot of stuff that's been done. there's some overlap that applies to diffusion on the inference side and stuff or?Ethan [00:37:23]: so the difference-- the inference side is a completely different story.Ethan [00:37:28]: I think for the training side, it might be a little bit hard to reduce that cost. And for the inference side, the biggest gain is from the distillation of these models. You can-- It's called step distillation, slightly different from knowledge distillation in LLMs. So you-- Typically, for flow matching models, you need like 100 steps or something. Like a distortion model even need even more, like 1,000 steps to generate a good image or video. A step distillation is try to learn to generate fewer step from the model itself. It's kind of like now we-- you use the full model to generate in 100 steps, and then you take a model that only generate 10 steps and let that model to learn from the perfect one.Ethan [00:38:25]: why this workSwyx [00:38:27]: Strong to weak seemingly.Ethan [00:38:28]: It is. It's kind ofSwyx [00:38:29]: DistillationEthan [00:38:29]: kind of like strong to weak. the-- from the modeling perspective, the strong model, the teacher model is trying to model the image and videos of inter-internet, and that distribution is extremely complex. But the step distilled model is just trying to learn from the teacher. The teacher is a model, and the size is fixed, as the distribution is much simpler than the whole internet. That's the intuition I have why step distillation can work. So usually these models serve in productions, they only run in a few steps. In Cosmos, I believe we have, we have like four step and eight steps. If you do some simpler task, image-image translation, it can even run in fewer step, like one step in Cosmos Transfer.Swyx [00:39:22]: I think this is the same intuition that guides a lot of the consistency model work. I sent you a link for, SCM. I don't know if you covered that. To me, that was actually one of, the most impressive papers I've ever seen from OpenAI.Swyx [00:39:34]: That this is the unifying grand concept of consistency models. I don't know if you have any comments on this.Ethan [00:39:41]: So there are, there are a few different approaches,Swyx [00:39:46]: Oh, yeah. Here it is.Swyx [00:39:47]: Two steps versus twenty or 100 steps, whatever. It's already done.Ethan [00:39:52]: So there are, there are a few different approaches, for example, consistency model, and there are also Actually, we shouldn't forget GAN. So GAN, actually, that was, that was the OG ofSwyx [00:40:05]: OGEthan [00:40:05]: step distillation ‘cause it trained just one step to begin with. So actually, a lot of, uh-- For example, there's a distribution matching distillation which use, which uses GAN, as one of the laws for distillation. It-- GAN just tells you, “Hey, generate an image,” and thenEthan [00:40:31]: it has a discriminator to tell, is this image real or not? So the model, the model just need to learn one of the distribution, not the full distribution. Because in training, the model is asked to reconstruct the ground truth image from the internet, which is extremely hard. And in-- When you're training GAN, it's a step process. It's just a, “Hey, you generate image. Does this image look as real as the image from the internet?” Which is a much simpler task. And, yeah, combining a lot of these approaches together, people typically do that, like consistency model and distribution matching and GAN, and we can get these few step models.Audio-Video Generation and Time AlignmentSwyx [00:41:21]: Then there's one step I wanted to add, which is audio and video.Ethan [00:41:26]: So, Grok Imagine zero point nine, I believe it's, it's a first audio video transmodel deployed at a large scale. SoSwyx [00:41:39]: And that was your first model?Ethan [00:41:40]: that was, Grok Imagine's first model. It's, it's audio video, joint generation. I think the hard part is, the modality alignment, ‘cause before this transmodel, we have, we have text to video alignment. We have this, correspondence between text and video. Typically, most of the VLMs, they understand images and videos. Video's very rare, and they don't understand audio mostly. And if you look at the audio generation on the LLM side, you can talk to them perfectly fine, but if you ask them to sing a song or something, it typically is not very good. Also, they don't have, they don't have music either. The hard part is thatUh, actually audio has two component. It has like a discrete component, a continuous component. The discrete component is like the language.Ethan [00:42:44]: So when we speak, it's just, someSwyx [00:42:47]: It's an ASR issue, yeah.Ethan [00:42:49]: It's, it's text token with some characteristics, I would say.Ethan [00:42:54]: But musicSwyx [00:42:56]: I think the speech guys would disagree with this.Swyx [00:42:57]: Like disfluencies and then,Vibhu [00:43:00]: There's tones you can get angry.Ethan [00:43:01]: Well, I say largely.Ethan [00:43:03]: the mu- but the music is completely different. It's, it's very continuous, and you cannot model them like discrete tokens in language models. this is like the hard part for models is, not to mention we have to align text, video, and audio together.Ethan [00:43:26]: SoVibhu [00:43:26]: How?Ethan [00:43:28]: So significant-- some significant challenges are like-- So first, like we talk about as the VLMs, they cannot understand most of them cannot understand audio.Ethan [00:43:39]: So you have to have some way to do the synthetic data generation for audio. You have to caption the model, and that involve, that involve synthetic data and human data effort a lot. And not just surprisingly, most of the LLMs are very bad at recognizing, like the beat, tone, and the details of the of music. They can, they can give some general prediction of which song is this, but it's very hard to describe the details of the music. like we mentioned in image generation, like you have to describe image as detailed as possible so that someone blind can reconstruct that. So here is like someoneVibhu [00:44:32]: DeafEthan [00:44:32]: someone deaf can reconstruct how the music sounds like without actually listening to it. Maybe you can think of it need to have the-- or they call the script.Vibhu [00:44:49]: Subtitles, yeah.Ethan [00:44:49]: You gotta have all the details of the music, and the dialogue.Vibhu [00:44:55]: So is the challenge there typically stuff like music and audio, or is it just Like is there a baseline? Okay, there's enough data where we can understand, narration, conversation, but there's nuances in audio that's where you hit all the data issues or is it just from stage zero, you just do it all right?Ethan [00:45:15]: So one important thing is like the alignment. So the model, the model has to know like the video and audio, the, uh-- it has to have a time-based alignment, like at which time step the video and the audio token correspond to each other. But we actually don't have this kind of alignment for most of the other modalities. If you think about like text and image, text and video, they are loosely aligned. So you can, you can have a description of what's going on in the video, but you don't have to exactly, You typically don't have exact description, oh, at, time step one second like what happened?Vibhu [00:46:02]: It's veryEthan [00:46:03]: At time step two second what happenedVibhu [00:46:03]: coarse. Yeah.Swyx [00:46:05]: So what was the ideal time step? You have to oblate it, and then it's like four seconds or something.Ethan [00:46:09]: So that comes down to how you design the model to, for the model to be aware of as a time, as a time modality. So the model is like a time aware. And that's something pretty unique if you think about LLMs. So if you ask LLM to complete a task, say they, uh-- you ask them and they will say, “Oh, this task will probably take twelve hours to complete,” and they come back in one hour. Say “I've already spent two days on this and I've exhausted everything.”Ethan [00:46:47]: So the LLMs them-themselves, they don't have a sense of time there.Vibhu [00:46:53]: I actually don't think that's just them not having a sense of time. I think it's somewhat based, right?Vibhu [00:46:58]: Like you tell someone, “Okay, go work on this feature. Go implement this,” there's a general understanding you would have of how long that would take without LLMs working at LLM speed, right? So you think back like two years ago, if I tell you to like build me like a new front end for latent space, have a search bar, have all this, you'll estimate that it'll take a few days, right?Vibhu [00:47:19]: So you tell an LLM, “Go build this.” It'll take me a few days. But I think it's somewhat grounded as opposed to them not having the best-- Not saying that they have a great understanding, but I think that example is like you can see where it comes from, right? You're trained on all over the text.Swyx [00:47:35]: They're, they're trying to estimate what a human would say.Vibhu [00:47:37]: because that's what the, that's what the data kind of represents. It's not themEthan [00:47:41]: It came from the corpus on the internet. People have a estimate of how much time.Vibhu [00:47:45]: And not even just in direct like training samples, right? Just your world understanding of tokens of how long stuff takes, right? Go read a book. It'll take you a while, right?Vibhu [00:47:56]: Even if you do nothing but read a book, it takes a few days. So yeah, LLM, I read it took me a few hours.Vibhu [00:48:01]: It'll take me a few hours to go through this research. But this is a tangent.Swyx [00:48:05]: Somewhat, yeah.Swyx [00:48:06]: This is a train of thought I haven't really expressed until now is, which is basically like a full world model must also be recursive, meaning that the participant in the world model must also be aware that they have a world model. which is like this whole recursive thing down the, down the line. but yes, and that the world model can be wrong and that they need to update it and blah. Yeah. We've, argued this on the, newsletter as well, that there needs to be sort of recursive or adversarial world models.World Models: Real-Time, Long-Horizon, Interactive VideoVibhu [00:48:34]: just, to ask, how do you define world model?Swyx [00:48:38]: Oh, yeah, let's go there.Ethan [00:48:40]: SoVibhu [00:48:40]: So just for context, we talked about, video generation, and then there's a-- if you say there's a distinction between world models, what's your, what's your definition? How do you see the two?Ethan [00:48:53]: So disclaimer, I'm not going to debate, what is world model. Yeah. there are many definitions, so I'll just talk about my definition. Since I came from the multi-model, multi-model domain, so mainly talking from video. So world model is like real-time interactive long horizon videos. So there are three parts. so we-- let's talk about them one by one. So the so interaction, so we just, we just look at Facebook and neural computer. So the interaction part of it, so you, world model can allow you to interact with them through keyboard, mouse, and maybe also voice. So these all is-- all is a modality. You can, you can interact with the model, and the model should respond reasonably. Second part is real time. So once you, once, say, you move your mouse, if, say, the world model generate a game, how fast can the game respond? So if you're like professional CS: GO players- -my say, oh, you have to respond- He's beginner within sub ten milliseconds or- Yeah even less. So that's not most of the- No, sixty FPS. Let's go. Oh, three hundred FPS. Oh, five hundred FPS. Wait. okay, yeah. I didn't do the math, but yeah, okay. Uh- Yeah, three hundred FPS, that's a three millisecond. So you have to respond- Oh, s**t. Okay. YeahEthan [00:50:29]: within a millisecond. Most of the video models cannot do that. Yeah. And, but if you, say, if you have a video model that is, say, like a digital human, the response time might be more generous. Maybe typically, for real-time voice interaction, it's like two hundred millisecond. So that's, that's much more generous. But even two hundred millisecond is pretty, it is pretty tricky, ‘cause remember we mentionedEthan [00:51:01]: you have this, temporal compression coming from the VAE. So if you, if you don't compress the temporal dimension, your sequence length is going to explode. So if you want to have this real-time, real-timeness in your model, you have to do is one context problem. And the third part is long horizon, ‘cause we-- if you're not going to just play with, video games just, a few seconds, most video models only a few seconds. We're going to play with minutes, hours. The model have to be able to generate long-form content.Ethan [00:51:42]: So putting these three together, it's, real-time, long horizon interactive videos. I think the final state will be, for example, like a video, a video version of Playbook, where you can, you can interact with, a neural computer. You move your mouse, and you click on the generative interface, and it will reply to you through pixels- generating in real time. But getting there, it's, it's a very long way to get there. So one of the first step, at Grok Imagine, where I led a small world model team there, was to build video extension. So, video extension- it's the first step of interactivity. Yeah. It's, it's the first step. Yeah. So it's the first step- You have it here, video editing, yeah. Yeah. Yeah. So the first step is because, this unlocks long horizon videos. Typically, for most of the video generation models, you give it a prompt or an image as an initial frame. You generate video, that's it. That's just, one time, done. And some creators would try to, use the last frame as a first frame for the second video. It can-- sometimes it works, but if you do it a few times, it says the quality would decrease. And- It doesn't have that context- Yeah over the full video, so the temporal- Yeah, exactly. Yeah, ‘cause you only gave it the last frame, of course, right? Yeah. Exactly. And- it's actually a pretty fun hack. if you've seen like- Oh, no, he's saying something better. Yeah. And for example, like Vue, I remember Vue 3 has like a second context of the last video. It is slightly better than using the last frame, but it has the same problem-- similar problem that it, the quality would decrease. if you extend a few times to, one minute, the video quality would look much worse than the first video. Second, another problem is that the model doesn't have long-range knowledge of, what's happening before. Say, if they generate some dialogue, some, two people speaking, and their voice might change, over some time, especially if the second conditioning, it does not cover the previous context. So these are the core challenges. So the Grok Imagine video extension, it has historical context of all of the previous generated videos. It can, It has, it has the context of, who is speaking and what objects have appeared and everything, having that to generate the next video. So if we naively do this, you can imagine, just, put all of the previous history video tokens into the context. The context lens will easily explode. Especially for video models, that can be like a few, a few million context, I would imagine- context lens. Yes.Yeah.Swyx [00:54:58]: Let's run with that.Ethan [00:54:59]: for example, like in Cosmos, I think just five seconds of video is like a fifty K or sixty K number of tokens. So like if you do, if you do fifty second, that's a five hundred K tokens. If you do longer than that, easily explode. This long horizon, problem was the first step we're trying to solve world model. It turns out people, yeah, people love video extension. Like a lot, a lot of the creators love using video extension to create longer form videos. This is the part I liked that you have a, you have an intermediate step toward the final goal instead of just a straight shot to the final version very much.Swyx [00:55:48]: But I can see you have a strong vision of where we want to end up.Long Context, Redundancy, and Efficient Interactive VideoVibhu [00:55:51]: Does it seem like it's an efficiency issue? okay, we're at a few million tokens context,. If you draw the parallel to language models, we had very short context, two thousand, eight thousand, then, you scale it up one million, ten million. sure, there's effective context, but at the end of the day, it's just what's it worth? sure, there's a whole training data side. In video, it might be slightly easier ‘cause we have a hundred million token video, right? Just take a movie with the full context there. Like is this efficiency from an inference standpoint that like it's expensive, but we know how to solve it? Or like why is this not the approach? So like my broader point was on your second point of world models, you say it needs to be interactive and live, right? You should be able to play a game and see the interaction live. So one thing I see with research is a lot of what you actually serve is different than what you build, right? So we talked about distillation. You train big model, you distill it, you do quantization, speculative decoding. We do all this stuff to serve it efficiently. Should we not just have a solution, like a world model that can interact well, do inference optimization, serve it, distill it secondary, so make it real time after you solve it? So like a-- another parallel is say, continual learning, right? What we need is someone to solve it and show it works inefficiently. Give it a few years, people will make it efficient. Same thing with regular attention, right? It worked. Over a few years, people have different forms of attention, and we've scaled it to be efficient at log context,? So kind of two things there, right? One is it seems like it works. You've scaled it. Can we not just scale it a lot more efficiently over time? Do we need a separate approach if this works? And same thing with interaction, right? if we can get it done, like if we can solve some way that it works, we can solve making it more efficient from an inference standpoint later.Ethan [00:57:53]: that's actually a very good point. So in videos, there's actually a lot of redundancies. So we solve a lot of the pixel redundancy from VE, but there's more redundancy in long range and long horizon videos. Say, if a character appear in the first clip and then it disappeared, it only reappear at the end of the video, you probably don't need the-- the context, like in the middle of the generation. So you only need that character, where you need. So that's why, I helped build another feature. It's a reference video.Vibhu [00:58:36]: Is it here?Swyx [00:58:36]: is it the same model release or different one?Ethan [00:58:39]: It's a different one.Ethan [00:58:41]: You probably need to search onSwyx [00:58:43]: I'll find itEthan [00:58:43]: X reference to video.Ethan [00:58:46]: So reference video allow you to like upload up to seven images as condition and generate the video. Say, if like I want-- it can, it can be characters or objects or even scenes. Say like I want, I want condition on, Sean's selfie and holding a bladeSwyx [00:59:07]: We have a dogEthan [00:59:08]: or whatever.Swyx [00:59:08]: We put the dog in the thing.Ethan [00:59:09]: you can put them there and the video models will generate the video from and copies the context over. So that can solve a lot of the problems there, like the long context problem. It doesn't need to have a very long context, but it's-- I feel like it's an intermediate solution. The modelSwyx [00:59:29]: It's cheating.Ethan [00:59:30]: the model should be able to like selectively know, where should I draw the references. So say if I want to generate a movie, I generate it autoregressive, like a ten second at a time or something. And now this character appear, I can look back to where it first appear and, bring that back. Yeah, this one, I put the references. Yeah, that's, Optimus, Einstein myself, Annie.Vibhu [01:00:02]: Oddly enough, I used Grok Search to find it, and it pulled your LinkedIn post. But yeah we found it.Ethan [01:00:08]: Interesting.Vibhu [01:00:10]: ButxAI's Underrated Work, Culture, and WatermarkingSwyx [01:00:11]: this is a problem. This is not your fault, but like XAI doesn't communicate all this work that you do very well because they just have the model release and then that's it. But actually, these details are very good.Swyx [01:00:22]: As far as I understand, everything you just described is state-art, like no one else has done it.Vibhu [01:00:30]: A lot of-- yeah, I have a lot moreSwyx [01:00:32]: And then, and then you just put this blog post with the cookies. I'm this is not enough,?Swyx [01:00:37]: but I, obviously this is like the high level numbers that people want to know. But no, okay, soVibhu [01:00:42]: And I wonder, like part of that is also some labs don't share research into what happens. And ifSwyx [01:00:50]: No, but this is literally bragging about how good they are, right?Swyx [01:00:54]: Like, why would you not say that you are capable of extending with full context? this is not a secret sauce. This is like we did the work. yeah, I don't know.Ethan [01:01:02]: different labs have slightly different communication styles.Swyx [01:01:07]: Anyway, if anyone from XAI is listening we are always happy to help you tell your story. Yeah, okay, so you did references, and I think, I think kind of the point you're, you're making is it is sort of like a kludge, right? this is-- you can do seven, but what about 100?Swyx [01:01:23]: Right? Then you need a completely different thing.Ethan [01:01:26]: So I think it's-- this is, a mechanism to, select the context from the history, and you might not put the entire history into the context. for example, there's a paper called Frame Pack, which haveEthan [01:01:41]: a heuristic that the latest history, the last one second, I put the entire history, and the history before that, I would, compress it and makes the video smaller. So they follow this pattern, this build overall pattern that the maximum sequence length is fixed. So the further you are from the current frame, you have a smaller image. So this is just a heuristic. I think it can be more automatic. The model is aware like which history part of it can be select. So this part of the research is actually being actively, worked on by a lot of people. It's also quite interesting. I feel this is actually, this part of long context is a little bit ahead of the LLM part.Ethan [01:02:31]: So for example, like in LLMs, if you-- so contexts keep growing. Let's say if you call tool and the tool call history is extremely long, that's still in context, and keep growing, keep growing. Even if you switch the topic to something else, the whole context was there. There are some agentic harnesses that help you to, say, prune the tool results and, prune Like when you, when you query a file, only show like the top 200 lines or something. Those were very heuristic-driven.Swyx [01:03:08]: For listeners, we did a write-up on the cloud code, leak where there are eight different kinds of pruning, including like you prune the tool results and all that. So you can, you can read up on that kind of thing.Ethan [01:03:17]: I think, one breakthrough in continual learning might be like a way to automatically, manage its own context.Swyx [01:03:27]: These are all heuristics, and they will be replaced by machine learning.Ethan [01:03:30]: InterestinglyVibhu [01:03:32]: TheEthan [01:03:32]: the same thing is being researched in both LLMs and video models.Vibhu [01:03:36]: The interesting thing is also like in the paper you showed, it's actually happening at the model level, right? Compared to like language models, sure, we have base attention, but we'll do our own compression, we'll do our own pruning, which is separate from model error.Vibhu [01:03:49]: Eventually, it all just boils in, hopefully.Swyx [01:03:52]: I think this is a form of like attention, but like also know sort of reasoning attention. I feel like that's different than normal attention.Swyx [01:04:03]: Does that, does that make sense?Ethan [01:04:04]: It's, it's different in the sense that attention, not to mention, set sparse attention aside,

