Podcasts about Boxing Day

Jhye Richardson joins Brad Haddin and Adam Peacock to chat about his comeback into the Australian side after multiple injuries. He shares some of the worst ways he’s been injured, Starc and Boland’s incredible stamina, and his Boxing Day Ashes dream. Plus, Adam Zampa joins the show to share the best T20 XI he’s ever played with - featuring legends such as Kohli, de Villiers, Gayle, Mitch Marsh and more! Send your cricket club cap to Producer Joel at the following address: Joel Harrison 50 Goulburn St, Sydney, NSW, 2000 Follow on Apple, Spotify and the LiSTNR app Watch on YouTube Drop us a message on Instagram and TikTok! See omnystudio.com/listener for privacy information.

On Boxing Day 1996, David Spencer (11) and Patrick Warren (13) were out in Chelmsley Wood. They stayed out all night. They were last seen alive in the early hours of 27 December. They never came home. No confirmed crime scene.No bodies.No explanation that holds. This episode of Seeing Red follows what little is known, what was missed, and what people living on that estate have had to sit with for nearly thirty years. Because two children didn't disappear into thin air. And someone knows why they didn't make it back. Mark's new podcast, Dead Famous, can be found here on Spotify: ⁠https://open.spotify.com/show/6VsxMyj7rQ913iGQzyK1UG?si=luKLzUYvSQ2S3iQVD11V4g⁠ And here on Apple Podcasts: ⁠https://podcasts.apple.com/gb/podcast/dead-famous/id1866715220⁠ Why not BINGE Seeing Red's back catalogue of over a HUNDRED Patreon exclusive bonus episodes? Sign up and you can access them on Spotify really easily (or on the Patreon app, or wherever you normally listen - cancel any time): www.patreon.com/seeingredpodcast If you would like to GIFT a Patreon membership to a special someone, head to www.patreon.com/seeingredpodcast/gift If you would like to buy us a coffee (or wine!), hit the link below: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠https://www.buymeacoffee.com/seeingredtw⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Get your merch here: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠www.seeingredpodcast.co.uk⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Theme music arranged and composed by Holly-Jane Shears - check her work out at ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠www.soundcloud.com/DeadDogInBlackBag⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Learn more about your ad choices. Visit megaphone.fm/adchoices

On Boxing Day 1996, David Spencer (11) and Patrick Warren (13) were out in Chelmsley Wood. They stayed out all night. They were last seen alive in the early hours of 27 December. They never came home. No confirmed crime scene.No bodies.No explanation that holds. This episode of Seeing Red follows what little is known, what was missed, and what people living on that estate have had to sit with for nearly thirty years. Because two children didn't disappear into thin air. And someone knows why they didn't make it back. Mark's new podcast, Dead Famous, can be found here on Spotify: ⁠https://open.spotify.com/show/6VsxMyj7rQ913iGQzyK1UG?si=luKLzUYvSQ2S3iQVD11V4g⁠ And here on Apple Podcasts: ⁠https://podcasts.apple.com/gb/podcast/dead-famous/id1866715220⁠ Why not BINGE Seeing Red's back catalogue of over a HUNDRED Patreon exclusive bonus episodes? Sign up and you can access them on Spotify really easily (or on the Patreon app, or wherever you normally listen - cancel any time): www.patreon.com/seeingredpodcast If you would like to GIFT a Patreon membership to a special someone, head to www.patreon.com/seeingredpodcast/gift If you would like to buy us a coffee (or wine!), hit the link below: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠https://www.buymeacoffee.com/seeingredtw⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Get your merch here: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠www.seeingredpodcast.co.uk⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Theme music arranged and composed by Holly-Jane Shears - check her work out at ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠www.soundcloud.com/DeadDogInBlackBag⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Learn more about your ad choices. Visit megaphone.fm/adchoices

Season 63, Episodes 71-82, Spoiler Level CFS (Crazy ** Spoilers) Happy New Year! And welcome to season four of our little GHing show. In this episode Stacy and Kathy discuss Britt being a doctor again, Sidwell's Boxing Day party, Charlotte's and Valentin's reunion, Portia's truth revealed, whether Nathan is who is says he is, Drew's outburst on the stand, AND WILLOW'S FLASHBACK!!!!! We also need to know if you are all pro lapel on suits or not. Thank you for listening to our General Hospital podcast. If you enjoyed it, please subscribe and tell your friends. Drop us a review. And let us know your own musings and theories and fashion notes. Reach Stacy at Alexis@areweghing.com and Kathy at Felicia@areweghing.com. For more information, please visit us at www.areweghing.com Recorded 1-10-26, Music by Grammy award winning Alex Robinson https://www.musicbyalexrobinson.com/ and logo by the equally as amazing Jakob Evans.

In this week's Our Millwall Fans Show, host Eamonn Barclay warmly welcomes the passionate No One Likes Talkin team members—dedicated Millwall supporter Dave Hart, the former Lion and effervescent Phil Coleman, and the insightful Craig Wilson.We're also thrilled to have some special guests:Millwall's matchday TV and Audio reporter Karl Bates recounts his views of the season so far and looks ahead to the remainder of the season. And some tips for aspiring commentators..Gianluca Sardi found a historical photograph and presented copies to James Berylson, Mark Fairbrother, and Sean Daly. Debbie Julians checks out what led to the presentation ahead of our Boxing Day presentation.Swansea was reviewed, and Burnley previewed.Ted's Prediction goes on and on.This show offers a lively, engaging mix of conversations, filled with genuine passion for Millwall.Plus, enjoy inspiring insights from Paul Loding, who shares heartfelt thoughts on football, community pride, and the unique culture that makes Millwall more than just a football club.Music and audio credits:https://www.maritimeradio.co.ukhttps://www.FesliyanStudios.comhttps://www.millwallcommunity.org.uk/YouTube/ @zamparecords 

