Podcasts about Clipping

Learn how to grow on YoUTube in 2026!

Links & Socials here:https://linktr.ee/haleygutz

Episode 304   This week, your hosts Jay Gilbert & Mike Etchart break down these important music industry stories:   •  TikTok's AI 'Text to Song' Trend May Be a Sign of Music to Come  •  The Midyear Box Score Report Shows Growth — But It Has Finally Slowed Down? •  Clipping campaigns: marketing's next move in a fragmented attention economy •  A Full List of Music-Related Legislation Before Congress Right Now     Plus an audio drop from Duetti's CEO Lior Tibon   Subscribe to the newsletter! : YourMorning.Coffee

I've updated my recommendation for the sand quantity to apply for every unit of clipping volume harvested, if your goal is to keep surface organic material constant. Bjarni and I discussed topdressing by this method and the new equation that finds this sand amount.We discussed this post: https://www.asianturfgrass.com/post/sand-topdressing-ratios-clipping-volume/The PACE Turf table of sand rates based on surface organic material is at https://www.paceturf.org/public/sand-and-clipping-volumeBjarni and I discussed the spring green-up and growth from adding sand: https://www.asianturfgrass.com/post/turfgrass-mystery-the-case-of-the-greener-grass/Read more about all kinds of turfgrass topics at https://www.asianturfgrass.com/Find a suite of decision-making tools at https://www.paceturf.org/Get free ATC newsletters at https://www.asianturfgrass.com/newsletter/ Find out more about soil tests with ATC at https://www.asianturfgrass.com/project/soil-tests/

Send James and Sam a message or voicemailWe pick apart Spotify's investor-day announcements and ask what its AI-first roadmap means for podcast creators, monetisation, and trust. We also talk to the co-founders of BIPOC Podcast Creators about why the community is closing and what the industry loses when creator support dries up. • Spotify's “time well spent” metric and what it tries to reframe • The “500 million video podcast” claim and why measurement matters • Real-time podcast Q&A on Spotify and the risk of AI hallucinations • Dynamic creator sponsorships and updating back catalogue ads • Spotify memberships as a Patreon and Supporting Cast rival, with big unanswered details • Verified by Spotify badges and why creators can't control verification • Clipping tools and the tradeoff between shareability and platform lock-in • Why BIPOC Podcast Creators closes, after a year of exploring options • How funding, layoffs, and politics change corporate support • The case for protecting indie creators and the industry's long-term health • Apple Podcasts plus Audible subscription access and why verification matters • YouTube's podcasts hub, top fans, and clearer AI content labels • Private feed security problems and why standards need to move faster • Direct Flow Auto Discover RSS and QR code discovery for podcasts Subscribe to our newsletter at podnews.net.We're sponsored by Buzzsprout; their CoHost summary tool made these show notes.Support the showConnect With Us: Email: weekly@podnews.netFediverse: @james@bne.social and @samsethi@podcastindex.socialSupport us: www.buzzsprout.com/1538779/supportGet Podnews: podnews.net

