Podcasts about Pelican

Gary Pelican v. 3M Company

A 28-year-old woman was killed and a man was injured by a gunman in Pelican Narrows on Monday. The community has been under a state of emergency for the past few years due to violence. Saskatchewan's Community Safety Minister Michael Weger was in Pelican Narrows for a first-hand look just a day before the shooting. This is Saskatchewan's political panel of Alexander Quon and Murray Mandryk join host Adam Hunter to discuss the issues facing Pelican Narrows.

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

Don't have time to listen to the full show? We got you covered on the Nathan, Nat & Shaun Quickie, all the best bits from Wednesday 3rd June! See omnystudio.com/listener for privacy information.

We kick off the morning with some unbelievable stories of getting physically stuck! After news broke of a woman rescued from quicksand at an Adelaide beach, our listeners called in with their own tight spots—including a toddler with a potty stuck on their head and Katie, who somehow managed to get her entire head stuck inside a pelican's mouth! See omnystudio.com/listener for privacy information.

The book, An Awesome Bird The Pelican, is a book for kids, written by Rusty Austin, and students from Nellie Coffman Middle School created the illustrations. This story teaches kids about pelicans in a fun and interesting way by showing off their various traits and behaviors.The story starts with a curious pelican going on a trip to find out where it fits in the world. The pelican faces many problems along its journey and gets to learn many important lessons. The pelican learn about never giving up and the value of community. The students' drawings add a personal touch that makes the readers enjoy he story in a different way.This book is useful for parents and teachers to teach youngsters about animals and their habitats. With its easy-to-read text and eye-catching pictures, this book keeps kids curious and excited to learn about animals.This book is fun and educational for kids to read in school or at home. It makes kids more curious and helps them appreciate nature more, which makes it a great book for any child's bookshelf. This book takes readers on an exciting journey through the animal kingdom. Each creature has its own fun poem that shares its unique story. From Axolotl Salamanders to Uromastyx Lizards, every animal gets a moment to explain their behavior.Available on Amazon! James Lott JR is the host!

Our lead story: RCMP in northeast Saskatchewan say a suspect is now in custody following a double shooting in Pelican Narrows, but say charges have yet to be laid.

http://www.mofpodcast.com/http://www.pbnfamily.comhttps://www.facebook.com/matteroffactspodcast/https://www.facebook.com/groups/mofpodcastgroup/https://rumble.com/user/Mofpodcastwww.youtube.com/user/philrabhttps://www.instagram.com/mofpodcasthttps://twitter.com/themofpodcasthttps://www.cypresssurvivalist.org/Support the showMerch at: https://southerngalscrafts.myshopify.com/Shop at Amazon: http://amzn.to/2ora9riPatreon: https://www.patreon.com/mofpodcastPurchase American Insurgent by Phil Rabalais: https://amzn.to/2FvSLMLShop at MantisX: http://www.mantisx.com/ref?id=173*The views and opinions of guests do not reflect the opinions of Phil Rabalais, Andrew Bobo, Nic Emricson, or the Matter of Facts Podcast*The boys start planning and prepping for their annual Summer Camp. Phil uncorked the wallet for his first hard case since his deployment days, while he and Nic talk about the boring yet necessary endeavor of storing, and transporting their gear, arms, and ammo. Stuart even tossed them a softball over the plate to talk about Grey Man transportation, something we all should seriously consider.Matter of Facts is now live-streaming our podcast on our YouTube channel, Facebook page, and Rumble at 7:30 PM Central on Thursdays . See the links above, join in the live chat, and see the faces behind the voices. Intro and Outro Music by Phil Rabalais All rights reserved, no commercial or non-commercial use without permission of creatorBecome a supporter of this podcast: https://www.spreaker.com/podcast/prepper-broadcasting-network--3295097/support.Support PBN and become a MEMBER of the PBN FAMILY! Free courses, Members only videos, reviews, and podcast! The Prepper's Medical Handbook Build Your Medical Cache – Welcome PBN FamilyJoin the Prepper Broadcasting Network for expert insights on #Survival, #Prepping, #SelfReliance, #OffGridLiving, #Homesteading, #Homestead building, #SelfSufficiency, #Permaculture, #OffGrid solutions, and #SHTF preparedness. With diverse hosts and shows, get practical tips to thrive independently – subscribe now!Newsletter – Welcome PBN FamilyGet Your Free Copy of 50 MUST READ BOOKS TO SURVIVE DOOMSDAYSupport PBN with a Donation 