Happy New Year! You may have noticed that in 2025 we had moved toward YouTube as our primary podcasting platform. As we'll explain in the next State of Latent Space post, we'll be doubling down on Substack again and improving the experience for the over 100,000 of you who look out for our emails and website updates!We first mentioned Artificial Analysis in 2024, when it was still a side project in a Sydney basement. They then were one of the few Nat Friedman and Daniel Gross' AIGrant companies to raise a full seed round from them and have now become the independent gold standard for AI benchmarking—trusted by developers, enterprises, and every major lab to navigate the exploding landscape of models, providers, and capabilities.We have chatted with both Clementine Fourrier of HuggingFace's OpenLLM Leaderboard and (the freshly valued at $1.7B) Anastasios Angelopoulos of LMArena on their approaches to LLM evals and trendspotting, but Artificial Analysis have staked out an enduring and important place in the toolkit of the modern AI Engineer by doing the best job of independently running the most comprehensive set of evals across the widest range of open and closed models, and charting their progress for broad industry analyst use.George Cameron and Micah-Hill Smith have spent two years building Artificial Analysis into the platform that answers the questions no one else will: Which model is actually best for your use case? What are the real speed-cost trade-offs? And how open is “open” really?We discuss:* The origin story: built as a side project in 2023 while Micah was building a legal AI assistant, launched publicly in January 2024, and went viral after Swyx's retweet* Why they run evals themselves: labs prompt models differently, cherry-pick chain-of-thought examples (Google Gemini 1.0 Ultra used 32-shot prompts to beat GPT-4 on MMLU), and self-report inflated numbers* The mystery shopper policy: they register accounts not on their own domain and run intelligence + performance benchmarks incognito to prevent labs from serving different models on private endpoints* How they make money: enterprise benchmarking insights subscription (standardized reports on model deployment, serverless vs. managed vs. leasing chips) and private custom benchmarking for AI companies (no one pays to be on the public leaderboard)* The Intelligence Index (V3): synthesizes 10 eval datasets (MMLU, GPQA, agentic benchmarks, long-context reasoning) into a single score, with 95% confidence intervals via repeated runs* Omissions Index (hallucination rate): scores models from -100 to +100 (penalizing incorrect answers, rewarding ”I don't know”), and Claude models lead with the lowest hallucination rates despite not always being the smartest* GDP Val AA: their version of OpenAI's GDP-bench (44 white-collar tasks with spreadsheets, PDFs, PowerPoints), run through their Stirrup agent harness (up to 100 turns, code execution, web search, file system), graded by Gemini 3 Pro as an LLM judge (tested extensively, no self-preference bias)* The Openness Index: scores models 0-18 on transparency of pre-training data, post-training data, methodology, training code, and licensing (AI2 OLMo 2 leads, followed by Nous Hermes and NVIDIA Nemotron)* The smiling curve of AI costs: GPT-4-level intelligence is 100-1000x cheaper than at launch (thanks to smaller models like Amazon Nova), but frontier reasoning models in agentic workflows cost more than ever (sparsity, long context, multi-turn agents)* Why sparsity might go way lower than 5%: GPT-4.5 is ~5% active, Gemini models might be ~3%, and Omissions Index accuracy correlates with total parameters (not active), suggesting massive sparse models are the future* Token efficiency vs. turn efficiency: GPT-5 costs more per token but solves Tau-bench in fewer turns (cheaper overall), and models are getting better at using more tokens only when needed (5.1 Codex has tighter token distributions)* V4 of the Intelligence Index coming soon: adding GDP Val AA, Critical Point, hallucination rate, and dropping some saturated benchmarks (human-eval-style coding is now trivial for small models)Links to Artificial Analysis* Website: https://artificialanalysis.ai* George Cameron on X: https://x.com/georgecameron* Micah-Hill Smith on X: https://x.com/micahhsmithFull Episode on YouTubeTimestamps* 00:00 Introduction: Full Circle Moment and Artificial Analysis Origins* 01:19 Business Model: Independence and Revenue Streams* 04:33 Origin Story: From Legal AI to Benchmarking Need* 16:22 AI Grant and Moving to San Francisco* 19:21 Intelligence Index Evolution: From V1 to V3* 11:47 Benchmarking Challenges: Variance, Contamination, and Methodology* 13:52 Mystery Shopper Policy and Maintaining Independence* 28:01 New Benchmarks: Omissions Index for Hallucination Detection* 33:36 Critical Point: Hard Physics Problems and Research-Level Reasoning* 23:01 GDP Val AA: Agentic Benchmark for Real Work Tasks* 50:19 Stirrup Agent Harness: Open Source Agentic Framework* 52:43 Openness Index: Measuring Model Transparency Beyond Licenses* 58:25 The Smiling Curve: Cost Falling While Spend Rising* 1:02:32 Hardware Efficiency: Blackwell Gains and Sparsity Limits* 1:06:23 Reasoning Models and Token Efficiency: The Spectrum Emerges* 1:11:00 Multimodal Benchmarking: Image, Video, and Speech Arenas* 1:15:05 Looking Ahead: Intelligence Index V4 and Future Directions* 1:16:50 Closing: The Insatiable Demand for IntelligenceTranscriptMicah [00:00:06]: This is kind of a full circle moment for us in a way, because the first time artificial analysis got mentioned on a podcast was you and Alessio on Latent Space. Amazing.swyx [00:00:17]: Which was January 2024. I don't even remember doing that, but yeah, it was very influential to me. Yeah, I'm looking at AI News for Jan 17, or Jan 16, 2024. I said, this gem of a models and host comparison site was just launched. And then I put in a few screenshots, and I said, it's an independent third party. It clearly outlines the quality versus throughput trade-off, and it breaks out by model and hosting provider. I did give you s**t for missing fireworks, and how do you have a model benchmarking thing without fireworks? But you had together, you had perplexity, and I think we just started chatting there. Welcome, George and Micah, to Latent Space. I've been following your progress. Congrats on... It's been an amazing year. You guys have really come together to be the presumptive new gardener of AI, right? Which is something that...George [00:01:09]: Yeah, but you can't pay us for better results.swyx [00:01:12]: Yes, exactly.George [00:01:13]: Very important.Micah [00:01:14]: Start off with a spicy take.swyx [00:01:18]: Okay, how do I pay you?Micah [00:01:20]: Let's get right into that.swyx [00:01:21]: How do you make money?Micah [00:01:24]: Well, very happy to talk about that. So it's been a big journey the last couple of years. Artificial analysis is going to be two years old in January 2026. Which is pretty soon now. We first run the website for free, obviously, and give away a ton of data to help developers and companies navigate AI and make decisions about models, providers, technologies across the AI stack for building stuff. We're very committed to doing that and tend to keep doing that. We have, along the way, built a business that is working out pretty sustainably. We've got just over 20 people now and two main customer groups. So we want to be... We want to be who enterprise look to for data and insights on AI, so we want to help them with their decisions about models and technologies for building stuff. And then on the other side, we do private benchmarking for companies throughout the AI stack who build AI stuff. So no one pays to be on the website. We've been very clear about that from the very start because there's no use doing what we do unless it's independent AI benchmarking. Yeah. But turns out a bunch of our stuff can be pretty useful to companies building AI stuff.swyx [00:02:38]: And is it like, I am a Fortune 500, I need advisors on objective analysis, and I call you guys and you pull up a custom report for me, you come into my office and give me a workshop? What kind of engagement is that?George [00:02:53]: So we have a benchmarking and insight subscription, which looks like standardized reports that cover key topics or key challenges enterprises face when looking to understand AI and choose between all the technologies. And so, for instance, one of the report is a model deployment report, how to think about choosing between serverless inference, managed deployment solutions, or leasing chips. And running inference yourself is an example kind of decision that big enterprises face, and it's hard to reason through, like this AI stuff is really new to everybody. And so we try and help with our reports and insight subscription. Companies navigate that. We also do custom private benchmarking. And so that's very different from the public benchmarking that we publicize, and there's no commercial model around that. For private benchmarking, we'll at times create benchmarks, run benchmarks to specs that enterprises want. And we'll also do that sometimes for AI companies who have built things, and we help them understand what they've built with private benchmarking. Yeah. So that's a piece mainly that we've developed through trying to support everybody publicly with our public benchmarks. Yeah.swyx [00:04:09]: Let's talk about TechStack behind that. But okay, I'm going to rewind all the way to when you guys started this project. You were all the way in Sydney? Yeah. Well, Sydney, Australia for me.Micah [00:04:19]: George was an SF, but he's Australian, but he moved here already. Yeah.swyx [00:04:22]: And I remember I had the Zoom call with you. What was the impetus for starting artificial analysis in the first place? You know, you started with public benchmarks. And so let's start there. We'll go to the private benchmark. Yeah.George [00:04:33]: Why don't we even go back a little bit to like why we, you know, thought that it was needed? Yeah.Micah [00:04:40]: The story kind of begins like in 2022, 2023, like both George and I have been into AI stuff for quite a while. In 2023 specifically, I was trying to build a legal AI research assistant. So it actually worked pretty well for its era, I would say. Yeah. Yeah. So I was finding that the more you go into building something using LLMs, the more each bit of what you're doing ends up being a benchmarking problem. So had like this multistage algorithm thing, trying to figure out what the minimum viable model for each bit was, trying to optimize every bit of it as you build that out, right? Like you're trying to think about accuracy, a bunch of other metrics and performance and cost. And mostly just no one was doing anything to independently evaluate all the models. And certainly not to look at the trade-offs for speed and cost. So we basically set out just to build a thing that developers could look at to see the trade-offs between all of those things measured independently across all the models and providers. Honestly, it was probably meant to be a side project when we first started doing it.swyx [00:05:49]: Like we didn't like get together and say like, Hey, like we're going to stop working on all this stuff. I'm like, this is going to be our main thing. When I first called you, I think you hadn't decided on starting a company yet.Micah [00:05:58]: That's actually true. I don't even think we'd pause like, like George had an acquittance job. I didn't quit working on my legal AI thing. Like it was genuinely a side project.George [00:06:05]: We built it because we needed it as people building in the space and thought, Oh, other people might find it useful too. So we'll buy domain and link it to the Vercel deployment that we had and tweet about it. And, but very quickly it started getting attention. Thank you, Swyx for, I think doing an initial retweet and spotlighting it there. This project that we released. And then very quickly though, it was useful to others, but very quickly it became more useful as the number of models released accelerated. We had Mixtrel 8x7B and it was a key. That's a fun one. Yeah. Like a open source model that really changed the landscape and opened up people's eyes to other serverless inference providers and thinking about speed, thinking about cost. And so that was a key. And so it became more useful quite quickly. Yeah.swyx [00:07:02]: What I love talking to people like you who sit across the ecosystem is, well, I have theories about what people want, but you have data and that's obviously more relevant. But I want to stay on the origin story a little bit more. When you started out, I would say, I think the status quo at the time was every paper would come out and they would report their numbers versus competitor numbers. And that's basically it. And I remember I did the legwork. I think everyone has some knowledge. I think there's some version of Excel sheet or a Google sheet where you just like copy and paste the numbers from every paper and just post it up there. And then sometimes they don't line up because they're independently run. And so your numbers are going to look better than... Your reproductions of other people's numbers are going to look worse because you don't hold their models correctly or whatever the excuse is. I think then Stanford Helm, Percy Liang's project would also have some of these numbers. And I don't know if there's any other source that you can cite. The way that if I were to start artificial analysis at the same time you guys started, I would have used the Luther AI's eval framework harness. Yup.Micah [00:08:06]: Yup. That was some cool stuff. At the end of the day, running these evals, it's like if it's a simple Q&A eval, all you're doing is asking a list of questions and checking if the answers are right, which shouldn't be that crazy. But it turns out there are an enormous number of things that you've got control for. And I mean, back when we started the website. Yeah. Yeah. Like one of the reasons why we realized that we had to run the evals ourselves and couldn't just take rules from the labs was just that they would all prompt the models differently. And when you're competing over a few points, then you can pretty easily get- You can put the answer into the model. Yeah. That in the extreme. And like you get crazy cases like back when I'm Googled a Gemini 1.0 Ultra and needed a number that would say it was better than GPT-4 and like constructed, I think never published like chain of thought examples. 32 of them in every topic in MLU to run it, to get the score, like there are so many things that you- They never shipped Ultra, right? That's the one that never made it up. Not widely. Yeah. Yeah. Yeah. I mean, I'm sure it existed, but yeah. So we were pretty sure that we needed to run them ourselves and just run them in the same way across all the models. Yeah. And we were, we also did certain from the start that you couldn't look at those in isolation. You needed to look at them alongside the cost and performance stuff. Yeah.swyx [00:09:24]: Okay. A couple of technical questions. I mean, so obviously I also thought about this and I didn't do it because of cost. Yep. Did you not worry about costs? Were you funded already? Clearly not, but you know. No. Well, we definitely weren't at the start.Micah [00:09:36]: So like, I mean, we're paying for it personally at the start. There's a lot of money. Well, the numbers weren't nearly as bad a couple of years ago. So we certainly incurred some costs, but we were probably in the order of like hundreds of dollars of spend across all the benchmarking that we were doing. Yeah. So nothing. Yeah. It was like kind of fine. Yeah. Yeah. These days that's gone up an enormous amount for a bunch of reasons that we can talk about. But yeah, it wasn't that bad because you can also remember that like the number of models we were dealing with was hardly any and the complexity of the stuff that we wanted to do to evaluate them was a lot less. Like we were just asking some Q&A type questions and then one specific thing was for a lot of evals initially, we were just like sampling an answer. You know, like, what's the answer for this? Like, we didn't want to go into the answer directly without letting the models think. We weren't even doing chain of thought stuff initially. And that was the most useful way to get some results initially. Yeah.swyx [00:10:33]: And so for people who haven't done this work, literally parsing the responses is a whole thing, right? Like because sometimes the models, the models can answer any way they feel fit and sometimes they actually do have the right answer, but they just returned the wrong format and they will get a zero for that unless you work it into your parser. And that involves more work. And so, I mean, but there's an open question whether you should give it points for not following your instructions on the format.Micah [00:11:00]: It depends what you're looking at, right? Because you can, if you're trying to see whether or not it can solve a particular type of reasoning problem, and you don't want to test it on its ability to do answer formatting at the same time, then you might want to use an LLM as answer extractor approach to make sure that you get the answer out no matter how unanswered. But these days, it's mostly less of a problem. Like, if you instruct a model and give it examples of what the answers should look like, it can get the answers in your format, and then you can do, like, a simple regex.swyx [00:11:28]: Yeah, yeah. And then there's other questions around, I guess, sometimes if you have a multiple choice question, sometimes there's a bias towards the first answer, so you have to randomize the responses. All these nuances, like, once you dig into benchmarks, you're like, I don't know how anyone believes the numbers on all these things. It's so dark magic.Micah [00:11:47]: You've also got, like… You've got, like, the different degrees of variance in different benchmarks, right? Yeah. So, if you run four-question multi-choice on a modern reasoning model at the temperatures suggested by the labs for their own models, the variance that you can see on a four-question multi-choice eval is pretty enormous if you only do a single run of it and it has a small number of questions, especially. So, like, one of the things that we do is run an enormous number of all of our evals when we're developing new ones and doing upgrades to our intelligence index to bring in new things. Yeah. So, that we can dial in the right number of repeats so that we can get to the 95% confidence intervals that we're comfortable with so that when we pull that together, we can be confident in intelligence index to at least as tight as, like, a plus or minus one at a 95% confidence. Yeah.swyx [00:12:32]: And, again, that just adds a straight multiple to the cost. Oh, yeah. Yeah, yeah.George [00:12:37]: So, that's one of many reasons that cost has gone up a lot more than linearly over the last couple of years. We report a cost to run the artificial analysis. We report a cost to run the artificial analysis intelligence index on our website, and currently that's assuming one repeat in terms of how we report it because we want to reflect a bit about the weighting of the index. But our cost is actually a lot higher than what we report there because of the repeats.swyx [00:13:03]: Yeah, yeah, yeah. And probably this is true, but just checking, you don't have any special deals with the labs. They don't discount it. You just pay out of pocket or out of your sort of customer funds. Oh, there is a mix. So, the issue is that sometimes they may give you a special end point, which is… Ah, 100%.Micah [00:13:21]: Yeah, yeah, yeah. Exactly. So, we laser focus, like, on everything we do on having the best independent metrics and making sure that no one can manipulate them in any way. There are quite a lot of processes we've developed over the last couple of years to make that true for, like, the one you bring up, like, right here of the fact that if we're working with a lab, if they're giving us a private endpoint to evaluate a model, that it is totally possible. That what's sitting behind that black box is not the same as they serve on a public endpoint. We're very aware of that. We have what we call a mystery shopper policy. And so, and we're totally transparent with all the labs we work with about this, that we will register accounts not on our own domain and run both intelligence evals and performance benchmarks… Yeah, that's the job. …without them being able to identify it. And no one's ever had a problem with that. Because, like, a thing that turns out to actually be quite a good… …good factor in the industry is that they all want to believe that none of their competitors could manipulate what we're doing either.swyx [00:14:23]: That's true. I never thought about that. I've been in the database data industry prior, and there's a lot of shenanigans around benchmarking, right? So I'm just kind of going through the mental laundry list. Did I miss anything else in this category of shenanigans? Oh, potential shenanigans.Micah [00:14:36]: I mean, okay, the biggest one, like, that I'll bring up, like, is more of a conceptual one, actually, than, like, direct shenanigans. It's that the things that get measured become things that get targeted by labs that they're trying to build, right? Exactly. So that doesn't mean anything that we should really call shenanigans. Like, I'm not talking about training on test set. But if you know that you're going to be great at another particular thing, if