Anas Instagram : https://www.instagram.com/zssnasChapters:00:00:00 - المقدمة والترحيب (الحلقة 227) 00:01:06 - إحساس "التحسينة" والثقة في النفس 00:03:25 - علاش أثمنة الحوالة طالعة هاد العام؟ 00:04:18 - الفرق بين الحولي ديال زمان ودابا 00:07:25 - ضرورة مقاطعة الغلاء والشراء بالعياقة 00:08:44 - رأيي في المحتوى ديال "الراس" وشوف تيفي 00:11:08 - كيفاش تخلص كـ Clipper على حساب الريزيلطا (Views) 00:12:35 - واش أرسنال ولا مانشستر سيتي؟ 00:14:12 - نصائح للدراري اللي باغيين يخدموا في الكليبين (Clipping) 00:18:19 - قصة وصولنا لـ 70K في إنستغرام 00:23:55 - أجواء صلاة العيد واللمة العائلية في المغرب 00:25:53 - أصعب شعور نهار العيد (المكالمات العائلية) 00:27:03 - علاش أكادير أحسن بلاصة كيدوز فيها العيد الكبير؟ 00:28:30 - ملي لالغوريتم كيترجم الكومونطيرات غلط 00:31:16 - طوندونس "زعزع" و"الطاكوس" في المغرب 00:33:50 - ذكريات "التفرتيت" و "باتيسري" زمان 00:35:46 - قصص الماتشات ديال الزنقة في الصهد 00:37:29 - برونزاج "الكرطون" وذكريات الصغر 00:42:35 - طبيعة العلاقات والموتيفاسيون في الحياة 44:28 - مفاجأة رجوع "أول فان" للستريم 00:50:11 - الخاتمة وتوديع الدراري*******************************************************************Follow WLEP on IG: https://www.instagram.com/wladlhajexperienceListen on Spotify: https://spoti.fi/3w1beaGI stream on Kick: https://kick.com/wladlhajexperienceI stream on Twitch : https://www.twitch.tv/anasokaaJoin our community on Discord: https://discord.gg/XTVf8cCnSy#بودكاست #podcast #maroc #المغرب

Today on The Press Box, Bryan and David react to a wild Game 1 of the Western Conference finals between the Spurs and Thunder, and they talk about how to revamp postgame interviews. Then they talk about another Bari Weiss story at CBS (15:28), the decline in “dad books” (22:01), a breakfast taco controversy (36:16), and much more. Then Bryan is joined by New York Times critic Jason Zinoman to discuss the end of Stephen Colbert's late-night show (59:31). Plus, the Overworked Twitter Joke of the Week, and David Shoemaker Guesses the Strained-Pun Headline! Hosts: Bryan Curtis and David ShoemakerGuest: Jason ZinomanProducers: Isaiah Blakely, Jaime Yukich, and Jon Roemer Learn more about your ad choices. Visit podcastchoices.com/adchoices

https://www.patreon.com/posts/158674480?pr=true (*Go ad-free with early access and monthly bonus content on Patreon!)Today we're discussing an article by Lane Brown for New York Magazine called "The Feed Is Fake" which reveals how the music and film industries use paid campaigns to influence YOUR opinion! We'll talk about 90% of the internet being fake, "Trend Simulation", Clipping practices, Spotify bot streams and the techniques used to influence reality. We'll talk about specific examples including: Taylor Swift, Justin Baldoni, Sydney Sweeney, Andrew Tate, Drake, Nick Fuentes, Bad Bunny, Justin Beiber's Coachella sets, Clavicular, Fleetwood Mac, Teddy Swims, Michael Jackson, Met Gala, The Geese, Eric Adams and the Russian Doppleganger program!   You can now sign up for our commercial-free version of the show with a Patreon exclusive bonus show called “Morning Coffee w/ the Weishaupts” at Patreon.com/BreakingSocialNorms  OR subscribe on the Apple Podcasts app to get all the same bonus “Morning Coffee” episodes AD-FREE with early access! (*Patreon is also NOW enabled to connect with Spotify! https://rb.gy/r34zj)Want more?…Index of all previous episodes on free feed: https://breakingsocialnorms.com/2021/03/22/index-of-archived-episodes/Leave a review or rating wherever you listen and we'll see what you've got to say!Follow us on the socials:instagram.com/theweishaupts2/Check out Isaac's conspiracy podcasts, merch, etc:AllMyLinks.com/IsaacWOccult Symbolism and Pop Culture (on all podcast platforms or IlluminatiWatcher.com)Isaac Weishaupt's book are all on Amazon and Audible; *author narrated audiobooks*STATEMENT: This show is full of Isaac's and Josie's useless opinions and presented for entertainment purposes. Audio clips used in Fair Use and taken from YouTube videos.