For May's episode we discuss our favourite songs of 2009, including epic drone soundscapes, haunted TV themes, Emo Chiptune, Indiepop songs about outdated heartthrobs, and deconstructed Arab Strap.We've each chosen our 10 favourite songs of the year and sent them over to Colin's wife Helen, who put the playlists together and distributed them so we were each given a playlist of the 20 songs from the other two hosts, along with our own 10. We then ranked the playlists in order of preference and sent them back to Helen, who totalled up the points and worked out the order. She also joined us on the episode to read out the countdown, which we found out as we recorded so all reactions are genuine.Now, admittedly, in parts we're a little bit brutal to some of the songs in the list as we're three separate people with differing music tastes, but please remember that to be in this episode at all the songs have to have been in one of our top 10's of that year.Bands featured in this episode include (In alphabetical order, no spoilers here!) - :(, Animal Collective, Belbury Poly, Betty & The Werewolves, Bon Iver, Brand New, Bill Callaghan, Crippled Black Phoenix, Editors, Future Of The Left, PJ Harvey & John Parish, The Horrors, Isis, Jesu, Dan Michaelson, Metric, Malcolm Middleton, Aidan Moffat & The Best Ofs, Mono, The National, Om, Paramore, Pelican, Porcupine Tree, Regina Spektor, Sunn O))), The Temper Trap, Cortney Tidwell, and The XX.Find all songs in alphabetical order here - https://open.spotify.com/playlist/5g3iJkWjs932dm8nn7bCEP?si=ae57751dec554930Find our We Dig Music Pollwinners Party playlist (featuring all of the winning songs up until now) here - https://open.spotify.com/playlist/45zfDHo8zm6VqrvoEQSt3z?si=Ivt0oMj6SmitimvumYfFrQIf you want to listen to megalength playlists of all the songs we've individually picked since we started doing best of the year episodes (which need updating but I plan on doing them over the next few months or so), you can listen to Colin's here – https://open.spotify.com/playlist/5x3Vy5Jry2IxG9JNOtabRT?si=HhcVKRCtRhWCK1KucyrDdgIan's here - https://open.spotify.com/playlist/2H0hnxe6WX50QNQdlfRH5T?si=XmEjnRqISNqDwi30p1uLqAand Tracey's here - https://open.spotify.com/playlist/2p3K0n8dKhjHb2nKBSYnKi?si=7a-cyDvSSuugdV1m5md9NwThe playlist of 20 songs from the other two hosts was scored as usual, our favourite song got 20 points, counting down incrementally to our least favourite which got 1 point. The scoring of our own list of 10 is now slightly more complicated in order to give a truer level of points to our own favourites. So rather than them only being able to score as many points as our 10th favourite in the other list, the points in our own list were distributed as follows -1st place - 20 points2nd place - 18 points3rd place – 16 points4th place – 14 points5th place – 12 points6th place – 9 points7th place – 7 points8th place – 5 points9th place – 3 points10th place -1 pointHosts - Ian Clarke, Colin Jackson-Brown & Tracey BGuest starring Helen Jackson-Brown.Playlist compiling/distributing – Helen Jackson-BrownRecorded/Edited/Mixed/Original Music by Colin Jackson-Brown for We Dig PodcastsThanks to Peter Latimer for help with the scoring system.Part of the We Dig Podcasts network along with Free With This Months Issue & Pick A Disc.Bluesky - https://bsky.app/profile/wedigmusic.bsky.socialInstagram - https://www.instagram.com/wedigmusicpcast/Facebook - https://www.facebook.com/wedigpusicpcast/Find our other episodes & podcasts at www.wedigpodcasts.com 