you're a researcher, there are a whole bunch of things that you can do to try to get better at that thing that preferably are going to be helpful for a wide range of how actual users want to use the thing that you're building. But will not necessarily work. Will not necessarily do that. So, for instance, the models are exceptional now at answering competition maths problems. There is some relevance of that type of reasoning, that type of work, to, like, how we might use modern coding agents and stuff. But it's clearly not one for one. So the thing that we have to be aware of is that once an eval becomes the thing that everyone's looking at, scores can get better on it without there being a reflection of overall generalized intelligence of these models. Getting better. That has been true for the last couple of years. It'll be true for the next couple of years. There's no silver bullet to defeat that other than building new stuff to stay relevant and measure the capabilities that matter most to real users. Yeah.swyx [00:15:58]: And we'll cover some of the new stuff that you guys are building as well, which is cool. Like, you used to just run other people's evals, but now you're coming up with your own. And I think, obviously, that is a necessary path once you're at the frontier. You've exhausted all the existing evals. I think the next point in history that I have for you is AI Grant that you guys decided to join and move here. What was it like? I think you were in, like, batch two? Batch four. Batch four. Okay.Micah [00:16:26]: I mean, it was great. Nat and Daniel are obviously great. And it's a really cool group of companies that we were in AI Grant alongside. It was really great to get Nat and Daniel on board. Obviously, they've done a whole lot of great work in the space with a lot of leading companies and were extremely aligned. With the mission of what we were trying to do. Like, we're not quite typical of, like, a lot of the other AI startups that they've invested in.swyx [00:16:53]: And they were very much here for the mission of what we want to do. Did they say any advice that really affected you in some way or, like, were one of the events very impactful? That's an interesting question.Micah [00:17:03]: I mean, I remember fondly a bunch of the speakers who came and did fireside chats at AI Grant.swyx [00:17:09]: Which is also, like, a crazy list. Yeah.George [00:17:11]: Oh, totally. Yeah, yeah, yeah. There was something about, you know, speaking to Nat and Daniel about the challenges of working through a startup and just working through the questions that don't have, like, clear answers and how to work through those kind of methodically and just, like, work through the hard decisions. And they've been great mentors to us as we've built artificial analysis. Another benefit for us was that other companies in the batch and other companies in AI Grant are pushing the capabilities. Yeah. And I think that's a big part of what AI can do at this time. And so being in contact with them, making sure that artificial analysis is useful to them has been fantastic for supporting us in working out how should we build out artificial analysis to continue to being useful to those, like, you know, building on AI.swyx [00:17:59]: I think to some extent, I'm mixed opinion on that one because to some extent, your target audience is not people in AI Grants who are obviously at the frontier. Yeah. Do you disagree?Micah [00:18:09]: To some extent. To some extent. But then, so a lot of what the AI Grant companies are doing is taking capabilities coming out of the labs and trying to push the limits of what they can do across the entire stack for building great applications, which actually makes some of them pretty archetypical power users of artificial analysis. Some of the people with the strongest opinions about what we're doing well and what we're not doing well and what they want to see next from us. Yeah. Yeah. Because when you're building any kind of AI application now, chances are you're using a whole bunch of different models. You're maybe switching reasonably frequently for different models and different parts of your application to optimize what you're able to do with them at an accuracy level and to get better speed and cost characteristics. So for many of them, no, they're like not commercial customers of ours, like we don't charge for all our data on the website. Yeah. They are absolutely some of our power users.swyx [00:19:07]: So let's talk about just the evals as well. So you start out from the general like MMU and GPQA stuff. What's next? How do you sort of build up to the overall index? What was in V1 and how did you evolve it? Okay.Micah [00:19:22]: So first, just like background, like we're talking about the artificial analysis intelligence index, which is our synthesis metric that we pulled together currently from 10 different eval data sets to give what? We're pretty much the same as that. Pretty confident is the best single number to look at for how smart the models are. Obviously, it doesn't tell the whole story. That's why we published the whole website of all the charts to dive into every part of it and look at the trade-offs. But best single number. So right now, it's got a bunch of Q&A type data sets that have been very important to the industry, like a couple that you just mentioned. It's also got a couple of agentic data sets. It's got our own long context reasoning data set and some other use case focused stuff. As time goes on. The things that we're most interested in that are going to be important to the capabilities that are becoming more important for AI, what developers are caring about, are going to be first around agentic capabilities. So surprise, surprise. We're all loving our coding agents and how the model is going to perform like that and then do similar things for different types of work are really important to us. The linking to use cases to economically valuable use cases are extremely important to us. And then we've got some of the. Yeah. These things that the models still struggle with, like working really well over long contexts that are not going to go away as specific capabilities and use cases that we need to keep evaluating.swyx [00:20:46]: But I guess one thing I was driving was like the V1 versus the V2 and how bad it was over time.Micah [00:20:53]: Like how we've changed the index to where we are.swyx [00:20:55]: And I think that reflects on the change in the industry. Right. So that's a nice way to tell that story.Micah [00:21:00]: Well, V1 would be completely saturated right now. Almost every model coming out because doing things like writing the Python functions and human evil is now pretty trivial. It's easy to forget, actually, I think how much progress has been made in the last two years. Like we obviously play the game constantly of like the today's version versus last week's version and the week before and all of the small changes in the horse race between the current frontier and who has the best like smaller than 10B model like right now this week. Right. And that's very important to a lot of developers and people and especially in this particular city of San Francisco. But when you zoom out a couple of years ago, literally most of what we were doing to evaluate the models then would all be 100% solved by even pretty small models today. And that's been one of the key things, by the way, that's driven down the cost of intelligence at every tier of intelligence. We can talk about more in a bit. So V1, V2, V3, we made things harder. We covered a wider range of use cases. And we tried to get closer to things developers care about as opposed to like just the Q&A type stuff that MMLU and GPQA represented. Yeah.swyx [00:22:12]: I don't know if you have anything to add there. Or we could just go right into showing people the benchmark and like looking around and asking questions about it. Yeah.Micah [00:22:21]: Let's do it. Okay. This would be a pretty good way to chat about a few of the new things we've launched recently. Yeah.George [00:22:26]: And I think a little bit about the direction that we want to take it. And we want to push benchmarks. Currently, the intelligence index and evals focus a lot on kind of raw intelligence. But we kind of want to diversify how we think about intelligence. And we can talk about it. But kind of new evals that we've kind of built and partnered on focus on topics like hallucination. And we've got a lot of topics that I think are not covered by the current eval set that should be. And so we want to bring that forth. But before we get into that.swyx [00:23:01]: And so for listeners, just as a timestamp, right now, number one is Gemini 3 Pro High. Then followed by Cloud Opus at 70. Just 5.1 high. You don't have 5.2 yet. And Kimi K2 Thinking. Wow. Still hanging in there. So those are the top four. That will date this podcast quickly. Yeah. Yeah. I mean, I love it. I love it. No, no. 100%. Look back this time next year and go, how cute. Yep.George [00:23:25]: Totally. A quick view of that is, okay, there's a lot. I love it. I love this chart. Yeah.Micah [00:23:30]: This is such a favorite, right? Yeah. And almost every talk that George or I give at conferences and stuff, we always put this one up first to just talk about situating where we are in this moment in history. This, I think, is the visual version of what I was saying before about the zooming out and remembering how much progress there's been. If we go back to just over a year ago, before 01, before Cloud Sonnet 3.5, we didn't have reasoning models or coding agents as a thing. And the game was very, very different. If we go back even a little bit before then, we're in the era where, when you look at this chart, open AI was untouchable for well over a year. And, I mean, you would remember that time period well of there being very open questions about whether or not AI was going to be competitive, like full stop, whether or not open AI would just run away with it, whether we would have a few frontier labs and no one else would really be able to do anything other than consume their APIs. I am quite happy overall that the world that we have ended up in is one where... Multi-model. Absolutely. And strictly more competitive every quarter over the last few years. Yeah. This year has been insane. Yeah.George [00:24:42]: You can see it. This chart with everything added is hard to read currently. There's so many dots on it, but I think it reflects a little bit what we felt, like how crazy it's been.swyx [00:24:54]: Why 14 as the default? Is that a manual choice? Because you've got service now in there that are less traditional names. Yeah.George [00:25:01]: It's models that we're kind of highlighting by default in our charts, in our intelligence index. Okay.swyx [00:25:07]: You just have a manually curated list of stuff.George [00:25:10]: Yeah, that's right. But something that I actually don't think every artificial analysis user knows is that you can customize our charts and choose what models are highlighted. Yeah. And so if we take off a few names, it gets a little easier to read.swyx [00:25:25]: Yeah, yeah. A little easier to read. Totally. Yeah. But I love that you can see the all one jump. Look at that. September 2024. And the DeepSeek jump. Yeah.George [00:25:34]: Which got close to OpenAI's leadership. They were so close. I think, yeah, we remember that moment. Around this time last year, actually.Micah [00:25:44]: Yeah, yeah, yeah. I agree. Yeah, well, a couple of weeks. It was Boxing Day in New Zealand when DeepSeek v3 came out. And we'd been tracking DeepSeek and a bunch of the other global players that were less known over the second half of 2024 and had run evals on the earlier ones and stuff. I very distinctly remember Boxing Day in New Zealand, because I was with family for Christmas and stuff, running the evals and getting back result by result on DeepSeek v3. So this was the first of their v3 architecture, the 671b MOE.Micah [00:26:19]: And we were very, very impressed. That was the moment where we were sure that DeepSeek was no longer just one of many players, but had jumped up to be a thing. The world really noticed when they followed that up with the RL working on top of v3 and R1 succeeding a few weeks later. But the groundwork for that absolutely was laid with just extremely strong base model, completely open weights that we had as the best open weights model. So, yeah, that's the thing that you really see in the game. But I think that we got a lot of good feedback on Boxing Day. us on Boxing Day last year.George [00:26:48]: Boxing Day is the day after Christmas for those not familiar.George [00:26:54]: I'm from Singapore.swyx [00:26:55]: A lot of us remember Boxing Day for a different reason, for the tsunami that happened. Oh, of course. Yeah, but that was a long time ago. So yeah. So this is the rough pitch of AAQI. Is it A-A-Q-I or A-A-I-I? I-I. Okay. Good memory, though.Micah [00:27:11]: I don't know. I'm not used to it. Once upon a time, we did call it Quality Index, and we would talk about quality, performance, and price, but we changed it to intelligence.George [00:27:20]: There's been a few naming changes. We added hardware benchmarking to the site, and so benchmarks at a kind of system level. And so then we changed our throughput metric to, we now call it output speed, and thenswyx [00:27:32]: throughput makes sense at a system level, so we took that name. Take me through more charts. What should people know? Obviously, the way you look at the site is probably different than how a beginner might look at it.Micah [00:27:42]: Yeah, that's fair. There's a lot of fun stuff to dive into. Maybe so we can hit past all the, like, we have lots and lots of emails and stuff. The interesting ones to talk about today that would be great to bring up are a few of our recent things, I think, that probably not many people will be familiar with yet. So first one of those is our omniscience index. So this one is a little bit different to most of the intelligence evils that we've run. We built it specifically to look at the embedded knowledge in the models and to test hallucination by looking at when the model doesn't know the answer, so not able to get it correct, what's its probability of saying, I don't know, or giving an incorrect answer. So the metric that we use for omniscience goes from negative 100 to positive 100. Because we're simply taking off a point if you give an incorrect answer to the question. We're pretty convinced that this is an example of where it makes most sense to do that, because it's strictly more helpful to say, I don't know, instead of giving a wrong answer to factual knowledge question. And one of our goals is to shift the incentive that evils create for models and the labs creating them to get higher scores. And almost every evil across all of AI up until this point, it's been graded by simple percentage correct as the main metric, the main thing that gets hyped. And so you should take a shot at everything. There's no incentive to say, I don't know. So we did that for this one here.swyx [00:29:22]: I think there's a general field of calibration as well, like the confidence in your answer versus the rightness of the answer. Yeah, we completely agree. Yeah. Yeah.George [00:29:31]: On that. And one reason that we didn't do that is because. Or put that into this index is that we think that the, the way to do that is not to ask the models how confident they are.swyx [00:29:43]: I don't know. Maybe it might be though. You put it like a JSON field, say, say confidence and maybe it spits out something. Yeah. You know, we have done a few evils podcasts over the, over the years. And when we did one with Clementine of hugging face, who maintains the open source leaderboard, and this was one of her top requests, which is some kind of hallucination slash lack of confidence calibration thing. And so, Hey, this is one of them.Micah [00:30:05]: And I mean, like anything that we do, it's not a perfect metric or the whole story of everything that you think about as hallucination. But yeah, it's pretty useful and has some interesting results. Like one of the things that we saw in the hallucination rate is that anthropics Claude models at the, the, the very left-hand side here with the lowest hallucination rates out of the models that we've evaluated amnesty is on. That is an interesting fact. I think it probably correlates with a lot of the previously, not really measured vibes stuff that people like about some of the Claude models. Is the dataset public or what's is it, is there a held out set? There's a hell of a set for this one. So we, we have published a public test set, but we we've only published 10% of it. The reason is that for this one here specifically, it would be very, very easy to like have data contamination because it is just factual knowledge questions. We would. We'll update it at a time to also prevent that, but with yeah, kept most of it held out so that we can keep it reliable for a long time. It leads us to a bunch of really cool things, including breakdown quite granularly by topic. And so we've got some of that disclosed on the website publicly right now, and there's lots more coming in terms of our ability to break out very specific topics. Yeah.swyx [00:31:23]: I would be interested. Let's, let's dwell a little bit on this hallucination one. I noticed that Haiku hallucinates less than Sonnet hallucinates less than Opus. And yeah. Would that be the other way around in a normal capability environments? I don't know. What's, what do you make of that?George [00:31:37]: One interesting aspect is that we've found that there's not really a, not a strong correlation between intelligence and hallucination, right? That's to say that the smarter the models are in a general sense, isn't correlated with their ability to, when they don't know something, say that they don't know. It's interesting that Gemini three pro preview was a big leap over here. Gemini 2.5. Flash and, and, and 2.5 pro, but, and if I add pro quickly here.swyx [00:32:07]: I bet pro's really good. Uh, actually no, I meant, I meant, uh, the GPT pros.George [00:32:12]: Oh yeah.swyx [00:32:13]: Cause GPT pros are rumored. We don't know for a fact that it's like eight runs and then with the LM judge on top. Yeah.George [00:32:20]: So we saw a big jump in, this is accuracy. So this is just percent that they get, uh, correct and Gemini three pro knew a lot more than the other models. And so big jump in accuracy. But relatively no change between the Google Gemini models, between releases. And the hallucination rate. Exactly. And so it's likely due to just kind of different post-training recipe, between the, the Claude models. Yeah.Micah [00:32:45]: Um, there's, there's driven this. Yeah. You can, uh, you can partially blame us and how we define intelligence having until now not defined hallucination as a negative in the way that we think about intelligence.swyx [00:32:56]: And so that's what we're changing. Uh, I know many smart people who are confidently incorrect.George [00:33:02]: Uh, look, look at that. That, that, that is very humans. Very true. And there's times and a place for that. I think our view is that hallucination rate makes sense in this context where it's around knowledge, but in many cases, people want the models to hallucinate, to have a go. Often that's the case in coding or when you're trying to generate newer ideas. One eval that we added to artificial analysis is, is, is critical point and it's really hard, uh, physics problems. Okay.swyx [00:33:32]: And is it sort of like a human eval type or something different or like a frontier math type?George [00:33:37]: It's not dissimilar to frontier frontier math. So these are kind of research questions that kind of academics in the physics physics world would be able to answer, but models really struggled to answer. So the top score here is not 9%.swyx [00:33:51]: And when the people that, that created this like Minway and, and, and actually off via who was kind of behind sweep and what organization is this? Oh, is this, it's Princeton.George [00:34:01]: Kind of range of academics from, from, uh, different academic institutions, really smart people. They talked about how they turn the models up in terms of the temperature as high temperature as they can, where they're trying to explore kind of new ideas in physics as a, as a thought partner, just because they, they want the models to hallucinate. Um, yeah, sometimes it's something new. Yeah, exactly.swyx [00:34:21]: Um, so not right in every situation, but, um, I think it makes sense, you know, to test hallucination in scenarios where it makes sense. Also, the obvious question is, uh, this is one of. Many that there is there, every lab has a system card that shows some kind of hallucination number, and you've chosen to not, uh, endorse that and you've made your own. And I think that's a, that's a choice. Um, totally in some sense, the rest of artificial analysis is public benchmarks that other people can independently rerun. You provide it as a service here. You have to fight the, well, who are we to, to like do this? And your, your answer is that we have a lot of customers and, you know, but like, I guess, how do you converge the individual?Micah [00:35:08]: I mean, I think, I think for hallucinations specifically, there are a bunch of different things that you might care about reasonably, and that you'd measure quite differently, like we've called this a amnesty and solutionation rate, not trying to declare the, like, it's humanity's last hallucination. You could, uh, you could have