Field clipping completed, the little Kioti and the new rotary cutter did swell with Blind Hog in the driver's seat.  The farmers usually get the fields clipped by this time- will keep the grass growing and not put all the energy into seed production.December-born wethers off to market this morning.  Next batch should go right before the 4th of July holiday.About time to get the fencing project started, working in little projects in between like putting in more cattle panel arches in the garden for BEANS...Geese are slow to hatch eggs this year- the cold mornings have not been helpful and Acorn fears for egg viability after exposure.

Apply to Work with Voics: https://www.voics.co/schedule-youtube Join Aura: https://www.aura-app.ai/ Guest: Eddie CumberbatchYoutube: ‪https://youtube.com/@eddiecumberbatchInstagram: https://www.instagram.com/eddiecumberbatch/Support the show

O programa Meio-Dia em Brasília desta terça-feira, 12, fala sobre os abusos do ministro Alexandre de Moraes, do Supremo Tribunal Federal (STF), e como o Congresso vai reagir à anulação da vigência do PL da Dosimetria.Além disso, o jornal também fala sobre o novo programa de combate ao crime organizado do governo Lula e a respeito da posse do ministro Kassio Nunes Marques como presidente do Tribunal Superior Eleitoral (TSE).Você já leu uma notícia hoje e sentiu que já viveu esse momento antes?   Essa sensação de déjà Vu não é coincidência. No Brasil, o que é manchete hoje costuma ser o eco de decisões e fatos que analisamos meses, ou até anos atrás.   Para celebrar os 8 anos da Crusoé, decidimos enfrentar esse ciclo. Pegamos o que nasceu no digital e, pela primeira vez, transformamos em um registro físico, tátil e permanente.   Chegou a edição especial Crusoé impressa.   É um item colecionável, atemporal e limitado. Uma revista feita para quem gosta de ler com calma, longe das notificações do celular. Um exemplar para guardar sobre o que realmente importa na história recente do brasil.   Esta edição é um presente exclusivo para novos assinantes do Combo de 2 anos O Antagonista e Crusoé.   Utilize o cupom 8ANOSCRUSOE e acesse o link:   https://bit.ly/crusoe-edicao-impressa  Meio-Dia em Brasília traz as principais notícias e análises da política nacional direto   de Brasília.     Com apresentação de José Inácio Pilar e Wilson Lima, o programa aborda os temas mais quentes do cenário político e econômico do Brasil.     Com um olhar atento sobre política, notícias e economia, mantém o público bem informado.    Transmissão ao vivo de segunda a sexta-feira às 12h no nosso canal do Youtube.  https://www.youtube.com/@OAntagonista   Siga O Antagonista no X:  https://x.com/o_antagonista   Acompanhe O Antagonista no canal do WhatsApp. Boletins diários, conteúdos exclusivos em vídeo e muito mais.  https://whatsapp.com/channel/0029Va2SurQHLHQbI5yJN344  Leia mais em www.oantagonista.com.br | www.crusoe.com.br#Congresso #Moraes #Politica #Brasilia #STF #Liberdade #Senado #Camara #Justiça #Direito #Brasil #Noticias #PodcastBrasil #LiberdadeDeExpressao #Opiniao #DebatePolitico #Atualidades #Democracia #EstadoDeDireito #Parlamento 