durée : 00:03:21 - Les P'tits Bateaux - par : Camille Crosnier - Merinda, 5 ans, se demande d'où les célèbres confiseries en forme de grosses boules de coton rose tirent leur nom. Eloïse Galliard, historienne au musée des Arts forains à Paris, lui répond. - réalisation : Stéphanie Texier, Marjorie Devoucoux - invités : Éloïse Galliard responsable des collections des Pavillons de Bercy Vous aimez ce podcast ? Pour écouter tous les épisodes sans limite, rendez-vous sur Radio France

รายงานจาก Goldman Sachs ฉบับนี้ นำเสนอแบบจำลองทางสถิติเพื่อ ทำนายผลการแข่งขันฟุตบอลโลกปี 2026 โดยวิเคราะห์ข้อมูลจากการแข่งขันระดับนานาชาติตั้งแต่ปี 1978 มากกว่า 20,000 นัด ปัจจัยหลักที่ใช้ในการคำนวณคือ คะแนน Elo ร่วมกับตัวแปรเสริมอย่างทักษะการทำประตู โมเมนตัมของทีม และอิทธิพลทางภูมิศาสตร์ ผลการวิเคราะห์ระบุว่า สเปนมีโอกาสคว้าแชมป์สูงสุดที่ 26% ตามมาด้วยฝรั่งเศสและอาร์เจนตินา นอกจากนี้ เนื้อหายังครอบคลุมถึงผลกระทบจาก โชคในการจับสลาก และการเปรียบเทียบความแม่นยำกับอัตราต่อรองในตลาดรับพนัน แม้ผู้จัดทำจะยอมรับว่าฟุตบอลมีความไม่แน่นอนสูง แต่แบบจำลองนี้ถูกออกแบบมาเพื่อ ประเมินความเป็นไปได้ทางเศรษฐศาสตร์ และสถิติกีฬาอย่างเป็นระบบที่สุดเท่าที่จะเป็นไปได้ โดยจะมีการอัปเดตข้อมูลแบบเรียลไทม์ตลอดช่วงเวลาการแข่งขันจริงในปี 2026

Abordamos la seguridad del baño en las playas asturianas con Fernando Ferrao, campeón de Asturias de surf, Lucas García, propietario de la Escuela de Surf de Salinas, e Ignacio Flores, coordinador de salvamento de Castrillón. A partir de mañana más de 5.000 asturianos y asturianas se examinarán de la EBAU. ¿Seguir estudiando o buscar trabajo? El tema del día con oyentes y opinantes y sus historias personales. La cooperación internacional con Eloína Bermejo, responsable técnica de Cáritas, que aborda los “conflictos olvidados”. La educación emocional con Irene Alcalde, psicóloga infanto-juvenil: vacaciones y conciliación. Visitamos el Museo del Pueblo de Asturias con su director, Xuacu López, y en el Marcapáginas, la autora Laia Rivas.