some interesting naming conventions and all this stuff. Um, the biggest picture answer to that. It's something that I actually wanted to mention. Just as George was explaining, critical point as well is, so as we go forward, we are building evals internally. We're partnering with academia and partnering with AI companies to build great evals. We have pretty strong views on, in various ways for different parts of the AI stack, where there are things that are not being measured well, or things that developers care about that should be measured more and better. And we intend to be doing that. We're not obsessed necessarily with that. Everything we do, we have to do entirely within our own team. Critical point. As a cool example of where we were a launch partner for it, working with academia, we've got some partnerships coming up with a couple of leading companies. Those ones, obviously we have to be careful with on some of the independent stuff, but with the right disclosure, like we're completely comfortable with that. A lot of the labs have released great data sets in the past that we've used to great success independently. And so it's between all of those techniques, we're going to be releasing more stuff in the future. Cool.swyx [00:36:26]: Let's cover the last couple. And then we'll, I want to talk about your trends analysis stuff, you know? Totally.Micah [00:36:31]: So that actually, I have one like little factoid on omniscience. If you go back up to accuracy on omniscience, an interesting thing about this accuracy metric is that it tracks more closely than anything else that we measure. The total parameter count of models makes a lot of sense intuitively, right? Because this is a knowledge eval. This is the pure knowledge metric. We're not looking at the index and the hallucination rate stuff that we think is much more about how the models are trained. This is just what facts did they recall? And yeah, it tracks parameter count extremely closely. Okay.swyx [00:37:05]: What's the rumored size of GPT-3 Pro? And to be clear, not confirmed for any official source, just rumors. But rumors do fly around. Rumors. I get, I hear all sorts of numbers. I don't know what to trust.Micah [00:37:17]: So if you, if you draw the line on omniscience accuracy versus total parameters, we've got all the open ways models, you can squint and see that likely the leading frontier models right now are quite a lot bigger than the ones that we're seeing right now. And the one trillion parameters that the open weights models cap out at, and the ones that we're looking at here, there's an interesting extra data point that Elon Musk revealed recently about XAI that for three trillion parameters for GROK 3 and 4, 6 trillion for GROK 5, but that's not out yet. Take those together, have a look. You might reasonably form a view that there's a pretty good chance that Gemini 3 Pro is bigger than that, that it could be in the 5 to 10 trillion parameters. To be clear, I have absolutely no idea, but just based on this chart, like that's where you would, you would land if you have a look at it. Yeah.swyx [00:38:07]: And to some extent, I actually kind of discourage people from guessing too much because what does it really matter? Like as long as they can serve it as a sustainable cost, that's about it. Like, yeah, totally.George [00:38:17]: They've also got different incentives in play compared to like open weights models who are thinking to supporting others in self-deployment for the labs who are doing inference at scale. It's I think less about total parameters in many cases. When thinking about inference costs and more around number of active parameters. And so there's a bit of an incentive towards larger sparser models. Agreed.Micah [00:38:38]: Understood. Yeah. Great. I mean, obviously if you're a developer or company using these things, not exactly as you say, it doesn't matter. You should be looking at all the different ways that we measure intelligence. You should be looking at cost to run index number and the different ways of thinking about token efficiency and cost efficiency based on the list prices, because that's all it matters.swyx [00:38:56]: It's not as good for the content creator rumor mill where I can say. Oh, GPT-4 is this small circle. Look at GPT-5 is this big circle. And then there used to be a thing for a while. Yeah.Micah [00:39:07]: But that is like on its own, actually a very interesting one, right? That is it just purely that chances are the last couple of years haven't seen a dramatic scaling up in the total size of these models. And so there's a lot of room to go up properly in total size of the models, especially with the upcoming hardware generations. Yes.swyx [00:39:29]: So, you know. Taking off my shitposting face for a minute. Yes. Yes. At the same time, I do feel like, you know, especially coming back from Europe, people do feel like Ilya is probably right that the paradigm is doesn't have many more orders of magnitude to scale out more. And therefore we need to start exploring at least a different path. GDPVal, I think it's like only like a month or so old. I was also very positive when it first came out. I actually talked to Tejo, who was the lead researcher on that. Oh, cool. And you have your own version.George [00:39:59]: It's a fantastic. It's a fantastic data set. Yeah.swyx [00:40:01]: And maybe it will recap for people who are still out of it. It's like 44 tasks based on some kind of GDP cutoff that's like meant to represent broad white collar work that is not just coding. Yeah.Micah [00:40:12]: Each of the tasks have a whole bunch of detailed instructions, some input files for a lot of them. It's within the 44 is divided into like two hundred and twenty two to five, maybe subtasks that are the level of that we run through the agenda. And yeah, they're really interesting. I will say that it doesn't. It doesn't necessarily capture like all the stuff that people do at work. No avail is perfect is always going to be more things to look at, largely because in order to make the tasks well enough to find that you can run them, they need to only have a handful of input files and very specific instructions for that task. And so I think the easiest way to think about them are that they're like quite hard take home exam tasks that you might do in an interview process.swyx [00:40:56]: Yeah, for listeners, it is not no longer like a long prompt. It is like, well, here's a zip file with like a spreadsheet or a PowerPoint deck or a PDF and go nuts and answer this question.George [00:41:06]: OpenAI released a great data set and they released a good paper which looks at performance across the different web chat bots on the data set. It's a great paper, encourage people to read it. What we've done is taken that data set and turned it into an eval that can be run on any model. So we created a reference agentic harness that can run. Run the models on the data set, and then we developed evaluator approach to compare outputs. That's kind of AI enabled, so it uses Gemini 3 Pro Preview to compare results, which we tested pretty comprehensively to ensure that it's aligned to human preferences. One data point there is that even as an evaluator, Gemini 3 Pro, interestingly, doesn't do actually that well. So that's kind of a good example of what we've done in GDPVal AA.swyx [00:42:01]: Yeah, the thing that you have to watch out for with LLM judge is self-preference that models usually prefer their own output, and in this case, it was not. Totally.Micah [00:42:08]: I think the way that we're thinking about the places where it makes sense to use an LLM as judge approach now, like quite different to some of the early LLM as judge stuff a couple of years ago, because some of that and MTV was a great project that was a good example of some of this a while ago was about judging conversations and like a lot of style type stuff. Here, we've got the task that the grader and grading model is doing is quite different to the task of taking the test. When you're taking the test, you've got all of the agentic tools you're working with, the code interpreter and web search, the file system to go through many, many turns to try to create the documents. Then on the other side, when we're grading it, we're running it through a pipeline to extract visual and text versions of the files and be able to provide that to Gemini, and we're providing the criteria for the task and getting it to pick which one more effectively meets the criteria of the task. Yeah. So we've got the task out of two potential outcomes. It turns out that we proved that it's just very, very good at getting that right, matched with human preference a lot of the time, because I think it's got the raw intelligence, but it's combined with the correct representation of the outputs, the fact that the outputs were created with an agentic task that is quite different to the way the grading model works, and we're comparing it against criteria, not just kind of zero shot trying to ask the model to pick which one is better.swyx [00:43:26]: Got it. Why is this an ELO? And not a percentage, like GDP-VAL?George [00:43:31]: So the outputs look like documents, and there's video outputs or audio outputs from some of the tasks. It has to make a video? Yeah, for some of the tasks. Some of the tasks.swyx [00:43:43]: What task is that?George [00:43:45]: I mean, it's in the data set. Like be a YouTuber? It's a marketing video.Micah [00:43:49]: Oh, wow. What? Like model has to go find clips on the internet and try to put it together. The models are not that good at doing that one, for now, to be clear. It's pretty hard to do that with a code editor. I mean, the computer stuff doesn't work quite well enough and so on and so on, but yeah.George [00:44:02]: And so there's no kind of ground truth, necessarily, to compare against, to work out percentage correct. It's hard to come up with correct or incorrect there. And so it's on a relative basis. And so we use an ELO approach to compare outputs from each of the models between the task.swyx [00:44:23]: You know what you should do? You should pay a contractor, a human, to do the same task. And then give it an ELO and then so you have, you have human there. It's just, I think what's helpful about GDPVal, the OpenAI one, is that 50% is meant to be normal human and maybe Domain Expert is higher than that, but 50% was the bar for like, well, if you've crossed 50, you are superhuman. Yeah.Micah [00:44:47]: So we like, haven't grounded this score in that exactly. I agree that it can be helpful, but we wanted to generalize this to a very large number. It's one of the reasons that presenting it as ELO is quite helpful and allows us to add models and it'll stay relevant for quite a long time. I also think it, it can be tricky looking at these exact tasks compared to the human performance, because the way that you would go about it as a human is quite different to how the models would go about it. Yeah.swyx [00:45:15]: I also liked that you included Lama 4 Maverick in there. Is that like just one last, like...Micah [00:45:20]: Well, no, no, no, no, no, no, it is the, it is the best model released by Meta. And... So it makes it into the homepage default set, still for now.George [00:45:31]: Other inclusion that's quite interesting is we also ran it across the latest versions of the web chatbots. And so we have...swyx [00:45:39]: Oh, that's right.George [00:45:40]: Oh, sorry.swyx [00:45:41]: I, yeah, I completely missed that. Okay.George [00:45:43]: No, not at all. So that, which has a checkered pattern. So that is their harness, not yours, is what you're saying. Exactly. And what's really interesting is that if you compare, for instance, Claude 4.5 Opus using the Claude web chatbot, it performs worse than the model in our agentic harness. And so in every case, the model performs better in our agentic harness than its web chatbot counterpart, the harness that they created.swyx [00:46:13]: Oh, my backwards explanation for that would be that, well, it's meant for consumer use cases and here you're pushing it for something.Micah [00:46:19]: The constraints are different and the amount of freedom that you can give the model is different. Also, you like have a cost goal. We let the models work as long as they want, basically. Yeah. Do you copy paste manually into the chatbot? Yeah. Yeah. That's, that was how we got the chatbot reference. We're not going to be keeping those updated at like quite the same scale as hundreds of models.swyx [00:46:38]: Well, so I don't know, talk to a browser base. They'll, they'll automate it for you. You know, like I have thought about like, well, we should turn these chatbot versions into an API because they are legitimately different agents in themselves. Yes. Right. Yeah.Micah [00:46:53]: And that's grown a huge amount of the last year, right? Like the tools. The tools that are available have actually diverged in my opinion, a fair bit across the major chatbot apps and the amount of data sources that you can connect them to have gone up a lot, meaning that your experience and the way you're using the model is more different than ever.swyx [00:47:10]: What tools and what data connections come to mind when you say what's interesting, what's notable work that people have done?Micah [00:47:15]: Oh, okay. So my favorite example on this is that until very recently, I would argue that it was basically impossible to get an LLM to draft an email for me in any useful way. Because most times that you're sending an email, you're not just writing something for the sake of writing it. Chances are context required is a whole bunch of historical emails. Maybe it's notes that you've made, maybe it's meeting notes, maybe it's, um, pulling something from your, um, any of like wherever you at work store stuff. So for me, like Google drive, one drive, um, in our super base databases, if we need to do some analysis or some data or something, preferably model can be plugged into all of those things and can go do some useful work based on it. The things that like I find most impressive currently that I am somewhat surprised work really well in late 2025, uh, that I can have models use super base MCP to query read only, of course, run a whole bunch of SQL queries to do pretty significant data analysis. And. And make charts and stuff and can read my Gmail and my notion. And okay. You actually use that. That's good. That's, that's, that's good. Is that a cloud thing? To various degrees of order, but chat GPD and Claude right now, I would say that this stuff like barely works in fairness right now. Like.George [00:48:33]: Because people are actually going to try this after they hear it. If you get an email from Micah, odds are it wasn't written by a chatbot.Micah [00:48:38]: So, yeah, I think it is true that I have never actually sent anyone an email drafted by a chatbot. Yet.swyx [00:48:46]: Um, and so you can, you can feel it right. And yeah, this time, this time next year, we'll come back and see where it's going. Totally. Um, super base shout out another famous Kiwi. Uh, I don't know if you've, you've any conversations with him about anything in particular on AI building and AI infra.George [00:49:03]: We have had, uh, Twitter DMS, um, with, with him because we're quite big, uh, super base users and power users. And we probably do some things more manually than we should in. In, in super base support line because you're, you're a little bit being super friendly. One extra, um, point regarding, um, GDP Val AA is that on the basis of the overperformance of the models compared to the chatbots turns out, we realized that, oh, like our reference harness that we built actually white works quite well on like gen generalist agentic tasks. This proves it in a sense. And so the agent harness is very. Minimalist. I think it follows some of the ideas that are in Claude code and we, all that we give it is context management capabilities, a web search, web browsing, uh, tool, uh, code execution, uh, environment. Anything else?Micah [00:50:02]: I mean, we can equip it with more tools, but like by default, yeah, that's it. We, we, we give it for GDP, a tool to, uh, view an image specifically, um, because the models, you know, can just use a terminal to pull stuff in text form into context. But to pull visual stuff into context, we had to give them a custom tool, but yeah, exactly. Um, you, you can explain an expert. No.George [00:50:21]: So it's, it, we turned out that we created a good generalist agentic harness. And so we, um, released that on, on GitHub yesterday. It's called stirrup. So if people want to check it out and, and it's a great, um, you know, base for, you know, generalist, uh, building a generalist agent for more specific tasks.Micah [00:50:39]: I'd say the best way to use it is get clone and then have your favorite coding. Agent make changes to it, to do whatever you want, because it's not that many lines of code and the coding agents can work with it. Super well.swyx [00:50:51]: Well, that's nice for the community to explore and share and hack on it. I think maybe in, in, in other similar environments, the terminal bench guys have done, uh, sort of the Harbor. Uh, and so it's, it's a, it's a bundle of, well, we need our minimal harness, which for them is terminus and we also need the RL environments or Docker deployment thing to, to run independently. So I don't know if you've looked at it. I don't know if you've looked at the harbor at all, is that, is that like a, a standard that people want to adopt?George [00:51:19]: Yeah, we've looked at it from a evals perspective and we love terminal bench and, and host benchmarks of, of, of terminal mention on artificial analysis. Um, we've looked at it from a, from a coding agent perspective, but could see it being a great, um, basis for any kind of agents. I think where we're getting to is that these models have gotten smart enough. They've gotten better, better tools that they can perform better when just given a minimalist. Set of tools and, and let them run, let the model control the, the agentic workflow rather than using another framework that's a bit more built out that tries to dictate the, dictate the flow. Awesome.swyx [00:51:56]: Let's cover the openness index and then let's go into the report stuff. Uh, so that's the, that's the last of the proprietary art numbers, I guess. I don't know how you sort of classify all these. Yeah.Micah [00:52:07]: Or call it, call it, let's call it the last of like the, the three new things that we're talking about from like the last few weeks. Um, cause I mean, there's a, we do a mix of stuff that. Where we're using open source, where we open source and what we do and, um, proprietary stuff that we don't always open source, like long context reasoning data set last year, we did open source. Um, and then all of the work on performance benchmarks across the site, some of them, we looking to open source, but some of them, like we're constantly iterating on and so on and so on and so on. So there's a huge mix, I would say, just of like stuff that is open source and not across the side. So that's a LCR for people. Yeah, yeah, yeah, yeah.swyx [00:52:41]: Uh, but let's, let's, let's talk about open.Micah [00:52:42]: Let's talk about openness index. This. Here is call it like a new way to think about how open models are. We, for a long time, have tracked where the models are open weights and what the licenses on them are. And that's like pretty useful. That tells you what you're allowed to do with the weights of a model, but there is this whole other dimension to how open models are. That is pretty important that we haven't tracked until now. And that's how much is disclosed about how it was made. So transparency about data, pre-training data and post-training data. And whether you're allowed to use that data and transparency about methodology and training code. So basically, those are the components. We bring them together to score an openness index for models so that you can in one place get this full picture of how open models are.swyx [00:53:32]: I feel like I've seen a couple other people try to do this, but they're not maintained. I do think this does matter. I don't know what the numbers mean apart from is there a max number? Is this out of 20?George [00:53:44]: It's out of 18 currently, and so we've got an openness index page, but essentially these are points, you get points for being more open across these different categories and the maximum you can achieve is 18. So AI2 with their extremely open OMO3 32B think model is the leader in a sense.swyx [00:54:04]: It's hooking face.George [00:54:05]: Oh, with their smaller model. It's coming soon. I think we need to run, we need to get the intelligence benchmarks right to get it on the site.swyx [00:54:12]: You can't have it open in the next. We can not include hooking face. We love hooking face. We'll have that, we'll have that up very soon. I mean, you know, the refined web and all that stuff. It's, it's amazing. Or is it called fine web? Fine web. Fine web.Micah [00:54:23]: Yeah, yeah, no, totally. Yep. One of the reasons this is cool, right, is that if you're trying to understand the holistic picture of the models and what you can do with all the stuff the company's contributing, this gives you that picture. And so we are going to keep it up to date alongside all the models that we do intelligence index on, on the site. And it's just an extra view to understand.swyx [00:54:43]: Can you scroll down to this? The, the, the, the trade-offs chart. Yeah, yeah. That one. Yeah. This, this really matters, right? Obviously, because you can b