Today in the business of podcasting:New Sounds Profitable research finds 86% of podcast listeners consume clips on at least one platform, raising questions about paid clipping strategies and whether flooding social feeds with short-form content helps or hurts long-term audience growth.Signal Hill Insights' Paul Riismandel examines what it actually means to have a "hit" podcast, finding that even The Joe Rogan Experience — the #1 show on reach-based charts — reached only 20% of the U.S. podcast audience in a given month.AdExchanger Senior Editor Alyssa Boyle analyzes YouTube's NewFronts presentation, where creators blurred the traditional line between talent pitches and publisher sales decks, as advertisers increasingly demand outcome-based commitments over broad reach.Consultant Steve Raizes explores how the weekly podcast production cycle traps creators on a content hamster wheel with no time for strategic growth, using Audiochuck's operational infrastructure as a model for sustainable scale.Tribeca Festival 2026 announces its most ambitious podcast lineup to date for its June run in New York City, featuring live events with Radiolab, The New Yorker Radio Hour, and Lemme Say This, with guests including Peter Dinklage, Adam Scott, and Laurie Anderson.To find links to these, and every article covered in today's episode, click here. You can also subscribe to The Download's newsletter to receive the full issue straight to your email inbox every day.

Today in the business of podcasting:New Sounds Profitable research finds 86% of podcast listeners consume clips on at least one platform, raising questions about paid clipping strategies and whether flooding social feeds with short-form content helps or hurts long-term audience growth.Signal Hill Insights' Paul Riismandel examines what it actually means to have a "hit" podcast, finding that even The Joe Rogan Experience — the #1 show on reach-based charts — reached only 20% of the U.S. podcast audience in a given month.AdExchanger Senior Editor Alyssa Boyle analyzes YouTube's NewFronts presentation, where creators blurred the traditional line between talent pitches and publisher sales decks, as advertisers increasingly demand outcome-based commitments over broad reach.Consultant Steve Raizes explores how the weekly podcast production cycle traps creators on a content hamster wheel with no time for strategic growth, using Audiochuck's operational infrastructure as a model for sustainable scale.Tribeca Festival 2026 announces its most ambitious podcast lineup to date for its June run in New York City, featuring live events with Radiolab, The New Yorker Radio Hour, and Lemme Say This, with guests including Peter Dinklage, Adam Scott, and Laurie Anderson.To find links to these, and every article covered in today's episode, click here. You can also subscribe to The Download's newsletter to receive the full issue straight to your email inbox every day.

This week on Yellow Flags, Petr and Thamoda break down the upcoming Miami GP and the updated regulations that are being brought in, along with why you shouldn't buy a hot dog at the track. We also discuss Red Bull's team personnel leaving one by one and what this might mean for Max Verstappen. May is here, which means the Indy 500 is right around the corner, with open testing taking place. 

Today we're going Patreon Mode on main with an all-new Straight Culture Gabfest, wherein we talk about three juicy things happening in pop culture. On the docket this week: Madonna's comeback single "I Feel So Free," season 3 of HBO's The Comeback, and two articles about the online clipping economy: "The Fanfare Around the Band Geese Was Actually a Psyop" by John Semley in WIRED and "Clipping on Social Media Makes Me Wonder What's Real and What Isn't" by Katie Notopoulos in Business Insider. SEE SAM ON TOUR: linktree.com/samtaggart WATCH GEORGE'S SPECIAL ON AMAZON, APPLE, AND MORE: https://www.comedydynamics.com/catalog/george-civeris-a-sense-of-urgency/ CALL US at 385-GAY-GUYS to leave questions and comments for our next surprise call-in show and you just might hear your call on your favorite podcast. STRAIGHTIOLAB MERCH: cottonbureau.com/people/straightiolab SUBSCRIBE TO OUR PATREON at patreon.com/straightiolab for bonus episodes twice a month and don't forget to rate and review us on Apple Podcasts! See omnystudio.com/listener for privacy information.