http://www.mofpodcast.com/http://www.pbnfamily.comhttps://www.facebook.com/matteroffactspodcast/https://www.facebook.com/groups/mofpodcastgroup/https://rumble.com/user/Mofpodcastwww.youtube.com/user/philrabhttps://www.instagram.com/mofpodcasthttps://twitter.com/themofpodcasthttps://www.cypresssurvivalist.org/Support the showMerch at: https://southerngalscrafts.myshopify.com/Shop at Amazon: http://amzn.to/2ora9riPatreon: https://www.patreon.com/mofpodcastPurchase American Insurgent by Phil Rabalais: https://amzn.to/2FvSLMLShop at MantisX: http://www.mantisx.com/ref?id=173*The views and opinions of guests do not reflect the opinions of Phil Rabalais, Andrew Bobo, Nic Emricson, or the Matter of Facts Podcast*The boys start planning and prepping for their annual Summer Camp. Phil uncorked the wallet for his first hard case since his deployment days, while he and Nic talk about the boring yet necessary endeavor of storing, and transporting their gear, arms, and ammo. Stuart even tossed them a softball over the plate to talk about Grey Man transportation, something we all should seriously consider.Matter of Facts is now live-streaming our podcast on our YouTube channel, Facebook page, and Rumble at 7:30 PM Central on Thursdays . See the links above, join in the live chat, and see the faces behind the voices. Intro and Outro Music by Phil Rabalais All rights reserved, no commercial or non-commercial use without permission of creator

Mike and Charlie interviewed Louisiana head baseball coach Matt Deggs and Chrissy Smith, a podcaster for The Kneaux. Coach Deggs broke down the Cajuns' challenge in the Starkville Regional, featuring No. 14 Mississippi State and No. 24 Cincinnati. Coach Deggs also recapped the Cajuns' trip in the Sun Belt Conference Tournament and evaluated UL's pitching staff. Smith discussed Pelican head coach Jamahl Mosley's introductory press conference.

Chrissy Smith, a podcaster for The Kneaux, joined Sports Talk. Smith discussed Pelican head coach Jamahl Mosley's introductory press conference. She also shared her thoughts on the Birds' roster and potential offseason moves.

Do you remember Pelican's Wharf restaurant in San Antonio? The eatery was located on N.E. Loop 410; there were also locations in Corpus Christi and Austin. If you remember the restaurant, you may also recall the Pelican's Cheesecake! The restaurant may have been lost to time, but the cheesecake recipe doesn't have to go the same way. This recipe is in Recipes for the Diner's Delight, a collection of recipes from San Antonio area restaurants, presented in 1982 by the San Antonio Area Lupus Foundation. A trawl through the little comb-bound book, put together as a fundraiser, is a stroll... Article Link