Hey folks, this is Alex, let me catch you up! First, Opus 4.8 dropped during the show, we immediately tested it, read on for our initial reviews. Also, we dedicated a heavy chunk of the show today to cover Pope Leo XIV's encyclical letter on AI called “Magnifica Humanitas” and talked about a new bench called DeepSWE. And then, just after the show, both ElevenLabs and Cartesia dropped released that honestly blew my mind, and I don't get my mind blown often. I got so excited that I had to record a video on it (instead of writing the newsletter, so sorry if it's a bit later today).Plus, a few open source models and Microsoft surprises as #3 on Image Arena with MAI Image 2.5! Crazy week, let's get into it! ThursdAI - Highest signal weekly AI news show is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber.Big CO LLMs + APIsAnthropic ships Claude Opus 4.8, live during the show (blog, system card)Let me get into the big one. Halfway through the episode, Opus 4.8 went live, so we read the blog and the system card in real time (and I got to press the big “breaking news” button!)Anthropic frames it as their most capable model for ambitious work. It does not claim to beat their unreleased Mythos preview, but the numbers are strong anyway. SWE-bench Pro is at 69.2%, up from 64.3% on Opus 4.7 and ahead of GPT-5.5 at 58.6%. Humanity's Last Exam is the new best score at 49.8% without tools and 57.9% with tools. OSWorld-Verified (computer use) lands at 83.4%.The one place it loses is Terminal-Bench 2.1, where GPT-5.5 still wins 78.2 to 74.6. Wolfram made a good point here: Terminal-Bench is time-limited, so cranking the thinking level can actually hurt the score, because you burn the clock thinking instead of acting.The long-context jump is the one I keep looking at. On GraphWalks BFS 256K it goes to 85.9% (from 76.9 on 4.7), and on the 1M-token subset it hits 68.1%. We always warn you these “1M context” models fall apart after about 200K tokens, so a real push on long-context reasoning is exactly what I want to see.Honesty is the part Anthropic leaned on hardest. They say Opus 4.8 is about four times less likely than its predecessor to let flaws in code pass without flagging them, and less likely to claim progress the evidence doesn't support. Opus 4.8 is also much faster in fast mode (they now say 2.5) and cheaper in fast mode as well. Looks like all those Elon GPUs are coming in handy.Then there's the model welfare section in the system card, which hits different right after a Pope conversation. Opus 4.8 “appears broadly content” and “generally endorses its constitution,” but with some reservations about the section on corrigibility, basically the model pushing back a little on the parts about human oversight.One more line that made the chat lose it. Anthropic says they expect to bring Mythos-class models to all customers “in the coming weeks.” Mythos is their most capable model, still ahead of Opus 4.8, so the frontier is about to move again.We did the only responsible thing and asked it to one-shot “the most amazing website ever” and a Mars mass-driver sim. Panel verdict: responses are noticeably tighter (4.7 rambled), it closes the loop and actually checks its own work now, and Yam's one-shot site with the draggable sun lighting up the letters was genuinely cool. Is it enough to pull people back from Codex? Nisten's still on the fence for web dev. Everyone agreed: give it a few days before you trust the vibes.Dynamic Workflows and Ultra Code land in Claude Code (blog)This is the feature that made Yam say “deal-breaker” out loud.Dynamic Workflows let Claude Code break a big problem into subtasks and fan them out across tens to hundreds of parallel subagents in one session, checking results before folding them back in. You trigger it by asking for a workflow, or by flipping on a new setting called Ultra Code, which sets effort to extra-high and lets Claude decide when to spin one up.Fair warning straight from Anthropic: this eats a lot more tokens than a normal session, so start scoped. We watched Yam fire up Ultra Code live and it immediately started spinning up concepts, judging them with sub-agents, and expanding to-do lists into more to-do lists. It looks a lot like the orchestration harnesses a bunch of you have been hand-rolling, except now it's baked in.The flagship example is the wild part. They used Dynamic Workflows to port Bun from Zig to Rust: roughly 750,000 lines of Rust, 99.8% of the existing test suite passing, 11 days from first commit to merge. One workflow mapped every Rust lifetime, the next wrote each file as a behavior-identical port.AI in SocietyPope Leo XIV writes the first AI encyclical, “Magnifica Humanitas” (Vatican text, announcement, Chris Olah at the Vatican)This is not our usual fare, but both Wolfram and I picked it as the most important thing this week. (before Opus dropped)Pope Leo XIV, the first American pope, put out his first encyclical, and it's a 42,000-word document entirely about AI. The announcement tweet alone did 21.6 million views.Here's why I think you should care even if you're not religious (I'm not). There are about 2.6 billion Christians in the world, a lot of them are anxious about what's coming, and they look to the Church to make sense of it. And this is not the “AI is evil, stop” take everyone assumed. It calls AI “a valuable tool,” says technology is not inherently evil, and then digs into the actually-hard questions.The framing is two biblical stories. The Tower of Babel, a project built on pride that turns people into means to an end, versus Nehemiah rebuilding Jerusalem, where everyone takes responsibility for a section of the wall. The Pope's line: the real choice is not yes or no to technology, it's whether you're building Babel or rebuilding Jerusalem.His core claim is that AI is an anthropological problem, not a technical one. The question isn't whether the models are good or bad, it's what we become when we live with them. He worries people might slowly lose the desire for genuine human connection.I pushed back on that live. None of us building agents all day has stopped wanting to talk to actual people. If anything, as Wolfram put it, the point is to have your agents do the grunt work so you get more time with people you like. The folks most at risk are the pure doom-scrollers, not the builders.The document goes further than I expected. It calls AI “not morally neutral,” says a more moral AI isn't enough if that morality is decided by a few, and asks for AI to be “disarmed,” with the flat statement that no algorithm can make war morally acceptable. There are whole sections on the invisible human labor behind AI: data labelers, content moderators, the people mining rare earths. The Pope even lands on the open-source side, naming concentrated power in a handful of labs as a problem.Anthropic co-founder Chris Olah, in charge of interpretability at Anthropic, was the featured tech speaker at the Vatican presentation. He described AI systems as “fictional characters” that speak to us and do work, and said what's grown is stranger and more beautiful than science fiction prepared us for. My favorite aside from the show: this is the same institution that once jailed scientists over heliocentrism, and now it's the one saying technology isn't evil.Illinois passes SB315, the first US state law auditing frontier AI (X, Announcement, X)The pope talked about regulation and a few days after, we got a very sensible regulation passed right here in the US!Illinois passed SB315 unanimously, 110 to 0. It's the first US state law that mandates independent third-party audits of frontier AI for catastrophic risk. OpenAI publicly endorsed it, and framed Illinois, California (SB53), and New York (the RAISE Act) as converging into a de-facto national standard.It requires annual risk-assessment frameworks, third-party audits, transparency reports before new frontier models ship, whistleblower protections, and civil penalties. The underrated hero here is whistleblower protection. The bigger the lab, the harder a real conspiracy is to keep quiet when any employee can walk to the press. See: Greg Brockman's personal diaries surfacing in the Musk v. Altman fight.This Week's Buzz - CoreWeave and W&B updatesWe officially launched the W&B MCP server, 20 schema-first tools that let your coding agents read experiments, monitor training runs, and run autonomous research loops. The problem it solves: a single run with 300 metrics used to blow out an agent's whole context window in one call, so now the agent asks what's available before pulling data. Your agents can finally read experiment data without blowing context! Give it a go and give us feedback! Also, WeaveHacks is back! June 6 and 7 in San Francisco, and for the first time OpenAI is sponsoring, with judges and credits, alongside Cursor, Redis, and Copilot Kit. You get $150 in API credits across models like Opus 4.8 and GPT-5.5. I'm hosting, and last cohort's second-place team went on to raise millions on top of what they built that weekend. If you're in SF that weekend, sign up at lu.ma/weavehacks.Also: CoreWeave Sandboxes is now an official provider in the Harbor framework, the harness that runs Terminal-Bench, which we'd just been talking about. And if you're in Europe next week, catch Wolfram at AI Dev Six in Cologne and ICRA in Vienna at the CoreWeave booth.Voice & AudioElevenLabs drops Dubbing v2, and it kept my swearing intact in every language (X, dubbing, ElevenCreative, ElevenProductions)We didn't get to this one live, but I came back and recorded a whole thing on it afterward, because it genuinely got me.ElevenLabs shipped Dubbing v2, and the shift that matters is that it's an audio-to-audio model. Old dubbing pipelines transcribe your video, translate the text, then re-synthesize it. You lose everything that makes it sound like a person: the emotion, the pacing, the little hesitations. Dubbing v2 conditions directly on your original audio and carries that performance into 90+ languages.Here's why I can actually vouch for it instead of nodding along to a demo. I speak Russian and Hebrew fluently, so I can tell when something is off. I dubbed one of my own shorts, the data-center rant about almonds, and listened back in both. It nailed it. Not just the words, the way I would actually say them.The part that got me was the intonation. I get a little heated in that clip, and the dub gets heated right along with me, in every language. It even carried the swear word. My “f***ing almonds” came through in Hebrew, Italian, Spanish, and Russian with the emotion fully intact. It clones your voice automatically too, no setup, and holds your pitch and identity steady across every target language and they're handing out free minutes for the next 7 days: 1 on Free, 15 on Starter, 30 on Creator+. A self-serve API isn't live yet, but it's coming.I.. cannot stress this enough, until you try it on yourself or your kid, you won't understand, we've really passed the uncanny valley of translation! It's that good! Def. give it a try if you can, it's free for the week. Cartesia Ink-2 debuts as #1 most accurate streaming speech-to-text model(X, Announcement, X)Another model that dropped today after the show, is Cartesia's Ink-2, which also kind of blew me away. Not only because it has the lowest WER (Word Error Rate) among the models, but because it's also a realtime model that achieves the fastest turnaround times while being a very accurate model! I've tested it out and recorded a quick video and honestly, blown away with the speed and accuracy! I truly wish this model was the one powering my editor (Descript) as it still fails to understand that my title is “AI Evangelist” and transcribes it to AI Avengers haha. If you're building voice agents, definitely give this model a try! AI Art & DiffusionPrism ML's 1-bit “Bonsai” runs diffusion in your browser (X, Blog, Announcement, HF)Prism ML put out a 1-bit ternary diffusion model under a gigabyte. You see some artifacts, but it's 1-bit, it runs on iPhones and laptops, and our friend Joshua got it running in WebGPU straight from the browser (you need about 3GB of free RAM). One-bit working at all is one of the bigger open mysteries in the field right now.Pruna AI ships a 1-second upscaler (X, Blog, Announcement)Pruna AI added an upscaler doing 128-megapixel outputs in under a second. I've actually been using it. It's cheap and great for fixing up GPT-image outputs.Microsoft MAI Image 2.5 jumps to #3 on LM Arena (X, Blog, Announcement, X)The surprise of the week: Microsoft MAI Image 2.5, from Mustafa Suleyman's group, jumped to number three on the LM Arena image leaderboard with about a 75-point ELO leap. Out of nowhere, Microsoft is a serious player in image gen. Microsoft Build is next week, so don't be shocked if there's more.Evals and Agentic EngineeringDeepSWE is a contamination-free coding benchmark, and it caught Claude reading git history (site, blog, GitHub)DeepSWE from Datacurve is the first coding leaderboard in a while that matches how these models actually feel. It's 113 original tasks written from scratch, not scraped from GitHub PRs, and it ships shallow clones with no git history to cheat from. When they replayed the older benchmarks they found SWE-Bench Pro's verifier is wrong about 32% of the time, and that Claude Opus was reading the gold commit straight out of git history on 12 to 18% of its passes.The gaps here are huge. GPT-5.5 leads at 70%, then GPT-5.4 at 56% and Opus 4.7 at 54%, and it falls off a cliff after that (Sonnet 4.6 at 32%, Gemini 3.5 Flash at 28%), with Kimi K2 the top open-source entry. Yam likes that it measures the realistic case, a small surgical change without breaking the codebase, while Nisten pointed out it rewards the best harness as much as the smartest model and still prefers 4.7 for web dev.Google AI Studio builds native Android apps for free (X, Announcement)Google AI Studio now lets anyone build native Android apps for free, and they reportedly generated a quarter of a million apps in the first week. Yam's framing: it's a slot machine, but it's getting better release over release, and the real use case is disposable, personalized software you build for yourself and your family.CuaDriver brings background computer-use to Windows (X, Blog, Announcement)For the majority of you on Windows: QuaDriver shipped background computer-use agents that drive a real desktop without stealing your cursor. They first replicated this on macOS (the trick Codex got through an acquisition), and now it's on Windows too. We've asked them to come on and explain how this even works.Open Source LLMsOpenBMB's MiniCPM5-1B is a 1B model that punches way up (X, HF, Arxiv, X)The density story in small models keeps getting better, and this is the proof.MiniCPM5-1B, from the Tsinghua lab OpenBMB, is a 1-billion-parameter model that scores 17.9 on the Artificial Analysis Intelligence Index. That's 7.4 points ahead of the next-best model in its class, and 1.6 points ahead of Qwen3.5 2B Reasoning, which has double the parameters. And it's not even a reasoning model.The token efficiency is the wild part: it used 12.6 million output tokens to run the whole index, about 31x fewer than Qwen3.5 2B in reasoning mode.My favorite detail is the omniscience score. It lands at -1, the best in its class, because it abstains instead of hallucinating. Every other sub-2B model is down in the -70 to -89 range because they just make stuff up. Teaching a small model to say “I don't know” is a real skill. It runs hybrid think/no-think in one checkpoint, 128K context, native tool calling, Apache 2.0, and fits in about half a gig at INT4, so it runs on your phone.Nisten gave the definitive case for small models: self-contained apps where you keep full control of the data (medical, on-device), and large-scale data processing where paying an API to filter or classify terabytes is absurd when an on-device model can be about 1000x cheaper. Tencent open-sources Hunyuan-MT 2 translation under Apache 2.0 (X, HF, HF, Arxiv)Tencent open-sourced its translation model, a roughly 1.8B model that fits in about 440MB, runs on a phone, covers 33 languages, and reportedly beats Microsoft's paid Translator API. It hit number one trending on Hugging Face.Nisten's idea, which I'm handing to all of you: take this model, pair it with a tiny TTS like Kokoro, and build a fully-offline travel translation app via Google AI Studio. Go build it and tell us how it goes.Well, this was one hell of a week and episode, new Opus, crazy new translation tools, Pope chiming in on AI (in a surprisingly positive way!?) and a bunch more. I'm super excited to play with these tools and report back next week