Welcome To The Real Oshow,0:00 Intro0:55 Kentucky Derby Gambling Machine3:30 Mint Julep Lore Around Kentucky Derby6:20 Clavicular's $650k Clipping Campaign Explained9:00 NFL Might Lock Out Refs12:30 Closing Thoughts The Kentucky Derby isn't just a horse race; it's one of the biggest money-making weekends in sports.In this episode, we break down why it's called “the most expensive two minutes in sports,” with over $250 million wagered on the race itself and more than $450 million bet across the entire weekend.We also get into one of the Derby's most iconic traditions: the Mint Julep. Over 150,000 are sold in just two days, generating millions in revenue. But what's even crazier? It's the exact same drink whether you're paying $22… or $5,000; the difference is all in the cup and the status.Then we shift into the business of modern internet growth, breaking down Clavicular's $600,000/month clipping strategy and how repost networks have quietly become the new PR machine for creators.And finally, we dive into the NFL's push to make referees full-time employees and why many of them are pushing back. Despite earning around $385,000 per year, many refs have high-paying careers outside of football and don't want to give them up.From sports gambling and luxury experiences to creator strategy and league politics, this episode covers the business behind the headlines.Check out our YouTube page - https://www.youtube.com/channel/UCoqz3s_B_VYHuQtuVIDxpiQTikTok - https://www.tiktok.com/@therealoshow?is_from_webapp=1&sender_device=pcTweet @zacharyowings2 with your thoughts about the podcast or suggestions for future shows.Music by Leno Tk - Greatness (Streaming on all platforms)

Today we get into the latest drama on Love Island, how the clipping industry is changing the way content is consumed, and why the looksmaxxing trend is taking over the internet.Subscribe to our newsletter from the Future Party here. You can follow us on social media at @futureparty as well as our hosts @boye and @chrissawtelle. We love to hear from our listeners, so if you want to message us, you can email us at future@futureparty.com or fill out a short survey here. Hosted on Acast. See acast.com/privacy for more information.

Are we watching the collapse of short-form video and on the cusp of yet another pivot to (a different kind of) video? Today we're talking about the rise of livestreaming and what makes it different than the Vines and YouTube Shorts that you know. From Clavicular's overdose to “nuisance streamers” like Vitaly (better known as “VitalyzdTv”) and banned-from-pretty-much-every-streaming platform Johnny Somali, why do people like to watch this stuff? And how do we adapt to this new era of video content that is maybe also helping cause the downfall of society?Ryan & Grant discuss, as well as how Panic World and Garbage Day will be experimenting with video ourselves. Sponsors This episode is sponsored by Surfshark. If you want to make your online life feel just a little less exposed, go to ⁠https://surfshark.com/panic⁠ and use code PANIC at checkout to get 4 extra months of Surfshark VPN. Learn more about your ad choices. Visit megaphone.fm/adchoices

The NIA boys discuss Claude Mythos, The Clipping Economy & Anthropic's $30B vs. OpenAI's $25B (?)Timestamps(00:00:00) - Intro(00:03:20) - Claude Mythos(00:13:27) - The Clipping Economy(00:23:16) - Claude Mythos (pt2) (00:27:09) - Anthropic's $30B vs. OpenAI's $25B (?)What Is Not Investment Advice?Every week, Jack Butcher, Bilal Zaidi & Trung Phan discuss what they're finding on the edges of the internet + the latest in business, technology and memes.Subscribe + listen on your fav podcast app:Apple: https://pod.link/notadvicepod.appleSpotify: https://pod.link/notadvicepod.spotifyOthers: https://pod.link/notadvicepodListen into our group chat on Telegram:https://t.me/notinvestmentadviceLet us know what you think on Twitter:http://twitter.com/bzaidihttp://twitter.com/trungtphanhttp://twitter.com/jackbutcherhttp://twitter.com/niapodcast Hosted on Acast. See acast.com/privacy for more information.