Massie treated the Constitution like it was delivered from Mount Sinai in a Pelican briefcase carried by Moses. No improvisation. No fingerprints, no smudges, no coffee stains. Meanwhile, Donald Trump treats politics like a Formula One pit crew during a tire change. For the record, Massie is no dummy. This guy is the kind of smart where you almost resent him on sight. MIT degrees in electrical engineering and mechanical engineering. Started a biotech company. The man probably fixes particle accelerators with a butter knife and some duct tape he bought at Tractor Supply. He's got conservative credentials too. Lifetime ratings that make constitutional scholars swoon like teenage girls at a Beatles concert.But here's the problem with purity in politics: sometimes the tiniest grain of sand jams the whole transmission.[X] SB – Ed Gallrein on taking advantage of history…And Massie is a purist.Not originally a Republican. Libertarian. Different animal entirely. Republicans tend to say, “Well, this isn't perfect, but let's move the ball.” Libertarians say, “If the ball moves one inch outside the exact constitutional boundary envisioned by James Madison on a rainy Tuesday in 1789, burn the stadium down.”That's the split.[X] SB – Massie votes against President TrumpTried to buy my vote for 14 years.Take the border wall. Massie said he supported the wall. Fine. But when Trump used executive authority to fund portions of it because Congress was moving slower than a DMV sloth on Ambien, Massie objected. Constitutionally, he had an argument. Congress controls the purse strings. That's textbook civics.But Trump supporters weren't watching “Schoolhouse Rock.” They were watching a country collapse at the border while politicians held symposiums on procedural etiquette.That's the disconnect.Massie looked at the process. Trump supporters looked at the outcome.And Americans are exhausted with process people. We've had process people for decades. America is drowning in process people. Every failed city in America had excellent process. Detroit had process. California has process. The Titanic had a committee.Trump came along and said, “I don't care which drawer the wrench is in. The engine's on fire.”That changes voter psychology completely.Then came the Iran dispute. After U.S. strikes on Iranian nuclear facilities, Massie argued Congress should authorize military action. Again, constitutionally coherent. Congress declares war. Presidents have accumulated too much unilateral military power. Endless intervention overseas bleeds the country dry. There's intellectual consistency there.The country didn't elect Massie. A district in KY did. And the idea that his district dictates Trump's worldview is ridiculous.But Trump's worldview is completely different. Trump approaches geopolitics like a New York landlord walking into a negotiation with a baseball bat wrapped in velvet. The point is uncertainty. The point is leverage. The point is making adversaries think, “This guy might actually do it.”And Trump allies saw Massie publicly objecting during a standoff with Iran as weakening the president in real time.Now whether people agree or disagree with either side is almost secondary to the larger political reality unfolding in front of us.Because this wasn't just a disagreement over policy. It was a disagreement over the operating system of conservatism itself.Massie represents constitutional restraint first. Trump represents national survival first.Massie says: “The rules matter most.”Trump supporters say: “What good are rules if the country collapses while we're admiring them?”And that's why this divide got so emotional.See, conservatives spent years watching Republicans surrender elegantly. Nobody lost with more dignity than old-school Republicans. These people could lose all three branches of government and still hold a press conference congratulating themselves on bipartisanship. Republicans became the Washington Generals of politics. Professional losers in expensive suits.See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Welcome back to the Konfidence in the Klutch Podcast with Donald Nelson (2:30).  Konfidence in the Klutch's Deezus gives his Konfident Service Announcement: Do You (5:00).  Deezus reviews Drake's three albums in his comeback.  Was it genius or way too much?  (9:50).  Deezus then shares his NBA news, including that Embiid is at odds with management, however he's always hurt, and signed an 3/$193M extension.  Luka doesn't want Reeves in any deals—Lakers, LeBron's future, and how they can keep Bron and Reeves.  Myles Turner airs out Giannis for not being the standard for the team.  I agree with Utah owner Ryan Smith's opinion on how to fix tanking.  Shai wins back-to-back MVPs.  Was Shams wrong for stepping on their partner's announcement?  Pelican hires Mosley: semi-final action and conference finals preview.  Western Conference Finals Game One Reaction: Wemby made a point!  (19:10).  Deezy then shares his WNBA thoughts, including the CC attending the Wallen concert hate is a joke.  Lisa Leslie gets a statue outside Crypto.  The WNBA cannot compete with the NBA playoffs, and the season should be moved from December to April (43:50).  Deezus discusses ‘Politics as usual,' including the Wisconsin state legislature blocking a bill by our outgoing governor and majority leaders.  I agree.  Xi lays the groundwork for a potential conflict with the US if the US interferes with Taiwan.  WTF is an anti-weaponization fund?  Trump continues to help and hold his people down.  The NAACP and CBC urge American-born African student athletes to boycott attending public universities in states that restrict American-born Africans' voting rights.   (33:50).  The podcast was recorded at 4:30 p.m. CT on Tuesday, May 19, 2026.  Host: Donald Nelson Producer/Engineer: Donald Nelson Music by: Konfidence in the Klutch Productions Subscribe, Stream, or Download:

Comedians Dave Anthony and Gareth Reynolds examine The Pelican Girls of LouisianaSOURCESTOUR DATESOFFICIAL MERCHNutrafol - Use code: DollopQUO - Try for free plus 20% off first six monthsRocketmoney Helix Sleep See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Mike and Charlie discussed the Pelicans' decision to hire head coach Jamahl Mosley and Mickey Loomis' comments about three Saints veterans. Jake Madison, the host of the Locked on Pelicans podcast, joined Sports Talk to review what Pelican fans should know about Coach Mosley. Mike interviewed Fox Sports commentator Tim Brando and Chessa Bouche, a sports reporter for LA First News. Steve and Charlie spoke to David Grubb, the host of The Post Up podcast, about Mosley and the Pelicans' future. The guys listened to the media availability of Mickey Loomis, Kellen Moore, and Tyler Shough at the Saints' Hall of Fame Celebrity Golf Classic.

Mike and Charlie discussed the Pelicans' decision to hire head coach Jamahl Mosley and Mickey Loomis' comments about three Saints veterans. Jake Madison, the host of the Locked on Pelicans podcast, joined Sports Talk. Madison broke down what Pelican fans should know about Coach Mosley. Mike and Charlie spoke to a WWL listener about Mosley.