We're back from the holiday break! (Sort of.) This interview with the inimitable Mike Pesca was recorded on Boxing Day and released right away to paying subscribers. Now it's available to everyone. Host of The Gist and author of the newsletters Pesca Profundities and The Gist List, Mike has turned the humble "bonus segment" into a multi-level rmarketing scheme multi-tiered pricing philosophy. How does he do it? We'll find out! We also talk about the hardest part of the creator economy (discovery), the incentives that reward martyrdom and outrage, and, most of all, Mike's December 26 Substack post No One's Nice To Bari Weiss. The CBS News editor-in-chief has been all over the headlines this past week after spiking delaying a 60 Minutes segment on CECOT, the notorious El Salvador terrorist prison, that was on the cusp of airing. Is it because the segment needed to "move beyond the forty-yard lines?" Or is something else going on? Also: a discussion on a mega-viral Compact article about systemic discrimination against white millennial men, a cry against Hamilton erasure, and why my lack of grip strength is more than made up for by my alarmingly hyperextensive fingers.

As the tenth anniversary of David Bowie's death approaches, Alexander Larman - author of Lazarus: The Second Coming of David Bowie – and Jonathan Stiasny – director of the documentary Bowie: The Final Act - join Tom to discuss David Bowie's legacy and his less successful, low-profile period.The National Year of Reading 2026 is a government campaign to address declining literacy, and we're running a series of items on the state of modern literacy. Today, we're discussing reading and the brain, with neuroscietist, Dr Maryanne Wolf and journalist Jo Glanville.A giant of Iranian cinema, director Bahram Beyzai, died on Boxing Day aged 87. We take a look back at his career and impact with Dr Saeed Talajooy, a scholar of Persian Literature and Culture, who's also a fan of Beyzai's work.Goblin Band, a London-based folk group, are live in studio to sing a wassail celebrating Twelfth Night. They'll chat to Tom about the draw of folk music in modern times and exactly what a wassail is.Presenter: Tom Sutcliffe Producer: Harry Graham