Hotel Pacifico was created by Air Quotes Media with support from our presenting sponsor TELUS, as well as FortisBC, and Wild First.Geoff and Mike welcome Dr. Benoit-Antoine Baçon, 17th President and Vice-Chancellor of the University of British Columbia.  Leading BC's largest university with over 66,000 students and over 20,000 faculty and staff, Bacon discusses UBC's key economic role, its accessibility to students, university funding, and the growing impact of UBC Okanagan.  With a Ph.D in Neuropsychology, he offers his views on BC's overdose crisis, addiction, and mental health.  He also announces that when the Broadway Subway ultimately arrives at UBC (*pending), it will be the busiest station in TransLink's network. In the Strategy Suite, Geoff outlines his blockbuster  post on his Lotusland substack regarding the politics of DRIPA, Mike ensures all credit downgrades are heard and observed, a Clipping of the Week from an Obama heavyweight, and the latest in the BC Conservative race, including a plug for the “Race to Replace” pod series starting Sunday, April 12, for the duration of the leadership race, that Mike is co-hosting with politico Dylan Kruger.

We've been on a bit of a mini World Models series over the last quarter: from introducing the topic with Yi Tay, to exploring Marble with World Labs' Fei-Fei Li and Justin Johnson, to previewing World Models learned from massive gaming datasets with General Intuition's Pim de Witte (who has now written down their approach to World Models with Not Boring), to discussing the Cosmos World Model with with Andrew White of Edison Scientific on our new Science pod, to writing up our own theses on Adversarial World Models. Meanwhile Nvidia, Waymo and Tesla have published their own approaches, Google has released Genie 3, and Yann LeCun has raised $1B for AMI and published LeWorldModel.Today's guests have a radically different approach to World Modeling to every player we just mentioned — while Genie 3 is impressive, its many flaws demonstrate the issues with their approach - terrain clipping, noninteractivity (single player, no physics/no objects other than the player move), and maximum of 60 second immersion. Moonlake AI (inspired by the Dreamworks logo) is the diametric opposite - immediately multiplayer, incredibly interactive, indefinite lifetime, capable of MANY different kinds of world models by simulating environments, predicting outcomes, and planning over long horizons. This is enabled by bootstrapping from game engines and training custom agents: In Towards Efficient World Models, Chris Manning and Ian Goodfellow join Fan-Yun in explaining why their approach to efficiency with structure and casuality instead of just blind scaling is sorely needed:SOTA models still show physical or spatial understanding glitches, such as solid objects floating in mid-air or moving “inside” other solid objects.If the goal is to plan for the next action, how often is a high-resolution pixel view necessary for modeling the world? Our bet is that there is a disproportionately large share of economically valuable tasks where such detail is not required. After all, humans with a wide variety of sensory limitations have little difficulty doing almost everything in the world. Furthermore, for a large number of purposes, describing a scene or a situation in a few words of language (“the car's tires squealed as it cornered sharply”) is sufficient for understanding and planning.Experiments also show that humans only partially process visual input in a top-down, task-directed way, often making use of abstracted object-level modeling. In almost all cases, partial representations combined with semantic understanding are sufficient.…If the goal is to facilitate the understanding of causality in multimodal environments, then the world model—whether it is used in the virtual world or the physical world—must prioritize properties such as spatial and physical state consistency maintained over long time periods, and an ability to evolve the world that accurately reflects the consequences of actions. That's what Moonlake is building.Game engines are the right starting point abstraction to efficiently extract causal relationships, and building the interfaces and community (including their new $30,000 Creator Cup) to kickstart the flywheel of actions-to-observations.We were fortunate enough to attend their sessions at GDC 2026 (the Mecca of Game Devs), and were impressed by the huge variety and flexibility of the worlds people were building with Moonlake's tools already! Live videos on the pod.Full Video Pod on YouTube!Timestamps00:00 Benchmarking Gets Hard00:47 Meet Moonlake Founders01:26 Why Build World Models03:12 Structure Not Just Scale05:37 Defining Action Conditioned Worlds07:32 