Steff, Milo and Gareth discuss our game at Stamford Bridge which saw everything now move to that final home game on Sunday against Everton. We also offer some relief tips for surviving the week, agreeing that getting outdoors and engaging in avian therapy is the way to go. This club never does anything easily does it...Website: https://thegameisaboutglory.co.uk/Bluesky: @thegameisaboutglory.co.uk Hosted on Acast. See acast.com/privacy for more information.

Jake Madison, the host of the Locked on Pelicans podcast, joined Sports Talk. Madison broke down what Pelican fans should know about new head basketball coach Jamahl Mosley.

Live from the “Russ’y Pelican” in Hermosa Beach, it's “Chris Norton: Linger Over It.” Chris interviews Phil Hendrie about his raunchy sex experiences with “church ladies.”Sign up for a Backstage Pass and enjoy Hours of exclusive content, Phil's new podcast, Classic podcasts, Bobbie Dooley's podcasts, special live streaming events and shows, and oh so very much more…See omnystudio.com/listener for privacy information.

Jack Armstrong - Pelican Catches FireBecome a supporter of this podcast: https://www.spreaker.com/podcast/harold-s-old-time-radio--4206392/support.

Jack Armstrong - Pelican Crew Is RescuedBecome a supporter of this podcast: https://www.spreaker.com/podcast/harold-s-old-time-radio--4206392/support.

Jack Armstrong - Carrying Line To The PelicanBecome a supporter of this podcast: https://www.spreaker.com/podcast/harold-s-old-time-radio--4206392/support.

In this episode, we head back to the world of graphic novels and explore the suburban mystery of "Where the Body Was" by celebrated comics duo, Ed Brubaker and Sean Phillips. What starts innocently enough, with some feral Gen-X childhood crime-fighting, soon curdles into something darker: hidden affairs, small-time crooks, unrequited love and a dead body that nobody can quite explain. The mythology of the safe and honest American neighbourhood is left in tatters here by Brubaker and LTP has all the angles covered from its treehouse vantage on the cul-de-sac of Pelican lane! FastFacts@05:00; Summary@31:30; PIPES@46:30

Christian kicks things off with Monday Winners and Losers - Patsy scores front‑row tickets, Alex celebrates getting the wishbone and Christian gets made aware of “hot pelicans”. Plus, Signs You’re an Adult returns with sleep‑tracking shame, peg‑bag politics and listeners naming their cars. That leads into Bad Time for a Power Cut, more Australia’s Funniest Mum jokes, before the team dives into Brand Bands for At Work Time Wasters.See omnystudio.com/listener for privacy information.

The incredible Pelican players are back with their first Sherlock Holmes adventure! Learn more about your ad choices. Visit megaphone.fm/adchoices