Boxing Day pie uses leftover turkey, stuffing and cranberry sauce together to make a delicious pie for post holiday festivities. Pastry requires practice for most people, it is not east to make, nor is it easy to make look good. But worth the process of care and work to produce the savory result, just like our lives.

Top political comedian Matt Forde reconvenes his Focus Group for a Boxing Day special with a Dickensian twist.Recorded in front of a live audience, Matt is joined by journalists, comedians and politicians – including former Cabinet Minister Michael Gove – to review the political state we're in through the lens of Charles Dickens' A Christmas Carol. Expect sharp analysis, unexpected confessions, and the year's biggest stories getting visited by the Ghosts of Politics Past, Present and Yet to Come.Appearing as a festive treat in BBC Radio 4's Friday Night Comedy feed, it's a topical comedy that's both genuinely funny and surprisingly insightful – perfect for digesting with the leftover turkey.Written and performed by Matt Forde Additional writing from Karl Minns, Laura Claxton and Richard Garvin Producer: Richard Garvin Executive Producers Jon Thoday and Richard Allen Turner Co-Producers: Daisy Knight and Jules Lom Broadcast Assistant: Sahar Rajabali Sound Design and Editing: David Thomas An Avalon production for BBC Radio 4

What has the biggest impact on your health and happiness today? Perhaps you're thinking it's work, money, what you eat, how you sleep… Maybe it's your friends and family and how you interact with them… These are all valid answers. But let me put it to you that I think there's one factor that is linked to, but overrides, all of these things: stress. For this bonus New Year's Day episode, I wanted to speak to you directly about stress, so you can take action to stop it controlling your life in 2026. A bit like my Boxing Day podcast a few days ago, his episode is designed to gently inspire you at the start of the year, to help you reflect on your life, and to encourage you to create positive change in the months ahead. So I'm sharing with you the five simple habits that I know will help you reduce the impact of stress and transform your wellbeing this year. In this episode I reveal why it's so important to: Have a morning routine – to dramatically reduce early micro stress doses and positively shape the rest of your day. Learn a breathing technique you can take anywhere – because the way you breathe is powerful information for your body. Stop taking things personally – because learning to create space between what happens and how you respond is a surefire stress reliever. Practice true prevention – and stop worrying about your future health, with my revolutionary new app, Do Health. Find out how you can be one of the first to try it! And prioritise your sleep – by optimising light exposure, being aware of caffeine and creating a calming evening routine. I genuinely hope this episode helps you see stress differently and reminds you that small, consistent changes can have a profound impact. A little stress is part of life – but chronic stress doesn't have to be. And if you want to find out more about optimising your health in 2026, my book Happy Mind Happy Life is available TODAY in a brand new format in the UK, in its original format in many other countries and as an audiobook which I narrate all over the world!   Support the podcast and enjoy Ad-Free episodes. Try FREE for 7 days on Apple Podcasts https://apple.co/feelbetterlivemore. For other podcast platforms go to https://fblm.supercast.com.   Thanks to our sponsors: https://drinkag1.com/livemore http://thewayapp.com/livemore   Show notes https://drchatterjee.com/607   DISCLAIMER: The content in the podcast and on this webpage is not intended to be a substitute for professional medical advice, diagnosis, or treatment. Always seek the advice of your doctor or qualified healthcare provider. Never disregard professional medical advice or delay in seeking it because of something you have heard on the podcast or on my website.

Sheffield Wednesday remain unbeaten after Christmas, and it's a run that's giving the squad and fans a real boost. We dive into the 2–2 Boxing Day clash with Hull City, a game full of twists that tested the team's resilience, and the 0–0 draw with Blackburn, which saw Cole McGhee make his Championship debut and impress on his first outing. Tune in as we explore how these performances are lifting confidence and building momentum at Hillsborough. Hosted on Acast. See acast.com/privacy for more information.

Festive Footy | Mecca of BanterThe festive period never disappoints—on or off the pitch.In this episode of Mecca of Banter, the boys embrace the holiday chaos and break down a packed run of festive fixtures across the Premier League. From Manchester United's gritty win and tactical tweaks under Ruben Amorim, to Chelsea's frustrating collapse against an in-form Aston Villa, to growing concerns around Brentford and Thomas Frank, nothing is spared.We dig into lineup decisions, second-half management, youth performances, and why some teams look energized while others feel completely lifeless. Aston Villa's title buzz gets put under the microscope, Chelsea's identity issues resurface, and United fans find themselves cautiously optimistic—again.The conversation also takes a global turn with AFCON kicking off, why it matters more than people realize, and how missing players could swing the Premier League table over the next few weeks. Equal parts tactical breakdown, supporter therapy session, and holiday banter—this one's a fun watch.Keywords: Premier League podcast, Manchester United, Chelsea, Aston Villa, festive fixtures, AFCON, football tactics, soccer fandom, Mecca of Banter 00:00 – Holiday chaos & festive vibes02:45 – Manchester United tactical shift & key performances05:37 – Chelsea vs Aston Villa: what went wrong08:33 – Tactical analysis & game management11:28 – Managerial decisions under pressure14:30 – What's coming next in the festive schedule25:16 – AFCON absences & squad impact28:26 – Player performances & expectations31:19 – Is Aston Villa a real title threat?33:58 – Brentford & Thomas Frank under scrutiny39:53 – Upcoming matches & AFCON storylinesPremier League, Premier League podcast, football podcast, soccer podcast, Mecca of Banter, festive fixtures, festive footy, Manchester United, Man United podcast, MUFC, Chelsea FC, Aston Villa, Brentford FC, Thomas Frank, Ruben Amorim, AFCON, AFCON 2025, African Cup of Nations, Premier League analysis, football tactics, soccer tactics, fan reactions football, soccer fandom, holiday football, Boxing Day football, Premier League discussion, football banter, soccer YouTube, American soccer podcast

Menners is joined by Victorian sportswriter Jono Baruch to dissect the fallout from a deeply flawed Boxing Day Test that ended in just two days. While England's win is acknowledged as legitimate, the focus quickly turns to the pitch, the loss of spectacle, and the wider consequences for Australian cricket. They examine why the MCG surface failed Test cricket, the financial and broadcast impact of short matches, and whether Australia's push for result wickets has gone too far. The discussion then shifts to the Australian team's looming transition, including hard questions around Marnus Labuschagne's form, Usman Khawaja's future, Cameron Green's role, and whether Travis Head has finally locked down the opening position. (01:05) England's Boxing Day win — legitimate result or hollow victory?(05:55) Bazball, bad pitches, and why this Test changed nothing(10:05) Why the MCG pitch became the real story(19:45) Has Australia gone too far with bowler-friendly wickets?(30:10) Australia's batting concerns: Marnus Labuschagne under pressure(38:40) Khawaja, Green, Head — and what the next Test team might look like Cricket Unfiltered Merchandise is Here! We've launched our official Cricket Unfiltered merch store thanks to a brilliant partnership with Exactamundo, a longtime supporter of the show.

Comedians Clare O'Kane, Alex Ptak, and Jeremy Kaplowitz explore the mysterious land of Quora.com to answer life's questions. This week's questions include: You write a practical plan to defeat a group of 30 thugs single-handedly. Is that possible? Who would win in a fight, Jack Skellington or The Grinch? My ex wife has been dating my uncle and it appears that they may end up getting married. I somehow feel that she is doing this to get back at me somehow for cheating on her. Am I just paranoid? Should I say anything to her about this feeling? --- Check out Josh's work @ https://joshboerman.com/ Get even more Quorators when you support the show @ patreon.com/quorators Send quoras and qommunicate on our discord discord.gg/7pPYuKuYCr Watch the show @ youtube.com/@quorators

SUN, SAND, AND SANTAS IN BOARD SHORTS: AN AUSTRALIAN CHRISTMAS Colleague Jeremy Zakis. Jeremy Zakis describes Christmas in Australia as the polar opposite of the Northern Hemisphere, featuring clear skies and temperatures in the mid-80s ideal for outdoor barbecues. While Queensland faced heavy rain and floods, most of the country enjoyed hot weather perfect for beach visits. Zakis details traditions like the Boxing Day cricket test and notes that while mall Santas wear wool, outdoor Santas often don board shorts and flip-flops. 1933 SYDNEY

To close out the year the 3WHH barflies recorded a special Boxing Day edition, in which, following the obligatory McDonald's news for John and a breaking story that indicates President Trump really does mean it about defending Western Christendom, we review our predictions for 2025 from a year ago (which, unlike the old McLaughlin Group […]

To close out the year the 3WHH barflies recorded a special Boxing Day edition, in which, following the obligatory McDonald's news for John and a breaking story that indicates President Trump really does mean it about defending Western Christendom, we review our predictions for 2025 from a year ago (which, unlike the old McLaughlin Group predictions, turned out to be fairly good in most cases); then discuss what each of think is the most significant story of 2025, and offer predictions for 2026. We couldn't make the Substack livestream work, but we're going to sort that out in the next week before our first show of the new season next weekend, which will be 2026!

This week we are bringing in the big guns

OA1219 - This year we are celebrating Boxing Day by not doing whatever people are supposed to do on Boxing Day and talking about weed instead. Did Donald Trump really just finish out 2025 by doing something good for US drug policy? We hotbox some Time Machine to revisit Matt's analysis from last May of Joe “Grandaddy Purple” Biden's announcement that he was initiating the long process to have the federal government to reclassify OG Kush from its current legal status as Green Crack down to the same category as metabolic steroids. We then return to the present to check in on the weirdly unreported story on how Biden's efforts went from Blue Dream to Trainwreck in the year after his big announcement before evaluating Trump's chances of turning cannabis policy Panama Red.  Finally, in a seasonal footnote Matt shares the story of how the city of Boston fired the first shots on the War on Christmas… in 1659. Biden DOJ's analysis of legal questions around plans to redesignate cannabis to Schedule III “Increasing Medical Marijuana and Cannabidiol Research,” The White House (12/18/25) “The Penalty For Keeping Christmas,” Archive.org (Boston, 1659)

Is happiness a skill you can develop? Or is it a place you find yourself, if you're lucky? Today's podcast is a bonus episode that I've recorded, from me to you, to demonstrate that yes, happiness is about more than just chance. These special Boxing Day podcasts are becoming a bit of a tradition now (look out for one I'll be releasing on New Year's Day too). And in this one, I share five powerful ideas with you – five happiness habits that can transform your life in meaningful ways. They're all explored in much greater detail in my book Happy Mind Happy Life: 10 Simple Ways to Feel Great Every Day, which is being re-published in the UK in an exciting new format on 1 January 2026. But you can leverage your happiness levels right away by listening today. Here's a quick overview of what you'll learn: 1. Happiness is a Skill - Discover the difference between ‘junk happiness' and ‘core happiness' to feel more content, in control, and aligned with your values. 2. Define Success for Yourself - Imagine yourself on your deathbed and identify three things you'll wish you had done. What can you do now to move toward that ending? 3. Eliminate Choice - We make thousands of decisions a day, and each one drains mental energy. By creating routines and reducing choice, you can reduce that stress. 4. Make Time Stand Still - Identify ‘flow state' activities that make you lose track of time, and schedule them as investments in your happiness. 5. Seek Out Friction - If someone upsets you, ask yourself why their words affected you so much. Rewriting their story with compassion will increase your own sense of control. I hope this episode helps you and your family cultivate lasting happiness in 2026 and beyond. I explore all these ideas and many more in my newly formatted book Happy Mind Happy Life - available here as a paperback or as an audiobook, which I am narrating. Support the podcast and enjoy Ad-Free episodes. Try FREE for 7 days on Apple Podcasts https://apple.co/feelbetterlivemore. For other podcast platforms go to https://fblm.supercast.com.   Thanks to our sponsor: https://drinkag1.com/livemore   Show notes https://drchatterjee.com/606   DISCLAIMER: The content in the podcast and on this webpage is not intended to be a substitute for professional medical advice, diagnosis, or treatment. Always seek the advice of your doctor or qualified healthcare provider. Never disregard professional medical advice or delay in seeking it because of something you have heard on the podcast or on my website.