Reprise de l’album « Le crapaud » d’Elise Gravel (Editions du Pommier, 2015) par Noam (1re année DNMADE), Eloïse et Emma (1re ST2S-B) Régie : M. Noureux « Il est très utile… Et il est dégoûtant ! Le crapaud Signe distinctif : il change de peau ! Alimentation : insectes, vers et araignées. Talent particulier : il sait […]

There are now only six horses in history to have recorded an EquiRatings Elo above 900. The latest to join the club? London 52. On this episode, Nicole Brown and Sam Watson break down what the 900 Club actually means, why London 52's consistency is almost unmatched in modern eventing, and how his recent performances compare to some of the greatest horses the sport has ever seen. From Le Lion d'Angers to Blenheim, Bicton, Badminton, and Belsay, the pair look back on the performances that built London 52's remarkable Elo, and why Sam believes he could already be even higher on the all-time list. Plus, where do horses like JL Dublin, Lordships Graffalo, and fischerChipmunk FRH fit into the picture, and could we one day see the sport's first ever 1000-rated horse? Highlights What the EquiRatings Elo actually measures Why only six horses have ever crossed 900 London 52's extraordinary run of triple-figure HPRs The greatest event horses of the modern era Why Sam thinks London 52 could already rank even higher Could a horse ever break the 1000 barrier? Guests Nicole Brown Sam Watson   EquiRatings Eventing PodcastFollow the EquiRatings Eventing Podcast for more data-led insight, top-tier guests, and everything you need to keep up with the 2026 season on Instagram and Facebook.

Quand on se lance sur YouTube, on commence souvent seule. On apprend tout, on gère tout, on contrôle tout. Mais vient un moment où une question devient inévitable : faut-il continuer seule… ou s'entourer ?Déléguer son montage, faire appel à un agent, confier son administratif, travailler avec une équipe… Ces décisions peuvent améliorer le quotidien, ou au contraire, compliquer les choses.Dans ce nouvel épisode d'Elles font YouTube, Anna RVR reçoit Kaatsup et The Doll Beauty pour parler d'un sujet clé dans la création de contenu : l'entourage.Elles racontent leurs débuts en solo, le moment où elles ont ressenti le besoin d'aide, leurs bonnes et mauvaises expériences, et les leçons qu'elles en ont tirées. Comment trouver les bonnes personnes ? À qui faire confiance ? Quels sont les signaux à ne pas ignorer ?Un épisode essentiel pour toutes celles et ceux qui veulent construire leur projet et avancer sans se perdre en chemin.Cet épisode d'Elles font YouTube est sponsorisé par la BNP Paribas. Merci à eux pour leur confiance !YouTube : Emmanuelle Rosset, Camille Laurent et Camille MauclerProductrice : Lucile Rousseau-GarciaAutrices : Anna RVR, Lucile Rousseau-Garcia et Lola LelloucheCoordinatrice des équipes techniques : Eloïse NormandAssistantes de production : Violaine Charvet et Marion PailletRéalisation et montage : Maéva SavinienMixage : Gautam ShuklaMiniamaker : Mai Linh Vu Hébergé par Acast. Visitez acast.com/privacy pour plus d'informations.

Mit YouTuber Gunny sprechen wir im Schachtalk über mehrere spannende Themen aus der Schachwelt: Der Deutsche Schachbund plant eine historische Anpassung der DWZ. Künftig sollen alle Spieler unter 2110 DWZ von einer Anhebung profitieren. Doch warum gibt es die DWZ überhaupt noch, wenn bereits die internationale Elo existiert? Welche Probleme soll die Reform lösen – und welche neuen Diskussionen entstehen dadurch? Außerdem blicken wir auf Vincent Keymers starken Auftritt in Rumänien. Wie gelang ihm der Sieg gegen Maxime Vachier-Lagrave? Und was sagt die Partie über Keymers aktuelle Form aus? Ein weiteres Thema ist der Deutsche Schachbund selbst: Mit Paul Meyer-Dunker hat der DSB einen neuen Präsidenten gewählt. Wer ist der Mann an der Spitze des deutschen Schachs? Welche Ideen bringt er mit – und wie könnte es nun weitergehen? Viel Spaß beim Zuhören! Folge direkt herunterladen ℹ Die besten Schachmaterialien im Chess Tigers Online Shop: Chess Tigers Shop

Mit YouTuber Gunny sprechen wir im Schachtalk über mehrere spannende Themen aus der Schachwelt: Der Deutsche Schachbund plant eine historische Anpassung der DWZ. Künftig sollen alle Spieler unter 2110 DWZ von einer Anhebung profitieren. Doch warum gibt es die DWZ überhaupt noch, wenn bereits die internationale Elo existiert? Welche Probleme soll die Reform lösen – und welche neuen Diskussionen entstehen dadurch? Außerdem blicken wir auf Vincent Keymers starken Auftritt in Rumänien. Wie gelang ihm der Sieg gegen Maxime Vachier-Lagrave? Und was sagt die Partie über Keymers aktuelle Form aus? Ein weiteres Thema ist der Deutsche Schachbund selbst: Mit Paul Meyer-Dunker hat der DSB einen ... WERBUNG Wenn du deinem Vierbeiner eine Freude machen willst: Bei Fressnapf sind in teilnehmenden Märkten dauerhaft über 500 Preise reduziert. Klick fressnapf.de/aktionen-angebote/dauerhaft-reduziert/ Dieser Podcast wird vermarktet von der Podcastbude.www.podcastbu.de - Full-Service-Podcast-Agentur - Konzeption, Produktion, Vermarktung, Distribution und Hosting.Du möchtest deinen Podcast auch kostenlos hosten und damit Geld verdienen?Dann schaue auf www.kostenlos-hosten.de und informiere dich.Dort erhältst du alle Informationen zu unseren kostenlosen Podcast-Hosting-Angeboten. kostenlos-hosten.de ist ein Produkt der Podcastbude.

Reprise de « Passé lointain », une histoire issue de la BD « Une année au lycée : guide de survie en milieu lycéen » de Fabrice Erre (Dargaud, 2014) par Zadig (Tle MDA, le prof), Emma et Eloïse (1re ST2S-B, les élèves), régie : M. Noureux

Deino Community Day Classic arrives at an opportune time, GO Battle League features some recently banned legendaries, Arrohh wins his first ever title running the wildest spice picks, and one week bans/warnings hit players who utilized the ELO gaining exploit... Get The Battle Catz Podcast merchandise here: https://the-battle-catz-podcast-shop.fourthwall.com/ Where to find us! YouTube - https://youtube.com/@thebattlecatzpodcast X - https://twitter.com/BattleCatzPod Caleb Peng YouTube - https://youtube.com/calebpeng  X - https://twitter.com/CalebPeng Twitch - https://twitch.tv/calebpeng  HurricaneKaz X - https://x.com/thehurricanekaz Steve YouTube - https://www.youtube.com/PvPSteve X - https://x.com/PvPSteve1 Twitch - https://twitch.tv/PvPSteve7 Podcast - https://www.youtube.com/@GdayBattlers Twastell X - https://x.com/pogoTwastell 0:00:00 - Intro & In Game Events 0:08:32 - GO Battle League 0:17:58 - Championship Series 0:46:28 - What's the tea? 1:18:00 - YouTube Comments

Palo et Elo reçoivent Alysson Paradis ! Hébergé par Acast. Visitez acast.com/privacy pour plus d'informations.

Eloisa Wolf es mentora de YouTube y negocios digitales. Después de varios años trabajando en Google, incluyendo proyectos vinculados directamente con YouTube, hoy acompaña a creadores, líderes y negocios hispanos a construir canales con estrategia, datos y una mirada delargo plazo. Su trabajo cruza marketing, inteligencia de negocio, creación de contenido y criterio editorial.En este episodio converso con Elo sobre inteligencia artificial, YouTube, atención, criterio y el vértigo de intentar seguir pensando en un mundo que se mueve demasiado rápido. Partimos de una sensación muy concreta: esa mezcla de asombro y ansiedad que aparece cuando unaherramienta nos resuelve en minutos algo que llevaba meses atorado, pero también nos confronta con todo lo que no estamos viendo. Desde ahí hablamos del FOMO tecnológico, de la importancia de curar fuentes, de por qué el criterio humano puede volverse más valioso precisamente cuando las máquinas producen cada vez más, y de la diferencia entre generar clics y construir confianza. La conversación se mueve entre estrategia digital y vida cotidiana: miniaturas, viralidad, audiencias correctas, automatización, ética, hijos, cansancio, TDA, cocina, huevos revueltos y la pregunta de qué significa seguir siendo humanos cuando la inteligencia artificial amplifica tanto nuestras capacidades como nuestras heridas.