Make a Logo on Fiverr Telycam's Mix One looks like the kind of production tool built for creators who need to move fast, pack light and still run a serious multi-camera show. Shown at NAB 2026, the Telycam Mix One combines a video switcher, touchscreen control surface and PTZ joystick into one portable unit aimed at live streamers, event producers, houses of worship, schools and mobile sports crews. The big headline: this is a six camera switcher that does not need a full rack of gear to get started. A Compact Switcher Built for Mobile Production The Telycam Mix One is designed as an all-in-one production console. Instead of carrying a separate switcher, PTZ controller and streaming encoder, this device puts those tools into a single portable box. That matters if you are producing basketball games, football games, presentations, interviews or live events where setup time is limited. The form factor is small enough to fit into a Pelican-style case, making it a practical option for creators who need to get in, connect cameras, produce the show and move on. Six Camera Inputs in One Box The Mix One supports up to six sources, giving producers a lot of flexibility for a portable system. The unit includes two HDMI inputs, two USB inputs and support for network-based video options including SRT, RTMP and NDI-HX3. That gives the Telycam Switcher room to handle traditional cameras, USB video sources and IP-based production workflows. For smaller productions, six cameras is more than enough to cover a wide shot, close-up, scoreboard, host camera, roaming angle and presentation feed. Touchscreen Control With Preview and Program The touchscreen is one of the Mix One's most useful features. You can control the switcher directly from the display using a finger or stylus, with preview and program areas visible on the screen. That makes it easier to see what is ready to go live before switching it to the main output. It also keeps the workflow familiar for anyone who has used a traditional video switcher, while still making the whole system feel more modern and compact. Built-In PTZ Joystick Control The integrated joystick is a major advantage for PTZ camera users. With the joystick, you can move a camera around, adjust framing and control shots from the same device used to switch the show. One smart detail is that PTZ control is tied to the preview side, not the live program feed. That means you can line up your next camera shot before sending it live, helping avoid awkward camera moves being seen by the audience. Streaming and Output Options The Mix One also includes streaming tools, with options for RTMP, SRT and NDI workflows. That gives users multiple ways to send a production out to streaming platforms, remote destinations or network-based video systems. On the back, the unit includes HDMI program outputs, USB connections, XLR microphone input, line in, line out and dual LAN ports. The dual network ports are useful for failover or production setups that need more reliable connectivity. The Mix One can also run on PoE, which reduces the amount of power gear needed on location. For mobile production, fewer cables and fewer power bricks can make a big difference. Computer Companion App Telycam also offers a companion app for computer control. That means the Mix One can be placed off to the side while an operator controls the production from a PC. That flexibility could be useful in venues where the switcher needs to stay near the cameras or network connections, but the producer wants to operate from a more comfortable position. Price and Availability The Telycam Mix One is expected to launch in June with a price of $1,999. For a portable production system that combines a six camera switcher, PTZ joystick, touchscreen interface, streaming tools and multiple input types, that price puts it in an interesting spot for creators and small production teams who want a compact live workflow without building out a larger control rig. First Impression The Telycam Mix One feels like a practical tool for real-world productions. It is not just a switcher. It is a portable control center for multi-camera live video, especially if your workflow already includes PTZ cameras and network-based video. For creators producing sports, events, presentations or on-location streams, this could be a strong all-in-one option. The portability, six-source support, built-in joystick and streaming features make the Telycam mix one worth watching as it gets closer to release. Find out more at their website https://telycam.com/mix-one.html Check out the Geekazine Merch, including "I AM AI " T-Shirt.  Thanks for reading! Don't forget to subscribe to Geekazine: RSS Feed - YouTubeTwitter - Facebook Tip Me via Paypal.me Send a Tip via Venmo RSS Bandwidth by Cachefly Get a 14 Day Trial Be a Patreon: Part of the Sconnie Geek Nation! Reviews: Geekazine gets products in to review. Opinions are of Geekazine.com. Sponsored content will be labeled as such. Read all policies on the Geekazine review page.  Reviews: Geekazine is also an affiliate of Amazon Last Updated on June 9, 2026 3:51 pm by Jeffrey PowersThe post Portable 6-Camera Switcher? Telycam Mix One Hands-On appeared first on Geekazine.

Henry Drake, a successful businessman is plagued by a terrifying "urge to kill" that he cannot control. Learn more about your ad choices. Visit megaphone.fm/adchoices

Most leaders think they're in the business of selling their product. JC Curleigh thinks that's exactly what limits your growth. And as CEO of Pelican, he's helping the company make a profound shift: they're not in the protective case business, they're in the protection business. JC understands that great brands sell more than products, and he knows how to position them the right way. In fact, it's how he led turnarounds at iconic brands like Levi's and Gibson Guitars.  In today's episode, you'll see how to use the same thinking to revitalize and expand your own brand. You'll also learn: How to make better decisions by being “aggressively patient” The incredible story behind the naming rights for Levi's Stadium What “helicopter vision” is, and why every leader should have it What you need instead of a “Plan B” Take your learning further. Get proven leadership advice from these (free!) resources: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠The How Leaders Lead App⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠: A vast library of 90-second leadership lessons to stay sharp on the go  ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Daily Insight Emails⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠: One small (but powerful!) leadership principle to focus on each day Whichever you choose, you can be sure you'll get the trusted leadership advice you need to advance your career, develop your team, and grow your business.

Mike, Steve, and Charlie played their daily "Triple Option" segment. Mike remembered former Eagles LB Jeremiah Trotter after evaluating his son Josiah in the 2026 NFL Draft. Steve and Charlie reviewed the lengthy list of former Pelican players in the NBA Playoffs. Mike also discussed Mike Tomlin's transition to broadcasting.