Fear not, the Ramble is here to fill the Premier League-shaped hole in your Boxing Day!Across two parts, Marcus shares our very favourite moments of the year. From Ruben Amorim's vengeance against the humble television, to Ian Rush's vengeance against … well everyone, there's fun for all the family! Come join us.Find us on Bluesky, X, Instagram, TikTok and YouTube, and email us here: show@footballramble.com.Sign up to the Football Ramble Patreon for ad-free shows for just $5 per month: https://www.patreon.com/footballramble.***Please take the time to rate us on your podcast app. It means a great deal to the show and will make it easier for other potential listeners to find us. Thanks!*** Hosted on Acast. See acast.com/privacy for more information.

Happy Boxing Day, Heal Squad. It's a festive Lonely Guy Friday, coming to you from the quiet stretch after Christmas, when the wrapping paper's gone, the expectations ease up, and reality sneaks back in. Kev reflects on why Christmas feels like it flies by, why we build so much pressure around one perfect day, and why maybe the spirit of the holiday matters more than the sermon about what it shouldn't be. A look at generosity versus shame, giving versus guilt, and why kindness and being seen might be the point after all. A reminder that you don't have to fix everything, carry everyone, or solve decades of dysfunction during the holidays. Sometimes the most generous thing you can do is protect your energy, keep your heart open, and let people walk their own path. Happy Boxing Day, wherever you are and however you're spending it. Bye Betches. -- HEAL SQUAD SOCIALS IG: https://www.instagram.com/healsquad/ TikTok: https://www.tiktok.com/@healsquadxmaria HEAL SQUAD RESOURCES: Heal Squad Website:https://www.healsquad.com/ Heal Squad x Patreon: https://www.patreon.com/HealSquad/membership Maria Menounos Website: https://www.mariamenounos.com My Curated Macy's Page: Shop My Macy's Storefront EMR-Tek Red Light: https://emr-tek.com/discount/Maria30 for 30% off Airbnb: https://www.airbnb.com/maria  Thrive Causemetics: https://thrivecausemetics.com/healsquad Get 20% OFF with this link!  Briotech: https://shopbriotech.com/ Use Code: HEALSQUAD for 20% off  ABOUT MARIA MENOUNOS: Emmy Award-winning journalist, TV personality, actress, 2x NYT best-selling author, former pro-wrestler and brain tumor survivor, Maria Menounos' passion is to see others heal and to get better in all areas of life. ABOUT HEAL SQUAD x MARIA MENOUNOS: A daily digital talk-show that brings you the world's leading healers, experts, and celebrities to share groundbreaking secrets and tips to getting better in all areas of life. DISCLAIMER: This Podcast and all related content (published or distributed by or on behalf of Maria Menounos or http://Mariamenounos.com and http://healsquad.com) is for informational purposes only and may include information that is general in nature and that is not specific to you. Any information or opinions provided by guest experts or hosts featured within website or on Company's Podcast are their own; not those of Maria Menounos or the Company. Accordingly, Maria Menounos and the Company cannot be responsible for any results or consequences or actions you may take based on such information or opinions. This podcast is presented for exploratory purposes only. Published content is not intended to be used for preventing, diagnosing, or treating a specific illness. If you have, or suspect you may have, a health-care emergency, please contact a qualified health care professional for treatment.

Dean Karayanis — New York Sun columnist, host of the History Author Show, and former Rush Limbaugh staffer — brings the Yuletide cheer for Derek. A story in Politico alleging that the "How the far right stole Christmas" prompts a discussion of the birth of Jesus Christ being turned into a generic, secular holiday. Plus, what happened to the little girl who wrote letter that led to the most reprinted editorial in the English language, 1897's "Yes, Virginia, There is a Santa Claus," in the New York Sun. The stories of "It's a Wonderful Life," "A Charlie Brown Christmas," and of Luxembourg's "American St. Nick" from a tradition begun by GI's in the middle of World War 2. Dean also notes that Christmas marked the 101st birthday of Rod Serling, who's enduring gift is The Twilight Zone's "Night of the Meek," starring Art Carney as a Skid Row Santa Claus.

For more coverage on the issues that matter to you, download the WMAL app, visit WMAL.com or tune in live on WMAL-FM 105.9 from 9:00am-12:00pm Monday-Friday  To join the conversation, check us out on Twitter @WMAL and @ChrisPlanteShow Learn more about your ad choices. Visit podcastchoices.com/adchoices

Ben Maller (produced by Danny G.) has a great Friday for you! He talks: Boxing Day, Charity for the Cameras, Maller Mansion Christmas Party, & more! ...Follow, rate & review "The Fifth Hour!" https://podcasts.apple.com/us/grpodcast/the-fifth-hour-with-ben-maller/id1478163837 #BenMallerSee omnystudio.com/listener for privacy information.

Missin Curfew Episode 444 The Fellas have another set of Curfew Calls from the fans to answer for the Holidays! The Fellas preview the World Junior Ice Hockey Championships starting Boxing Day Why did the Fellas choose their uniform numbers? The Fellas talk Boxing Day and rules about regifting presents SAUCE HOCKEY MERCH | https://saucehockey.com/collections/missin-curfew YOUTUBE | www.youtube.com/@MissinCurfew SPOTIFY | https://open.spotify.com/show/4uNgHhgCtt97nMbbHm2Ken APPLE | https://podcasts.apple.com/us/podcast/missin-curfew INSTAGRAM | www.instagram.com/missincurfew TWITTER | www.twitter.com/MissinCurfew TIKTOK | www.tiktok.com/@missincurfewpod Learn more about your ad choices. Visit podcastchoices.com/adchoices

Best of - Americans see a government that can't solve their problems, why customer service is designed not to serve customers, and what is Boxing Day.

Judd and AJ gather for a Boxing Day discussion about Quinn Hughes now 6 games into his Minnesota Wild tenure. Is he fully integrated yet or will it take more time? What will things look like once he builds more chemistry with teammates? Is there a case to put Brock Faber on top power play unit with him? Plus more!See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Drift off with a calm bedtime reading about Boxing Day, designed for sleep and anyone facing insomnia after busy holidays. Relax with a calm bedtime reading that supports sleep, gently easing insomnia as the history and traditions unfold, all in one peaceful flow. In this episode, Benjamin explores the origins of Boxing Day, its connection to Saint Stephen's Day, and the way charitable customs evolved into modern traditions, shared in a soothing, unhurried cadence that helps your thoughts slow down. You can learn something new while you relax, with no whispering—just peaceful, fact-filled education meant to quiet the mind. This gentle approach can be especially comforting for insomnia, stress, and anxious thoughts that tend to linger at night. Press play, get comfortable, and let the calm rhythm guide you softly toward rest. Happy sleeping! Read with permission from Boxing Day and Saint Stephen's Day, Wikipedia (https://en.wikipedia.org/wiki/Boxing_Day, https://en.wikipedia.org/wiki/Saint_Stephen%27s_Day), licensed under CC BY-SA 4.0. Learn more about your ad choices. Visit megaphone.fm/adchoices

RHLSTP Book Club - Boxing Day Special - Right Bollock - I Right Bollock - Herring gets the interview everyone wants as he chats to debut author Right Bollock about his autobiography. Find out what it was like to be born a testicle, how RB felt when he discovered he had a brother, his perspective on some of the incidents that have made it into Herring's stand-up, how he escaped during the operation and what his aspirations for the future are. If you want to spend Boxing Day listening to a man talking to his own testicle, then this is the podcast for you.Buy the book/pamphlet available soon at https://gofasterstripe.com/cgi-bin/w.cgi?showfull=67271, or from Richard at gigsSUPPORT THE SHOW!See details of the RHLSTP LIVE DATES Watch our TWITCH CHANNELBecome a badger and see extra content at our WEBSITE Buy DVDs and books from GO FASTER STRIPE Hosted on Acast. See acast.com/privacy for more information.

Ken Matthews guests hosts on Boxing Day. Learn more about your ad choices. Visit megaphone.fm/adchoices

A year-end Boxing Day Q&A covering realistic downside expectations for global portfolios, the marginal value of adding international small-cap value, details for RetireMeet 2026, and a deeply skeptical look at Medicaid-compliant annuities. The common thread: diversification helps, simplicity usually wins, and when complexity shows up early, commissions are often lurking nearby. 0:04 Boxing Day confusion, goodwill, and a short-format holiday Q&A 1:07 Why this is a shorter, four-question episode to wrap the year 2:17 How much can a globally diversified stock portfolio really fall 3:06 Limits of global market data and why 2008 still sets expectations 4:11 Roughly 40% decline for global stocks in 2008 and how bonds softened the blow 4:54 Why worst-case scenarios are about expectations, not predictions 6:07 Listener portfolio with VXUS, AVUV, and SWTSX and whether to add AVDV 6:35 Balancing small-cap value exposure versus keeping things simple 7:56 Why a few basis points rarely justify added complexity 8:38 RetireMeet 2026 question and a well-earned jab at Tom's joke delivery 10:02 RetireMeet 2026 details and early seat reservations 10:29 Event date and location: March 7, Bellevue at Meydenbauer 11:44 Medicaid-compliant annuities explained through a real family scenario 13:57 Why MCAs are usually last-resort tools, not early planning solutions 15:49 Concerns about elder law attorneys, incentives, and hidden commissions 16:35 What MCAs really do: income conversion, not asset protection 17:28 Why skepticism is healthy and shopping non-commission options matters 18:43 Closing thoughts on trust, incentives, and surviving another financial year Learn more about your ad choices. Visit megaphone.fm/adchoices

The adrenaline has crashed. The wrapping paper is cleared away. But are your shoulders still up by your ears?Welcome to a special Boxing Day edition of the Calming Anxiety Podcast. Today, we aren't just trying to "think positive thoughts."We are going deeper. We are using Somatic Release Therapy to manually turn off the body's stress response after the intensity of the holidays.In just 10 minutes, we will guide you through a physical "un-storing" of the last 48 hours. This session is designed to metabolize the residual adrenaline, flush out cortisol, and signal safety to your brain through your body.In this episode, you will learn:The Body Scan: How to locate your "armor"—the physical tension hiding in your jaw, tongue, and shoulders.Somatic Shaking: Why "flicking" your hands and shaking your limbs is the fastest way to dislodge static anxiety and metabolize stress hormones.The Heel Drop Technique: Using impact and vibration to send a shockwave of relaxation up the spine.Progressive Muscle Relaxation: teaching your muscles the distinct difference between "On" (tension) and "Off" (relaxation) through deep squeezing and releasing.Vagus Nerve Activation: Using specific breath counts (Inhale 4, Exhale 8) to trigger the parasympathetic nervous system and surrender to gravity.Perfect for:Relieving "Holiday Burnout" and social exhaustion.Anyone physically feeling the effects of the "Fight or Flight" response.Resetting your sleep cycle after the festive disruption.You do not need a yoga mat or activewear. You can do this in your pajamas, on the floor, or in a chair. It's time to stop serving, stop organizing, and simply be a heavy object on the earth.