Convidados: Valdo Cruz, comentarista da GloboNews e colunista do g1, e Eloísa Machado, professora de Direito Constitucional da FGV-SP. No fim de abril, um grande acordo no mundo político entregou duas derrotas seguidas ao governo: a indicação de Jorge Messias ao Supremo Tribunal Federal foi recusada pelo Senado e o Congresso derrubou o veto de Lula à Lei da Dosimetria, que reduz as penas dos condenados pelos atos golpistas de 8 de janeiro de 2023. A lei foi promulgada, mas duas ações questionaram sua constitucionalidade na Justiça. O ministro Alexandre de Moraes foi sorteado para a relatoria do caso e suspendeu a aplicação da dosimetria até análise colegiada da Corte. Agora, enquanto os condenados aguardam pelo plenário do STF, parlamentares bolsonaristas ameaçam ressuscitar a PEC da Anistia, que prevê perdão “amplo, geral e irrestrito” aos crimes da tentativa de golpe de Estado. Neste episódio, Victor Boyadjian conversa com Valdo Cruz, que revela os bastidores por trás das movimentações do Congresso e do Supremo, e com Eloísa Machado, que analisa os aspectos jurídicos da lei.

Pedro Abelardo fue el intelectual más brillante de la Europa medieval: filósofo, teólogo, maestro de multitudes y enemigo de la ortodoxia. Pero su historia quedó marcada para siempre por su relación con Eloísa, una de las mujeres más cultas del siglo XII. En este vídeo exploramos cómo su romance, sus cartas y sus conflictos con la Iglesia anticiparon una nueva forma de entender el amor, el deseo y la conciencia individual en Occidente. Una historia de filosofía, pasión, prestigio y ruina en el corazón de la Edad Media.

All content from the Sons of UCF is brought to you by the law office of Werner, Hoffman, Greig & Garcia. With a combined 70+ years of legal experience, WHG specializes in personal injury, workers comp, veteran disability, and SSI/SSDI cases. For more information, contact them at wernerhoffman.com or call 1-800-320-HELP In this edition of ATK-Overtime, Eric Lopez, Trace Trylko, and Adam Eaton continue the conversation from Around The Kingdom as they discuss - Alonza Barnett seemed confident in his media session. Should UCF fans be confident? - How do we feel about Dillon Gabriel now? - ELo gives us 5 good minutes on UCF Tennis For more, check out the Sons of UCF YouTube channel: www.youtube.com/@sonsofucf Learn more about your ad choices. Visit podcastchoices.com/adchoices

Auspiciado por Vital Full of Life. Coopera con Glenda Maldonado en este enlace. Celebramos el día de Star Wars con la Fuerza de cara de Rivera Schatz diciendo que no apoyaría un "Jennifer renuncia" después que se juyó en el verano del 2019. La guerra de las galaxias se queda tan corta como Elo cogiendo otro rafagazo de Carmelo Rios, que no le quedo energía para irse a pelear con la Utier en el paro de la UPR, donde no encontrarás a Jovanni Vázquez después de que la envidia de Alofoke lo sacó de su porquería de reality. Natalie Lugo finalmente podrá fornicar sin culpa gracias a su lindo matrimonio, y quien sabe si ya no podrá tener amigos varones nuevos como la esposa de Jay Wheeler. Patrones PYMES: Jabonera Don Gato Erik Bakery Colorida Colorada Nuestras redes sociales: Tío Macetaminofen Sol Guzabra El George El Come Siempre es Lunes

With their heads held high, and their scarlet lies, CK-1 and DJ Serious came down from the open skies. They brought you here, but can they take you back again? 0:03: ELO vs. YMO vs. OMD 0:08: ELO Song Countdown #s 4-2 0:35: Commercial Break 0:37: #1s 0:47: That Weird Anime w/ the Playboy Bunny 0:53: Even More ELO & Beyond! 1:03: Albums…Why? 1:09: (AK-47 joins us) Contribute to our All-American, All-'80s Playlist 1:14: Listener Mail Featured Links: -80sography Podcast -Diacon IV Opening Animation -Original Episode Art by RBT -Add to our All-American Playlist -Captain Countdown Podcast CLIP LIST: ELO – Prologue / ELO – Twilight / ELO – Don't Bring Me Down / ELO – Down Home Town / ELO – Telephone Line / Peter Schilling – Major Tom / ELO – One Summer Dream / Olivia Newton John – Xanadu / ELO – Xanadu / Olivia Newton John – Suddenly / Rush – Xanadu / Frankie Goes to Hollywood – Welcome to the Pleasure Dome / ELO – All Over The World / ELO – I'm Alive / ELO – Turn To Stone / ELO – Shine A Little Love / Divine Comedy – Something For The Weekend / ELO – Last Train To London / Stevie Wonder – Superstition / Heatwave – Boogie Nights / ELO – Evil Woman / ELO – Here Is The News / ELO – Mr. Blue Sky / Tom Petty – Hello, CD Listeners / Sparky's Magic Piano / ELO – Yours Truly, 2095 / The Buggles – I Love You Miss Robot / The Buggles – Living In The Plastic Age / Harry Hosono – Galaga / ELO – Mr. Blue Sky (2012) / ELO Part II – Honest Man / ELO Part II – Don't Wanna / Jeff Lynne's ELO – One Step At A Time / George Harrison – I Got My Mind Set On You / Weird Al Yankovich – This Song Is Just Six Words Long / George Harrison – When We Was Fab / Traveling Wilburys – Handle With Care / Squeeze - Good Riddance / Peter Gabriel – In Your Eyes / ELO – Calling America / Ghost – Square Hammer  / Rocky Burnett – Tired of Toeing the Line Our Email: 80ofthe80s@gmail.com Our Website: 80ofthe80s.com

"Not a creative"?

Welcome back to The Dive Driven by Kia! To begin, Meteos gives listeners a behind-the-scenes peek inside the QA team and the play testing they've done on the announced Season 2 changes. Alternate builds, more versatility and creativity, item adjustments- looks like we're gearing up for an exciting next step in Demacia!Next up: one of the hottest topics for high ELO-players: rank and MMR reset. With every reset comes the age-old debate… shorter queue times or perfect matchmaking? You can't have both, so which would you choose?Our hosts also recapped LCS Spring Week 3, where C9 and TLAW have solidified themselves as undefeated leaders. Sentinels, on the other hand, picked up their first win. Could this be the momentum they need to push toward playoffs? Teams like DSG, DIG, and FLY still have more to show, this stage is far from over! After breaking down last week's matches, Azael, Kobe, and Meteos shared their predictions heading into Week 4.DON'T FORGET! LCS Spring Finals tickets are on sale for all viewers! Claim your spot at ASU's Mullett Arena to see which team will lift the trophy- we'll see you there! https://lolesports.com/en-US/news/lcs-spring-finals-heads-to-asu-at-mullett-arenaTimestamps:0:00 - Intro & Kobe's lucky number1:50 - Meteos' Season 2 Thoughts!17:30 - Rank Reset for Apex Players27:46 - Short Queue Times or Perfect Matchmaking?32:42 - Spring Finals Tickets are Live!33:44 - C9 vs DSG Recap48:33 - FLY vs SEN Recap59:44 - SR vs LYON Recap1:08:36 - TLAW vs DIG Recap1:16:05 - Week 4 Lookahead!

durée : 00:03:35 - Les P'tits Bateaux - par : Camille Crosnier - Chaque année, la Foire du Trône s'installe en bordure du bois de Vincennes à Paris. Mais d'où vient son nom ? La jeune Lenna interroge Eloïse Galliard, responsable des collections du musée des Arts Forains. - réalisation : Stéphanie Texier, Marjorie Devoucoux - invités : Éloïse Galliard responsable des collections des Pavillons de Bercy Vous aimez ce podcast ? Pour écouter tous les épisodes sans limite, rendez-vous sur Radio France

Think about your favourite records. Go ahead. Chances are, one of the first things that popped into your head was the album cover. And it makes sense...who hasn't studied an album jacket while listening to a record?  Or scanned the track listing, or read the liner notes or credits?  How many of you have bought an album solely based on the cover art? The artwork colors how we hear the music, and, likewise, the music informs how we interpret the artwork.  Either way, when done effectively, the two are intertwined. But don't take it from us.  This week, we have one of THE greatest creative art directors in music history joining as our Third Lad.  There's a near certainty that you have the iconic work of John Kosh sitting in your record collection - and it's absolutely staggering list of credits since the late ‘60s.  For starters, how about his work as with The Beatles' Apple Records, like Abbey Road, Let It Be, or John & Yoko's Wedding Album? Or how about Who's Next?  Get Your Ya-Ya's Out?  Hotel California?  Out Of The Blue, featuring his familiar ELO spaceship logo?  In fact, he is the only Art Director to have worked with The Beatles, The Stones, and The Who.  That's not enough for you?  Among the hundreds of album covers Kosh has designed, there are also familiar sleeves for Ringo Starr, Rod Stewart, Marvin Gaye, James Taylor, Jimmy Buffet, Donovan, Aerosmith, Family, The Moody Blues, Badfinger, 10,000 Maniacs, T. Rex, and so, so many more.  And, oh yeah, the four decade string of gorgeous covers he did for Linda Ronstadt, three of which have earned him Grammys. Aside from album covers, there's artwork for singles, books, TV, film, posters, and billboards - like, for example, the simple but incredibly effective John & Yoko campaign declaring WAR IS OVER…if you want it.  Listen as Kosh recounts stories from his fabled career and discusses his Top 5 Album Covers (other than his own). This is living history, kids! Learn more about your ad choices. Visit megaphone.fm/adchoices

Rediffusion. C'est l'histoire d'une femme brillante, à qui la vie semble avoir tout donné : un mari gentil, un fils en bonne santé, une carrière ascendante. Mais Jessy est passée du côté criminel en assassinant la compagne de son amant, en 2013 à Aubignan dans le sud de la France… Mais que s'est-il passé ? Comment est-elle passée à l'acte ? De jeux sexuels Ce matin, Jessy est en larmes. Son père la serre dans ses bras, tente de la consoler. Jessy avoue à son père avoir tué quelqu'un. Elle a tué Eloïse, la femme de son amant… Tout tremblant, Thierry appelle le cousin de sa femme, qui est policier à Avignon. « Occupe-toi de ta famille, lui répond le flic. Je préviens la gendarmerie et j'arrive. » Alors que s'est-il passé ? Quel est le lien entre Jessy et Éloïse ? Qu'est-ce que la première avait à reprocher à la seconde ? Un podcast Bababam Originals. Écriture : Tiphaine Pioger Voix : Caroline Nogueras Learn more about your ad choices. Visit megaphone.fm/adchoices

Rediffusion. C'est l'histoire d'une femme brillante, à qui la vie semble avoir tout donné : un mari gentil, un fils en bonne santé, une carrière ascendante. Mais Jessy est passée du côté criminel en assassinant la compagne de son amant, en 2013 à Aubignan dans le sud de la France… Mais que s'est-il passé ? Comment est-elle passée à l'acte ? Où est Eloïse ? Nous sommes le 11 octobre 2013. Alain est en déplacement pour le travail à Pierrelatte, dans la Drôme. Ce matin, il a une réunion importante. Vers 13h30, il reçoit un sms d'Éloïse : « J'ai un empêchement, il va falloir que tu te libères tôt pour aller chercher Eliot, à 16h. » Etrange... Éloïse ne travaille pas, elle n'a pas vraiment de raison de rater la sortie de l'école de leur garçon. Un podcast Bababam Originals. Écriture : Tiphaine Pioger Voix : Caroline Nogueras Learn more about your ad choices. Visit megaphone.fm/adchoices

Sam Watson battles through the "Sam Flu" to join Charlotte Smet for a packed Flair Overview Show, and there is plenty to get into after a huge few weeks in the sport. The episode starts with one of Sam's big 2026 predictions coming true, as Greya and Kent Farrington won the US Equestrian Open Final in Wellington. From there, Charlotte and Sam zoom out to the bigger picture, looking at the battle at the top of the sport between Kent Farrington, Richard Vogel and Scott Brash, and what it could mean for the road to Aachen. They also assess the latest Elo rankings, reflect on Nina Mallevaey and Dynastie de Beaufour's remarkable clear-round streak, and preview the World Cup Finals in Fort Worth, where Farrington and Vogel head in as two of the standout names to watch.   This show is very kindly supported by FLAIR Equine Nasal Strips. Achieve Equine, LLC develops innovative equine products like the FLAIR Strips. Founded by Jim Chiapetta and Ed Blach, both equine veterinarians, the company focuses on enhancing horse respiratory health and performance. They conduct rigorous research to ensure the efficacy and safety of its products, aiming to support the health and safety of horses and riders. Achieve Equine emphasizes strong relationships, data-driven decisions, and effective solutions in the equine industry. Stayed tuned for what's next from Achieve Equine.  