This episode (dated 10/10/1943) was never produced. The actress who auditioned (and got) the part of Nancy, saved the script and got to play the part 83 years later. You walk by a small shop and in the window you see dolls with such incredible detail, you stop in to get more information. Learn more about your ad choices. Visit megaphone.fm/adchoices

Lavinia and Florence, decide to take in a movie in the downtown area near where they live. There is a shortcut across a ravine that will take them there, but there is a problem, there's been a serial strangler in the area known as "The Lonely One". Learn more about your ad choices. Visit megaphone.fm/adchoices

Your driving on a country road when you hear, on the radio, that there is someone on the run after murdering three people with a meat cleaver at a nearby mental hospital. Learn more about your ad choices. Visit megaphone.fm/adchoices

You could start listing the locally owned restaurants that have closed already this year and tell a pretty dire story: Margot, Varallos, Pelican & Pig. And we're just three months into the year. But restaurants that are part of out-of-town investment groups have closed too — all while new concepts are opening up. Is it simply natural churn in a volatile business? We know it's more expensive than ever to open and maintain a restaurant, so we're looking at the economics and the local food scene with the people who watch it most closely.This episode was produced by Josh Deepan. Guests: Jill Melton, Edible Nashville Editor & Founder Brandon Styll, Nashville Restaurant Radio Host and Nashville Area Restaurant Alliance Founder (NARA) Mackensy Lunsford, Senior Dining Reporter, The Tennessean Naima Walker Fierce, Germantown Pub Primary Owner

Join Luigi Basco, a newly arrived Italian immigrant, as he tries navigating life in a new land and attends his first football game. Learn more about your ad choices. Visit megaphone.fm/adchoices

What if the nuclear industry's biggest problem has nothing to do with the reactor itself? And what happens when a SpaceX veteran decides he's the one to fix it? What you'll discover today… (00:00) From a bush pilot in Alaska to building SpaceX launch pads to reshaping nuclear infrastructure.  (06:10) Understanding the market and customer-driven innovation. (08:45) A bold new approach to nuclear energy innovation. (12:05) Financing future growth and sustainability: Flexible models for growth. (15:00) The reality and challenges of starting a start-up.  (18:00) Lessons from a sabbatical and the importance of reflection. (22:30) The importance of patience in startups. (25:00) Building customer trust in a skeptical market- winning over early adopters. (28:00) Navigating regulatory challenges early (29:25) The learning curve of transitioning from aerospace to nuclear  (30:20) Balancing innovation with industry responsibility  (33:30) How to build trust with investors (36:00) How to deal with doubts, fears, and keeping the momentum going in a startup. (37:20) The impact of fatherhood on leadership and managing stress as a founder (40:25) Applied Atomics' vision of the future More about the episode Ben Kellie is not a nuclear scientist. He's an infrastructure builder. He spent years at SpaceX leading the launch pad construction at Vandenberg and running the landing barge programme day to day — learning what it actually takes to push complex, high-stakes infrastructure into the world. When he left to found The Launch Company, he bootstrapped it, served every major venture-backed rocket company, and exited on his own terms. Then he took two years off to think. What he found, after long walks and deep dives into advanced fuels, carbon sequestration and the future of industry, was a single blocker: the lack of affordable, firm, zero-emission baseload power. That insight became Applied Atomics — a company now just 13 months old, with a reactor licence in hand, a plant design at 60%, a digital twin running real-time plant physics from a Pelican case, and signed customer letters of intent.  Applied Atomics is not waiting to perfect the reactor. It is vertically integrating well-understood, high-heritage nuclear technology with new control systems and a supply chain built for actual deployment. If you are a founder, investor, or operator in hard tech, energy, or infrastructure, this episode is a blueprint for how to move fast without losing discipline — and why the most powerful innovation is sometimes a better process, not a better reactor. Connect with us Peng-Sang Cau LinkedIn Website Ben Kellie LinkedIn Website

Join us for an afternoon with George Burns and Gracie Allen as Gracie makes her plans to run for president.. Learn more about your ad choices. Visit megaphone.fm/adchoices

Fr. Matingly's homily from The Pelican Summit. The Pelican Summit is a Catholic intellectual conference for women of all stages of life.The goal is to provide a means by which women can encourage, support, and help one another in fulfilling their vocation well, in both a practical and theoretical sense.