Happiness guru and Harvard professor Arthur Brooks discusses generosity, family, and gratitude this Boxing Day, and 5 New Digital founder Michael Zakkour shares insights about the holiday shopping season, including the retail winners across luxury and budget sectors. Plus, the news headlines that got us Squawking: a winter storm warning in the Northeast, U.S. military strikes in Nigeria, and one very lucky Poweball ticket holder.  Michael Zakkour - 10:25Arthur Brooks - 20:45 In this episode:Arthur Brooks, @arthurbrooksLeslie Picker, @LesliePickerContessa Brewer, @contessabrewerSteve Liesman, @steveliesmanKatie Kramer, @Kramer_Katie Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

The Thinklings Podcast — Episode 276 Booxing Day Welcome to Episode 276 of The Thinklings Podcast! Why settle for boring Boxing Day when you could celebrate Booxing Day instead? In this special post-Christmas episode, the Thinklings exchange books with one another to read on December 26...turning the day after Christmas into a celebration of reading, friendship, and absolutely no boxes. Add an “O” to your boxing and join the Thinklings as they share book recommendations, surprise exchanges, and plenty of literary cheer. Thanks for tuning in to this festive conversation!

"Genius is one percent inspiration and 99 percent perspiration." Well, tonight's show contains a lot of genius -- but we've cleaned up all the sweat and just left you with the inspiration. If you're looking for fashion inspiration, why not look to the trend-setting chimpanzees -- who are accessorizing with blades of grass placed delicately in their ears, and, even more delicately, in their butts. Anna Brynald of Denmark won the whole shebang this year at the world's most important seagull-impersonating contest -- by keeping her feet on the ground and screeching for the stars. The Vienna Vegetable Orchestra produces music from produce -- although, when you first hear it, you might feel like you've been sold a bill of gourds. At 14 years old, Pearl is now the world's oldest living chicken -- and her owner credits her longevity to her joie de vivre, and her close friendship with a mop. When Mitchell O'Brien found himself being slowly swallowed by a patch of quicksand, he and a longtime friend admitted they both admired one another romantically -- emphasis on "mire".

It's a Boxing Day bonus, as we bring you not one but two episodes of Soundtracking in the spirit of festive cheer. First up is Josh Safdie, co-writer, producer and director of Marty Supreme, the film which has been wowing critics across the globe with five star review after five star review. Then, after you've polished off your Christmas Day leftovers, we'll hear from Joachim Trier & Stellan Skarsgård, who joined Edith live on stage as part of our Everyman Soundtracking Film Club to discuss Sentimental Value. But we begin with Josh and Marty Supreme. Starring Timothée Chalamet and loosely based on a true story, the narrative follows an up-and-coming table tennis star who gets embroiled in all manner of scrapes to achieve his dream. It's beautifully scored by Daniel Lopatin

As promised, we have a second episode of Soundtracking for you this Boxing Day, as Joachim Trier and Stellan Skarsgard join us to discuss Sentimental Value, which is on general release in the UK as of now. Addressing themes of intergenerational trauma, nepotism and suicide, Sentimental Value follows a fractured relationship between an acclaimed director and his two estranged daughters, which becomes even more complicated when he decides to make a personal film about their family history. This was our last Everyman Soundtracking Film club of the year, where we screen a movie and Edith speaks to person or persons connected to it afterwards. You can find every single edition of our partnership at edithbowman.com

A Boxing Day reflection on a standout year of Full Disclosure. James O'Brien revisits key guests and conversations from 2025, offering perspective on the ideas, stories and people that shaped the podcast over the past twelve months. With sincere thanks to everyone who has listened, shared and stayed curious, your company makes these conversations possible. We'll be back in the new year with even bigger guests and more in depth discussions.

It's Boxing Day and the Fat One wraps up the week with a recap of his Chrima Eve and Day which included eggnog, a HUGE feast, some very meaningful giftettes, a gas report and a listener's BFO Chrima story. Happy National Candy Cane Day.

Theres a festive feel down the club, talking babysitter crushes, boxing day traditions, Westlife after parties, and classic TV. Learn more about your ad choices. Visit podcastchoices.com/adchoices

Judd and AJ gather for a Boxing Day discussion about Quinn Hughes now 6 games into his Minnesota Wild tenure. Is he fully integrated yet or will it take more time? What will things look like once he builds more chemistry with teammates? Is there a case to put Brock Faber on top power play unit with him? Plus more!See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

In the 5 AM hour, Larry O’Connor and Patrice Onwuka discussed: HOW WAS EVERYBODY’S CHRISTMAS? NIGERIAN STRIKES POLITICO DISCOVERS CHRISTMAS IS CHRISTIAN WHAT THE HECK IS BOXING DAY? Where to find more about WMAL's morning show: Follow Podcasts on Apple Podcasts, Audible and Spotify Follow WMAL's "O'Connor and Company" on X: @WMALDC, @LarryOConnor, @JGunlock, @PatricePinkfile, and @HeatherHunterDC Facebook: WMALDC and Larry O'Connor Instagram: WMALDC Website: WMAL.com/OConnor-Company Episode: Friday, December 26, 2025 / 5 AM HourSee omnystudio.com/listener for privacy information.

If you're British, the chances are that last Christmas you watched the Gavin and Stacey Christmas Special. And Gyles's guest this Boxing Day is one of its stars: Matthew Horne, also known as the kind-hearted, loyal everyman, Gavin. In this episode, Matthew tells Gyles about his country childhood, about his loving and hard-working parents and their devotion to caring for him and his older brother. He talks about his schooldays, and the intense relationship he had with his girlfriend there. He talks about getting into stand-up at Manchester University and the phenomenon of Gavin and Stacey. We wish all our Rosebud listeners a very merry Christmas! Enjoy this. Hosted on Acast. See acast.com/privacy for more information.

On this Boxing Day episode, we discuss the Ethan Nwaneri dilemma - could we see him depart on loan in this upcoming transfer window? Plus, we'll begin our look ahead to Brighton (h) in the Premier League. That and more! Sign up to support us on Patreon: https://patreon.com/thechroniclesofagooner?utm_medium=unknown&utm_source=join_link&utm_campaign=creatorshare_creator&utm_content=copyLink

Katie Smith is joined by former West Ham and Aston Villa midfielder Nigel Reo-Coker and Brighton midfielder Fran Kirby to look ahead to the busy festive football period.They discuss what it's like to be a footballer at Christmas time and whether it's possible to enjoy the holidays while also getting ready for matches.Boxing Day's only Premier League match this year sees Manchester United host Newcastle, the panel discuss how much Ruben Amorim's side will miss Bruno Fernandes during his spell out injured.Coventry City look to take another step towards promotion to the top flight when they host Swansea on Boxing Day and Sky Blues fan Katie Stafford discusses what life is like at the moment.The panel also chat about West Ham's struggles and the WSL headlines going into the winter break.1:00 – Nigel and Fran's Christmas traditions 2:30 – Player management at Christmas 4:10 – Nigel on players being weighed after Christmas Day 7:30 – Festive training plans 11:00 – How much will Man Utd miss Bruno Fernandes? 17:30 – Opportunity for Kobbie Mainoo 19:30 – Newcastle focus 24:00 – Coventry City fan Katie Stafford 30:30 – Fran Kirby on WSL 35:00 – Nigel on West Ham 37:40 – Nigel and Fran's Christmas wishes

Join the Oxventurers as they journey to the small seaside town of Milton-on-Sea as strange and odd things pop up. When one of the town's local children goes missing on Boxing Day, his friends leap into action to solve this Twixtmas mystery. Get yourself a set of our new Oh No the Consequences Dice & OX Mystery Box! ⁠https://store.outsidexbox.com/⁠⁠ Get tickets to Oxventure's Tales From the Guild 2026 live tour at ⁠⁠⁠https://bit.ly/OXGuild⁠⁠⁠ 01:09 Actual play begins⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ ------------------ Join the OX Supporters Club and official Discord server: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠patreon.com/oxclub⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Check out the official store for sweet merch: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠store.outsidexbox.com⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ To watch all the original Oxventure videos, visit us on YouTube at ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠youtube.com/oxventure⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Learn more about your ad choices. Visit megaphone.fm/adchoices

Please follow us on: ⁠⁠⁠⁠⁠⁠⁠⁠Instagram⁠⁠⁠⁠ ⁠⁠⁠⁠ or ⁠⁠⁠⁠⁠⁠⁠⁠Facebook ⁠⁠⁠⁠! In this episode, Kimberly and Tommaso wish everyone a Buon Natale and a Happy New Year. They share their past Christmas experiences in Italy, highlighting the unique ways Italians celebrate the holiday season. The episode reflects on how these traditions bring people together and how a few of their friends are currently experiencing Italy for Christmas. Key Points: Tomaso's Holiday Message and Shout-Out: Tomaso extends sympathy to Australian listeners for a recent tragedy. Tomaso also gives a shout-out to participants of the Sydney to Hobart sailing race on Boxing Day. Christmas Eve Traditions: Kimberly and Tommaso share their plans their Christmas Eve dinner with handmade fusilli, bresaola and fresh mozzarella. They pair their meal with a special pesto from Geneva and a bottle of wine by a roaring fire. Listener Reviews and Italian Phrases: Tomaso thanks two listeners, Traveling Zia and Miller Sherry, for their reviews on Apple Podcasts. Kimberly shares various ways to say “that's very nice” in Italian. Kimberly's First Christmas in Italy: Kimberly recounts her first Christmas in Italy driving from Milano to Sicilia in a 25-year-old Fiat Cinquecento. She describes how Italians decorate their cities with lights strung across buildings, fostering a sense of connection. She remembers seeing a huge Christmas tree made of hundreds of red poinsettias in Taormina. An Expat Christmas Dinner in Milano: Kimberly organized a Christmas dinner for expat friends and models stuck in Milano for the holidays. Each person made a dish from their home country, creating a diverse and humorous meal. A friendly Italian neighbor invited everyone to his Nonna's apartment for traditional panettone and pandoro. Christmas in Italy in 2024: Kimberly and Tommaso describe their trip through Italy in December 2024, visiting Rome, Montepulciano, Cortona, Arezzo, Modena, Bergamo, Castelrotto, and Treviso. They experienced outdoor festivals, concerts, flag throwers, and Christmas markets, emphasizing the community spirit. Tomaso notes the non-commercial aspect of Italian Christmas celebrations, focusing on regional specialties. Friends' Christmas Trip to Italy: Kimberly's friends from Boston are currently traveling in Venice and Rome for Christmas. They saw hundreds of gondoliers dressed as Santa Claus (Babbo Natale) on the Grand Canal. Murano chandeliers light up Piazza San Marco, a skating rink in Campo San Polo, and artisan craft demonstrations on Murano and Burano. Their friends will also experience Rome's sights, including the Colosseum, Roman Forum, and the new Metro station that has artifacts like a museum. A Look Ahead: Kimberly and Tommaso thank listeners for their patience with bi-weekly episodes. They promise to return to weekly episodes when they move to Italy, sharing their experiences of living there. They end the episode wishing everyone a New Year filled with love, peace, pasta, tiramisu, and Brunello!