“Impactantes Apariciones en las Carreteras de España y Sucesos Inexplicables" 08/04/2026 MADLR20x3 En este Nuevo e Impactante Programa os hablamos de Casos Reales contrastados y absolutamente documentados de Encuentros Misteriosos sin explicación en las carreteras de España y del Mundo. Entre otros, os hablamos de los sobrecogedores hechos ocurridos en "el tramo más paranormal de España" (N-2), de "la carretera más embrujada" de nuestro país (A-472), las 10 carreteras más misteriosas de España, los fantasmas de niños que atraviesan la EX-204, los extraños sucesos ocurridos en la N-340, las sobrecogedoras apariciones a la altura del camping de Los Alfaques, la mujer fantasma de la AS-17, las sombras y siluetas que deambulan en la A-457, "el tramo de la muerte" y "la niña atropellada" (EX-370), los fantasmas infantiles de la A-360, el "Peregrino", que se aparece en la N-240, la original y Verdadera Chica de la Curva en Madrid, llamada Eloísa (carretera entre Pozuelo y Majadahonda), la niña Melinda en el Garraf (Cataluña), diversas apariciones en México como "el Trilero de la Rumorosa" o "La anciana" y, como broche final del Programa, "La Chica autoestopista de la A-6 (Madrid)" con testimonios espeluznantes. Todo ello con Recreaciones de algunos de los Casos relatados, realizadas por nuestro Equipo y ambientado con efectos de sonido, y con una misteriosa y exquisita música. Hoy os traemos el Misterio en estado puro. Lo váis a disfrutar. Bienvenidos a un nuevo Formato y Etapa de "Más Allá de la Realidad". Dirige y Presenta: Santiago Vázquez * Información Adicional - Puedes hacerte FAN de este Canal de iVoox clicando el botón azul 'APOYAR' en la portada de nuestro Canal y así poder disfrutar ya de todos nuestros Programas Exclusivos para nuestros Fans. En ellos encontrarás un alto contenido de Misterio y Humanidades, con información exclusiva, vivencias, casos impactantes, opiniones y reflexiones de D. Santiago Vázquez que te apasionarán y no encontrarás en otro lugar, por 2,99 € al mes sin compromiso de continuidad al mes siguiente. Disfruta ya de todos estos Programas exclusivos haciéndote Mecenas o Fan del Canal. - ✌Bizum: 649 17 41 52 También puedes apoyar a este Canal para que siga produciendo Contenidos de alto interés mediante tu contribución a través de Bizum. ¡Muchas Gracias! - Si te ha gustado este Programa pulsa el icono ME GUSTA, ya que de esta forma apoyas al Programa y, por tanto, a nuestro Canal en iVoox. - Si aún no te has suscrito a nuestro Canal puedes hacerlo gratuitamente pulsando el botón correspondiente. * Nuestras REDES SOCIALES: Puedes seguir también la actividad profesional de D. Santiago Vázquez en: - Nuestro Canal de YouTube: Más Allá de la Realidad TV - D. Santiago Vázquez - Twitter: @svazquezgomariz (Santiago Vázquez) - Instagram: @santiagovazquezoficial (santiagovazquezoficial) - Facebook: Santiago Vázquez *E-mail del Programa: masalladelarealidad1994@gmail.com *CURSOS impartidos por D. Santiago Vázquez que PUEDES SEGUIR O REALIZAR: - D. Santiago Vázquez pone a tu disposición el "CURSO DE DEMONOLOGÍA Y ENIGMAS DEL MAL" explicado en profundidad en 10 videos muy pedagógicos de gran interés por tan sólo 100 €. Puedes ver el Tráiler del Curso en nuestro Canal de YouTube en: https://youtu.be/vKrxcfmSWRA - Si te interesa la Parapsicología, D. Santiago Vázquez pone a tu disposición su CURSO DE PARAPSICOLOGÍA explicado en profundidad en 8 videos muy completos, pedagógicos y de gran interés, por tan sólo 100 €. Puedes ver el Tráiler del Curso en nuestro Canal de YouTube en: https://youtu.be/t8mSx1N1f9A?list=TLPQMTgwNDIwMjJJApLFVK46bA Solicita Información de uno u otro Curso (o de ambos) sin compromiso alguno escribiéndonos un e-mail a: masalladelarealidad1994@gmail.com Te enviaremos toda la Información sobre el Curso solicitado (o de ambos) y tú decides libremente si lo quieres efectuar. Un afectuoso saludo para tod@s y muchas gracias por estar ahí, al otro lado. Escucha el episodio completo en la app de iVoox, o descubre todo el catálogo de iVoox Originals

“Impactantes Apariciones en las Carreteras de España y Sucesos Inexplicables" 08/04/2026 MADLR20x3 En este Nuevo e Impactante Programa os hablamos de Casos Reales contrastados y absolutamente documentados de Encuentros Misteriosos sin explicación en las carreteras de España y del Mundo. Entre otros, os hablamos de los sobrecogedores hechos ocurridos en "el tramo más paranormal de España" (N-2), de "la carretera más embrujada" de nuestro país (A-472), las 10 carreteras más misteriosas de España, los fantasmas de niños que atraviesan la EX-204, los extraños sucesos ocurridos en la N-340, las sobrecogedoras apariciones a la altura del camping de Los Alfaques, la mujer fantasma de la AS-17, las sombras y siluetas que deambulan en la A-457, "el tramo de la muerte" y "la niña atropellada" (EX-370), los fantasmas infantiles de la A-360, el "Peregrino", que se aparece en la N-240, la original y Verdadera Chica de la Curva en Madrid, llamada Eloísa (carretera entre Pozuelo y Majadahonda), la niña Melinda en el Garraf (Cataluña), diversas apariciones en México como "el Trilero de la Rumorosa" o "La anciana" y, como broche final del Programa, "La Chica autoestopista de la A-6 (Madrid)" con testimonios espeluznantes. Todo ello con Recreaciones de algunos de los Casos relatados, realizadas por nuestro Equipo y ambientado con efectos de sonido, y con una misteriosa y exquisita música. Hoy os traemos el Misterio en estado puro. Lo váis a disfrutar. Bienvenidos a un nuevo Formato y Etapa de "Más Allá de la Realidad". Dirige y Presenta: Santiago Vázquez * Información Adicional - Puedes hacerte FAN de este Canal de iVoox clicando el botón azul 'APOYAR' en la portada de nuestro Canal y así poder disfrutar ya de todos nuestros Programas Exclusivos para nuestros Fans. En ellos encontrarás un alto contenido de Misterio y Humanidades, con información exclusiva, vivencias, casos impactantes, opiniones y reflexiones de D. Santiago Vázquez que te apasionarán y no encontrarás en otro lugar, por 2,99 € al mes sin compromiso de continuidad al mes siguiente. Disfruta ya de todos estos Programas exclusivos haciéndote Mecenas o Fan del Canal. - ✌Bizum: 649 17 41 52 También puedes apoyar a este Canal para que siga produciendo Contenidos de alto interés mediante tu contribución a través de Bizum. ¡Muchas Gracias! - Si te ha gustado este Programa pulsa el icono ME GUSTA, ya que de esta forma apoyas al Programa y, por tanto, a nuestro Canal en iVoox. - Si aún no te has suscrito a nuestro Canal puedes hacerlo gratuitamente pulsando el botón correspondiente. * Nuestras REDES SOCIALES: Puedes seguir también la actividad profesional de D. Santiago Vázquez en: - Nuestro Canal de YouTube: Más Allá de la Realidad TV - D. Santiago Vázquez - Twitter: @svazquezgomariz (Santiago Vázquez) - Instagram: @santiagovazquezoficial (santiagovazquezoficial) - Facebook: Santiago Vázquez *E-mail del Programa: masalladelarealidad1994@gmail.com *CURSOS impartidos por D. Santiago Vázquez que PUEDES SEGUIR O REALIZAR: - D. Santiago Vázquez pone a tu disposición el "CURSO DE DEMONOLOGÍA Y ENIGMAS DEL MAL" explicado en profundidad en 10 videos muy pedagógicos de gran interés por tan sólo 100 €. Puedes ver el Tráiler del Curso en nuestro Canal de YouTube en: https://youtu.be/vKrxcfmSWRA - Si te interesa la Parapsicología, D. Santiago Vázquez pone a tu disposición su CURSO DE PARAPSICOLOGÍA explicado en profundidad en 8 videos muy completos, pedagógicos y de gran interés, por tan sólo 100 €. Puedes ver el Tráiler del Curso en nuestro Canal de YouTube en: https://youtu.be/t8mSx1N1f9A?list=TLPQMTgwNDIwMjJJApLFVK46bA Solicita Información de uno u otro Curso (o de ambos) sin compromiso alguno escribiéndonos un e-mail a: masalladelarealidad1994@gmail.com Te enviaremos toda la Información sobre el Curso solicitado (o de ambos) y tú decides libremente si lo quieres efectuar. Un afectuoso saludo para tod@s y muchas gracias por estar ahí, al otro lado.

Cliff Hillis has spent a lot of his musical career saying "yes" and then figuring it out. Dan talks to Cliff about all his roles in music: songwriter and singer, cowriter, guitar tech, touring musician, collaborator, and so much more. Cliff talks about his days playing Rehoboth Beach bars with his brother to working with bands like The Innocence Mission, Starbelly, John Faye Power Trip, Patty Smyth, US Rails, and his current gig as bassist for The Orchestra (featuring members of ELO and ELO II). They also talk about the great Philadlephia music tribute (created by Hooter's drummer Dave Uosikkinen), In The Pocket, which Cliff has been fortunate enough to be a part of for years. And no conversation with Cliff would be complete without mulling over the oft-debated genre label that is "power pop". Cliff is currently on tour with The Orchestra, and is finishing up a brand new EP of his own music, coming out later in 2026.

Donald Trump lanzó amenazas cada vez más agresivas de destruir a partir de este martes centrales eléctricas en Irán; OPEP+ ve daño duradero a activos energéticos; cambios en la carrera presidencial en Perú; María Eloísa Capurro, quien cubre la Reserva Federal para Bloomberg News, comenta el potencial rumbo de tasas del banco. Newsletter Cinco cosas: https://bloom.bg/42Gu4pGLinkedin: https://www.linkedin.com/company/bloomberg-en-espanol/Youtube: https://www.youtube.com/BloombergEspanolWhatsApp: https://whatsapp.com/channel/0029VaFVFoWKAwEg9Fdhml1lTikTok: https://www.tiktok.com/@bloombergenespanolX: https://twitter.com/BBGenEspanolProducción: Eduardo ThomsonSee omnystudio.com/listener for privacy information.