The Pelican Players tackle this classic horror. Three men tend a lighthouse off the coast of French Guiana. It's a boring, uneventful job until one night they get a visit from "The Flying Dutchman" Learn more about your ad choices. Visit megaphone.fm/adchoices

Steve and Charlie interviewed Oleh Kosel, a credentialed NBA reporter covering the Pelicans. Kosel projected Brandon Ingram to get a standing ovation from Pelican fans in his return at the Smoothie King Center. Kosel also shared his thoughts on Trey Murphy, Dejounte Murray, and the Pels' defense.

In this episode, Nick Guidry, Owner of the Pelican & Pig announces that he will be closing the doors to their restaurant this Saturday. We wanted to give him a way to tell his story. To talk about the people who made P & P special, and to thank all of the people who made it special for the last 7 years. This is becoming all too common these days, and unfortunately, this probably isn't the last one to close.

Picture this, if you will, In a 1974 world a company creates an AI computer and sells it to every government, business and home. All is well until a twelve year old little brat kid gets a hold of one, and the world goes..... Learn more about your ad choices. Visit megaphone.fm/adchoices

start set the show00:07:00 Memphis falls to T-Wolves00:13:00 Zach Edey surgery update00:14:00 Last night's NBA actionNBA on NBC throwback nightWCF contenders00:23:00 Men's college basketball news and notesAJ Dybantsa flirts with staying at BYUBill Self's ejectionMiami of Ohio still undefeated00:34:00 WNBA CBA negotiations00:44:00 DeAngelo Williams01:13:00 WTFJon Sumrall's photoshoot with a gatorCristo Fernandez makes soccer debutWhat's going on with Jim Carrey?Pelican on the loose

From our Christmas Sunday Showcase of this year. We begin our Pelican Players features on the Matinee! It's the day before Christmas at the Old Mission Plaza Church when Father Rojas discovers the statue of the infant Jesus has been stolen. It's only worth a few dollars but has great sentimental value. Friday and Smith promise to try to get it back for Christmas, but that means that they have less than 24 hours to catch the thief Learn more about your ad choices. Visit megaphone.fm/adchoices

Sarah and Vinnie are aging like a fine wine, and so is this old episode! Originally aired: April 2025

David Grubb, the host of "The Post Up" podcast, joined Sports Talk. Grubb reviewed the Pelicans' up-and-down play post All-Star Break. He criticized New Orleans' shooting issues and previewed their upcoming matchup against Golden State.

Da li su Srbi i Hrvati konačno pronašli zajednički jezik u bioskopu?

Florida continues to promote unfettered growth without paying attention to the water demands of all those new people and businesses. Pelican Island National Wildlife Refuge in Vero Beach was the first site in a program that now features nearly 600 locations. Paul Tritiak was the former refuge manager at Pelican Island and tells us how the refuge came to be."Welcome to Florida" patrons receive our weekly Florida Conservation Newsletter for only $5 per month.

Matt welcomes Producer /engineer/mixer and film composer Sanford Parker. As an artist he's performed and released albums with extreme heavy and industrial bands like Black Cross Hotel, Corrections House, Mirrors for Psychic Warfare and Minsk. Throughout the years he's collaborated with members of Sonic Youth, Ministry, Napalm Death and Neurosis as well as producing and mixing albums for Darkthrone, Voivod, Brutal Truth, Pelican, YOB, Hide, Youth Code, Wovenhand, Rwake, Local H and many others. TakeawaysSanford opened his studio in March 2020, just before the pandemic.He prefers working with independent artists and punk music.Chicago's music scene is affordable compared to other major cities.Managing overhead is crucial for running a successful studio.Sanford transitioned to mixing in the box for efficiency.He values genuine relationships with artists over bureaucracy.The pandemic shifted his work focus back to mixing.The flexibility of working remotely with clients.Learning to navigate financial discussions with bands.Independent music often allows for quicker decision-making.Links and Show Notes:Sanford's SiteMatt's Rant: Your JourneyCredits:Guest: Sanford ParkerHost/Engineer/Producer: Matt BoudreauWCA Theme Music: Cliff TruesdellThe Voice: Chuck Smith