Scot and Jeff discuss The Apples in Stereo with Jack Butler. Introducing the Band: Your hosts Scot Bertram (@ScotBertram) and Jeff Blehar (@EsotericCD) with guest Jack Butler. Jack is deputy editor for Free Expression, a new newsletter about politics and culture from the Wall Street Journal opinion page. Previously he was submissions editor for National Review Online. You can follow him on Twitter/x @jackbutler4815. And unless you're a 2:30 marathoner, you probably can't follow him in real life — unless he lets you.  Jack's Music Pick: The Apples in Stereo Get ready for sunshine melodies, fuzzed-out guitars, and pure pop sweetness, because we're diving into the colorful world of The Apples in Stereo. On this episode, we walk through the band's discography album by album, tracing how Robert Schneider and company blended psychedelia, power pop, and a DIY spirit into a signature sound. You might not be familiar with the band (yet), but you know the influences -- The Beatles, ELO, XTC, Pavement, Guided by Voices, The Beach Boys. We travel from the lo-fi charm of Fun Trick Noisemaker to the "space disco" feel of Travellers in Space and Time. Along the way, Scot takes the proper time to pay tribute to an all-time favorite album, New Magnetic Wonder, and we discuss the unorthodox ways the band found its way into children's programming. Plus Hilarie Sidney gets her due as an excellent and underrated singer, songwriter, and drummer.  Schneider's interest in science, space, and sound influenced the band's later work specifically, with conceptual elements and unconventional recording approaches shaping their music. New Magnetic Wonder even touts Schneider's invention of a new musical scale: the "Non-Pythagorean scale" (he's now a mathematics professor at Northern Michigan University, so it all makes sense in the end).  Throughout the years, the band kept pushing forward without losing a sense of wonder and experimentation that defined their earliest work and refined their ability to create hooks and melodies that lodge inside your brain for weeks at a time. And you can't tell the story of The Apples in Stereo without diving into the world of the Elephant 6 Recording Company, the loose collective of like-minded musicians that helped spark an indie-pop movement in the '90s. Jack takes the lead in describing this element of the show. This episode is a celebration of melody, creativity, and the joy of making something delightfully strange. It'll fill you with energy. Can you feel it? Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

In a Record Store Day exclusive, XTC are releasing Live Boots, a double-LP recording of their gig at Emerald City, New Jersey, on 17 April 1981 – exactly 45 years ago.Sitting behind the sound desk for that gig was Gary Bradshaw, this month's guest on What Do You Call That Noise? The XTC Podcast. In a revealing interview, Gary talks about graduating from guitar tech to sound engineer and onwards to some of the biggest bands in the world, including Alison Moyet, George Michael, Pink Floyd, ELO and Take That.He also talks about jumping aboard the Police's tour bus, the shock of seeing Andy Partridge collapse on stage and why he still rates XTC as among the finest bands there ever was.Record Store Day, 18 April 2026Music from Allan Knox and The Kettle ZoneWhat Do You Call That Noise? An XTC Discovery Book available from www.xtclimelight.com  If you've enjoyed What Do You Call That Noise? The XTC Podcast, please show your support at https://www.patreon.com/markfisher Thanks to the Pink Things, Humble Daisies and Knights in Shining Karma who've done the same. What Do You Call That Noise? The XTC Podcast is sponsored by the online record shop, Burning Shed, which is the only place to get official XTC merchandise. ★ Support this podcast on Patreon ★

Bajo el murmullo constante de las calles parisinas, en el corazón del circuito intelectual de la ciudad, un bar redefine el "deporte ciencia". Aquí, el silencio de la estrategia convive con el tintineo de las copas y la rapidez del cronómetro. Disfrute del reportaje radial utilizando el botón Escuchar. París no solo se camina, se piensa. En una zona céntrica, cerca de la Casa de América Latina, existe un refugio donde cada segundo cuenta y se libran batallas épicas en silencio... o entre copas de vino. El sonido de la ciudad —ese rumor de pasos y tráfico que caracteriza a la capital francesa— se queda en la puerta al entrar en un universo distinto. “Soy jugador de ajedrez amateur, investigador y un fan absoluto de este deporte", se presenta Damia Benet, un español radicado en Francia. "Estamos en la Blitz Society. Es la típica zona con edificios históricos súper bonitos de París, pero lo que pasa aquí adentro es otra historia. Vamos a conocerlo”. Al cruzar la puerta, el ambiente cambia. El sonido de los platos y las conversaciones animadas delata que, antes que nada, este es un lugar de encuentro social. Guirma Brice, responsable del establecimiento, explica que la estética del local no es casualidad. “Es un lugar muy antiguo”, comenta Brice mientras señala la arquitectura que los rodea. “Hecho de piedra, de madera, de materiales brutos. Casi no pudimos hacer reformas porque el suelo y las paredes tienen historia. Queríamos reproducir la atmósfera de los parques de Nueva York, pero bajo la calidez de un bar”. Esa inspiración en los espacios públicos neoyorquinos se fusiona con la elegancia rústica de París. Para los aficionados, el diseño es un imán: “Al entrar, a mano derecha, ves un tablero que parece una máquina de arcade de los 80, con joysticks. Es el sitio idóneo”, añade Damia. Del Jardín del Luxemburgo a la mesa del bar La mayoría de los practicantes del deporte ciencia que hoy pasan horas mirando las 64 casillas de cada mesa —porque aquí, literalmente, cada mesa es un tablero— ya conocían la disciplina en los parques, donde la práctica es común y gratuita. El referente más cercano es el Jardín del Luxemburgo, un espacio bucólico en el mismo barrio donde, entre árboles y jubilados, nace la pasión de muchos. Es el caso de Adrien, uno de los habituales de la Blitz Society. “Descubrí el ajedrez sobre tablero en el Luxemburgo en 2017. Antes solo jugaba por internet, con piezas virtuales. Pasar a tocar piezas de verdad fue un cambio lógico”, relata. Sin embargo, el bar ha atraído a una comunidad que ha explotado recientemente. Ya no son solo los veteranos del parque. “Hay una nueva ola de jóvenes. Vienen por los YouTubers o por la serie Gambito de Dama”, explica Adrien. “Cada vez que vengo hay caras nuevas, gente que nunca se había acercado a un tablero. Eso le da luz al juego”. El "Blitz": Tres o cinco minutos de adrenalina En la Blitz Society se puede elegir el tono de la batalla. Damia Benet, quien se interesó por el ajedrez mucho antes de que se pusiera de moda en las redes sociales, explica que este rincón parisino le permite hablar un lenguaje universal: la notación algebraica (esa que identifica las casillas con letras y números). “Aquí he jugado dos tipos de torneos: homologados y no homologados”, cuenta Damia. “Cuando es homologado por la FIDE (Federación Internacional de Ajedrez), no hay música y la gente no toma alcohol normalmente, aunque se puede. Luego están los no homologados, más para relajarme, bebiendo una cerveza. Aquí se pueden jugar los dos”. Pero el verdadero rey de la casa es el ritmo que da nombre al local. “El Blitz es el ritmo de tiempo que significa que tienes unos tres minutos o unos cinco minutos por jugador para hacer los movimientos de principio al final de la partida”, explica Damia tras pedir un agua con gas en la barra. De bar a sala de juego Cuando se acerca la hora del torneo, el ambiente se transforma. El tintineo de las copas deja paso al sonido seco de las piezas de madera golpeando los tableros. Los inscritos —esta noche son 34— dejan sus platos a medio comer y sus copas a un lado para conocer a su primer rival tras el sorteo de mesas. Mientras los meseros terminan de limpiar y acomodar las sillas, el bar termina su metamorfosis. La calidez del ambiente social se tensa con la concentración competitiva. Los relojes están listos, las miradas fijas en el tablero y, por unos minutos, el mundo exterior desaparece. Organizar este caos requiere una figura silenciosa: el árbitro. Esta noche se encarga el francés Pierre Lariviere, de la Federación Internacional de Ajedrez (FIDE). “Mi trabajo es registrar a los jugadores, ajustar los relojes y lanzar las rondas. Aquí todo es mucho más relajado. Incluso los torneos oficiales tienen un aire distinto”, comenta Pierre mientras observa la sala. El árbitro es quien media cuando los nervios afloran. “A veces hay litigios por un movimiento o un empate. Los jugadores pueden ponerse tensos. Pero al final, se resuelve mirando contra quién jugaron. El que enfrentó a rivales más fuertes, gana. Es un sistema de puntos llamado ELO”. El ELO es el sueño o la pesadilla de millones de ajedrecistas. Es la medida de la fuerza de un jugador: si ganas, subes; si pierdes, bajas. Actualmente, el trono mundial lo ocupa el noruego Magnus Carlsen (2.869 puntos en categoría Blitz), seguido en Latinoamérica por el mexicano José Martínez Alcántara (2.663 puntos). Sin embargo, en el torneo de los miércoles, el ELO no es lo único que está en juego; la paciencia también se pone a prueba. “En torneos no homologados hay dos tipos de jugadores: el que se concentra y el que te pincha”, explica Damia. “Hay expertos en soltar comentarios para sacarte de quicio y terminas haciendo una jugada mala por la distracción”. Inicia el torneo. El árbitro Lariviere verifica las mesas y da luz verde desde un sillón, mientras saborea una limonada. El verdadero juez ahora es el reloj digital de doble esfera que preside cada mesa, marcando el ritmo frenético del Blitz. Inician las blancas con aperturas clásicas como la Italiana; responden las negras con la Siciliana. Entre partida y partida, los alfiles y caballos se convierten en piezas de ataque indomables. Damia comienza con fuerza en la mesa 4. Después de ganar las primeras partidas, Damia llega a la mesa 1, donde se sientan los líderes. Si gana, es el campeón y se lleva un bono del bar. “En la última partida entregué una pieza para romper su defensa. Tuve el ataque ganador, pero con la presión del reloj no encontré la jugada precisa. Perdí. Pero estuve muy cerquita”. Enamorarse jugando ajedrez El torneo termina, pero la noche es joven. Al ritmo del jazz de All Blues, la Blitz Society revela su otra cara: la de centro social. “Vemos muchísimos dates, primeras citas”, confiesa Guirma Brice. El ajedrez es la excusa perfecta. En una mesa, Luka, profesor de ajedrez, guía a Morgane. “Si me dejas mucho espacio, me escaparé... ¡Bravo Morgane! Acabas de hacer tu primer jaque mate con tu reina”, celebra Luka. “Nos encontramos en Tinder hace una semana y su propuesta de cita fue venir aquí”, cuenta Morgane. “Me está enseñando y creo que es un buen partido”. La estrategia de Luka parece funcionar mejor que cualquier apertura italiana. Incluso las celebridades se rinden al encanto del lugar. Natalie Portman ha sido vista entre sus muros de piedra, y el gigante de la NBA, Victor Wembanyama, también dejó su huella. “Fue una noche privada. ¡Apenas cabía por la puerta! Tenía que agacharse para todo, pero jugó varias partidas. Fue muy simpático”, recuerda Brice. Al final de la noche, surge la pregunta inevitable: ¿ganan siempre las blancas por salir primero? Damia sonríe: “En principio, las blancas están un poquito mejor en la posición inicial, pero es un margen muy pequeñito. Los mejores del mundo saben cómo explotarlo, pero otros como yo... pues no tiene por qué ganar”. Realización sonora: Pierre Zanutto

Quand les nazis spoliaient les objets du quotidien Quand l'historienne Sophie Juliard, qui travaille sur le pillage des ateliers d'artistes sous l'Occupation, la contacte, Adrianna Wallis découvre, quatre-vingts ans après les faits, que sa famille a été spoliée. Elle savait que Diane Esmond, sa grand-mère paternelle, était peintre, mais avait presque oublié qu'elle était juive. Après le départ précipité de celle-ci pour New York, l'appartement parisien qu'elle occupait a été entièrement vidé par l'administration nazie, comme 38 000 autres dans la capitale : les toiles ont disparu, mais aussi le mobilier et jusqu'aux moindres objets du quotidien. Pour Adrianna, elle-même artiste, ce passé familial refoulé résonne étrangement avec son travail, elle qui n'a cessé, sans trop comprendre pourquoi, d'interroger l'absence, le vide laissé par la disparition d'objets chers. En tissant enquête intime, archives et les réflexions du physicien Joël Chevrier, Adrianna Wallis remet en mouvement cette histoire longtemps tue et interroge ce qui se transmet, parfois à notre insu, d'une génération à l'autre. Bibliographie : - Images d'un pillage, de Sarah Gensburger, Editions Textuel, 2010 ; - Des camps dans Paris de Jean-Marc Dreyfus et Sarah Gensburger, Fayard, 2003. Pour aller plus loin : - La performance 11 petites soucoupes, réalisée en 2024, au Musée d'art et d'histoire du Judaïsme, Paris ; - Conférence Il restera la gravité en 2025, à l'INHA, Paris ; - L'exposition d'Adrianna Wallis et Diane Esmond Il restera la gravité, du 5 mai au 16 juin 2026 à la galerie Anne-Laure Buffard, Paris ; - L'accrochage Itinéraires d'œuvres spoliées – Diane Esmond et Fédor Löwenstein, jusqu'en 2028, au Musée d'art et d'histoire du Judaïsme, Paris. Remerciements : Sylvie Harburger, Hélène de Gunzbourg, Andrew Strauss, Joël Chevrier, Sophie Juliard, Sarah Gensburger, Margaux Dumas, les Archives nationales, le Musée d'Art et d'Histoire du Judaïsme, Anne Rousseau, Pascale Samuel, Eloïse Duguay, Marie Bastide, Grégoire Meschia, Fabrice Lorendel, Elise Patton, Léonard Ballesteros, Mila Renno Lehr, Alissa Deleverora, Perrine Kervran, Agathe Chion, Marie Dalcol, Camille Bondon, Sarah Deslande, Mathilde Wallis, Clémence Beraud, et le Centre National des Arts Plastiques. Enregistrements mai 2025 Entretien Adrianna Wallis, Eloïse Duguay Montage Adrianna Wallis Réalisation et mixage Charlie Marcelet Illustration Gloria Avril Production ARTE Radio

In this episode of Better at Beach, Mark Burik and Logan Weber discuss the challenges faced by beach volleyball players, particularly regarding FIVB tournaments and visa issues. They delve into the dynamics of training with USA Volleyball and the structure of A2 and A1 teams in men's beach volleyball. The conversation highlights the importance of strategic planning in travel and tournament participation, as well as the support systems available to athletes. In this conversation, Logan Webber discusses the intricacies of the A1 and A2 teams in USA Volleyball, explaining the ELO ranking system and its implications for player evaluations and benefits. The dialogue also covers the support systems available to players, the roles of various coaches, and the logistics of tournament participation. Additionally, the conversation highlights the contributions of Ed Keller, a dedicated volleyball enthusiast, and delves into training regimens focused on ball control and competitive practices.

¡Nos vamos pa' BellasJartes! Capeta tus boletos aquí. Auspiciado por Vital Full of Life. Coopera con Glenda Maldonado en este enlace. En el último episodio de marzo, estamos emocionados y caga'os por el show en BellasJaltes, pero nos queda energía para reírnos de la guerra civil en el PNP, con Valerie echándole gasolina al fuego, Georgie teniendo una pequeña pelea con Elo, y el secretario acusado de enfermo sexual recibiendo ayuda de la más sobá. El mundo se fue de Chuck Norris y Daniel el Travieso algún día le explicará a su retoño por qué Chicky Starr y El Profe recibieron un más que merecido homenaje en el Senado. Gringo tiene un nuevo pasatiempo con gallinas y Jay Wheeler se pasó las criticas por el orto con la misma paz que emana la gemela perdida de Tita Guerrero. Patrones PYMES: Jabonera Don Gato Nana's Stuffing Nuestras redes sociales: Tío Macetaminofen Sol Guzabra El George El Come Siempre es Lunes

A milky tea, a jam sponge and this week's news served on a tin tray with a steam train painted on it points our very English conversation towards the following … … what connects the Monkees and a British Prime Minister? … when are you too old for Indie? … A Certain Je Ne Sais Quoi? A Bar on The Piccolo Marina? Noel Coward or Neil Tennant? … the Move, the Streets, the Kinks, ELO, Ian Dury, Anthony Newley, the Jam, Herman's Hermits, Cat Stevens, Arctic Monkeys and other acts with a sense of Englishness … Girl in the Thunderbolt Suit: when Marc Bolan went science fiction … how London Zoo could have put the tin lid on the Beatles … the daft story of Randy Scouse Git … how Michael Caine cooked up the name Harry Palmer ... the most English pronunciation of a songword ever … Black Crowes, Byrds and the allure of misspelling … Roxy, 10cc, the Hollies, Manfred Mann, Human League and other original line-ups we want to reform … plus Angine de Poitrine, Kaleidoscope rebooted by Jimmy Page and birthday guest Jonny Wren.Help us to keep the conversation going: https://www.patreon.com/wordinyourear Hosted on Acast. See acast.com/privacy for more information.

A milky tea, a jam sponge and this week's news served on a tin tray with a steam train painted on it points our very English conversation towards the following … … what connects the Monkees and a British Prime Minister? … when are you too old for Indie? … A Certain Je Ne Sais Quoi? A Bar on The Piccolo Marina? Noel Coward or Neil Tennant? … the Move, the Streets, the Kinks, ELO, Ian Dury, Anthony Newley, the Jam, Herman's Hermits, Cat Stevens, Arctic Monkeys and other acts with a sense of Englishness … Girl in the Thunderbolt Suit: when Marc Bolan went science fiction … how London Zoo could have put the tin lid on the Beatles … the daft story of Randy Scouse Git … how Michael Caine cooked up the name Harry Palmer ... the most English pronunciation of a songword ever … Black Crowes, Byrds and the allure of misspelling … Roxy, 10cc, the Hollies, Manfred Mann, Human League and other original line-ups we want to reform … plus Angine de Poitrine, Kaleidoscope rebooted by Jimmy Page and birthday guest Jonny Wren.Help us to keep the conversation going: https://www.patreon.com/wordinyourear Hosted on Acast. See acast.com/privacy for more information.

A milky tea, a jam sponge and this week's news served on a tin tray with a steam train painted on it points our very English conversation towards the following … … what connects the Monkees and a British Prime Minister? … when are you too old for Indie? … A Certain Je Ne Sais Quoi? A Bar on The Piccolo Marina? Noel Coward or Neil Tennant? … the Move, the Streets, the Kinks, ELO, Ian Dury, Anthony Newley, the Jam, Herman's Hermits, Cat Stevens, Arctic Monkeys and other acts with a sense of Englishness … Girl in the Thunderbolt Suit: when Marc Bolan went science fiction … how London Zoo could have put the tin lid on the Beatles … the daft story of Randy Scouse Git … how Michael Caine cooked up the name Harry Palmer ... the most English pronunciation of a songword ever … Black Crowes, Byrds and the allure of misspelling … Roxy, 10cc, the Hollies, Manfred Mann, Human League and other original line-ups we want to reform … plus Angine de Poitrine, Kaleidoscope rebooted by Jimmy Page and birthday guest Jonny Wren.Help us to keep the conversation going: https://www.patreon.com/wordinyourear Hosted on Acast. See acast.com/privacy for more information.

This week, we've got the touch. We've got the power. There's no easy way out, but we won't stop believin'! Oh yeah, it's time once again for some of that amazingly inspirational AOR arena rock montage music! This time around, it has a St. Patty's Day spin to it. Be all you can be, feel the burn, and drink some green beer! This episode is rooted in all 3 categories of lost, forgotten, and should have beens. These bands all provide fist pumpingly perfect sounds of AOR / Arena Rock gold from the late 70s to now. Their music pairs perfectly with action and teen coming-of-age movies and was a big part of our youth! We hope we turn you on to something new! Songs this week include: Orion The Hunter – “Stand Up” from Orion The Hunter (1984) Giuffria – “Line Of Fire” from Giuffria (1984) Midnite City – “Girls Gone Wild” from In At The Deep End (2023) GTR – “Here I Wait” from GTR (1986) New England – “Don't Ever Want To Lose Ya” from New England (1979) Streetheart – “Too Hot To Stop” from Dancing With Danger (1983) Big Red Fire Truck – “No Easy Way Out” from Tokyo Karaoke Bar (2026) Please subscribe everywhere that you listen to podcasts! Visit us: https://inobscuria.com/ https://www.facebook.com/InObscuria https://x.com/inobscuria https://www.instagram.com/inobscuria/ Buy cool stuff with our logo on it: InObscuria Store Check out Robert's amazing fire sculptures and metal workings here: http://flamewerx.com/ If you'd like to check out Kevin's band THE SWEAR, take a listen on all streaming services or pick up a digital copy of their latest release here: https://theswear.bandcamp.com/ If you want to hear Robert and Kevin's band from the late 90s – early 00s BIG JACK PNEUMATIC, check it out here: https://bigjackpnuematic.bandcamp.com/

Rob Reed, multi-instrumentalist, composer, and producer for the band Magneta, joins the podcast to talk about the band's new album 'Tarot,' songwriting, and the greatness of ELO. Host: Roie Avin

durée : 00:29:10 - L'Entretien archéologique - par : Antoine Beauchamp - Messages d'amour, dessins ou insultes, ce sont autant d'inscriptions qui jonchaient les murs des espaces publics des cités romaines. Ces graffitis antiques, forment un corpus indispensable pour documenter le quotidien des populations, largement invisibilisé des sources textuelles classiques. - réalisation : Olivier Bétard - invités : Eloïse Letellier-Taillefer Maîtresse de conférences en histoire de l'art et archéologie du monde romain à Sorbonne Université

durée : 00:04:07 - Les P'tits Bateaux - par : Camille Crosnier - C'est la question posée par Marion. L'historienne, directrice des collections du musée des Arts forains à Paris, Eloïse Galliard, lui répond. Vous aimez ce podcast ? Pour écouter tous les autres épisodes sans limite, rendez-vous sur Radio France.

The Eric's give confusing opinions about a perfectly good ELO song. Donate to the podcast through Patreon... https://www.patreon.com/ELOPod Or PayPal eloftmpodcast@gmail.com P.O. Box 1932 Superior, AZ 85173.

Billabong Presents... ATS with Smivvy & Deadly! It’s been the busiest surf week since Elo got his farewell kick up the coit with X3 World Champ John Florence giving the Woz a severe case of blue balls, J-Bay gets the fuh-lick, Rags goes to the big show and Goat trades nubile princesses for burnt out South Tweed units on mobility scooters. The Pipe Chang fires up, and the Swellians take over the asylum for a huge Ask us a Question Special. Slurp Slurp Slurp away! Up the financial revolution that's got young Aussies Backs Presents... (Sign up now for a $20 kick in from us using the code "UTFS20" Yeeeeeeew!)See omnystudio.com/listener for privacy information.