Abstraction Versus Bitter Lesson14:39 Language Versus JEPA Debate20:27 Reasoning Traces And Rendering Layer37:00 Gameplay Over Graphics38:02 Fiction Rules And World Tweaks39:15 Code Engines Beat Learned Priors41:10 Diffusion Scaling Limits43:23 Symbolic Versus Diffusion Boundary46:14 Platform Vision Beyond Games50:24 Spatial Audio And Multimodal Latents54:23 NLP Roots Hiring And Moon Lake NameTranscript[00:00:00] Cold Open[00:00:00] Chris Manning: Think this whole space is extremely difficult as things are emerging now. And I mean, it's not only for world models, I think it's for everything including text-based models, right? ‘cause in the early days it seemed very easy to have good benchmarks ‘cause we could do things like question answering benchmarks.[00:00:20] But these days so much of what people are wanting to do is nothing like that, right? You're wanting to get some recommendations about which backpack would be best for you for your trip in Europe next month. It's not so easy to come up with a benchmark, and it's the same problem with these world models.[00:00:41] Meet the Founders[00:00:41] swyx: Okay. We're back in the studio with Moon Lake's, two leads. I, I guess there's other founders as well, but, sun and Chris Manning. Welcome to the studio.[00:00:54] Fan-yun Sun: Thanks. Thanks, Chris. Thanks for having us.[00:00:56] swyx: You've got, you guys have, come burst onto the scene with a really refreshing [00:01:00] new take of mold models.[00:01:01] I would just want to, I guess ask how you, the two of you came together. Chris, you're a legend in NLP and just AI in, in, in general. You're, you're his grad student, I guess[00:01:10] Fan-yun Sun: Actually my co-founder.[00:01:11] swyx: Oh, yeah.[00:01:12] Fan-yun Sun: I should give a lot of credit to my co-founder, Sharon. Yeah. She was, she was actually working with Professor Fe Androgyn and then she ended up working with, Ron and Chris Manning here.[00:01:22] And then, so I got connected through to Chris initially, actually through my co-founder,[00:01:26] What is Moon Lake?[00:01:26] swyx: what is Moon Lake? What, what is, actually, I'm also very curious about the name, but like why going into world models?[00:01:33] Fan-yun Sun: So I was working a lot. With actually Nvidia research during my PhD years on essentially generating interactive worlds to train reinforcement learning agents or embody EA agents.[00:01:44] And then there's two observations. One in academia and one in industry. An industry like folks at Nvidia are actually paying a lot of dollars to purchase these types of interactive worlds, whether it's for the sake of evaluation or training the robots, or policies or models. And [00:02:00] then, in academia, same thing is happening.[00:02:02] And more specifically, when I was actually working with Nvidia on the synthetic data foundation model training project, we were actually generating a lot of these synthetic data and showing that, hey, you can actually, these synthetic data are actually as useful as real world data when it comes to multimodal pre-training.[00:02:16] But then, like I said, there's a lot of dollars being paid out to like external vendors or, or like. Other folks to manually curate these types of data. It was very clear to us that, okay, on our way to, let's call it embody general intelligence models need to learn the consequences behind their actions, which means that they need interactive data and the demand for those types of data are growing exponentially.[00:02:38] But everybody's sort of thinking about it from a pure, say, video generation perspective or something else. But we feel like the true actually opportunity is actually building reasoning models that can do these things, like how humans do these things today. So that's a little bit on the genesis of Moon Lake, and I think the reason I got into world models was partly.[00:02:59] A philosophical [00:03:00] take of the on the world where I like, believe the simulation theory and stuff like that. But on the other, on the other hand, it's really just like, oh, like there's an opportunity there that I feel like nobody's doing it the way I think should be done.[00:03:10] Structure, Not Scale: The Vision[00:03:10] Chris Manning: I can say a little bit about that.[00:03:12] Yeah. So of the overall goal is the pursuit of artificial intelligence and most of my career has been doing that in the language space and that's been just extremely productive. As we all know, the story of the last few years, I don't have to tell about how much we've achieved with large language models, but, uh.[00:03:31] Although they have been extremely effective for ramping language and general intelligence, it's clearly not the whole world. There's this multimodal world of vision, sound, taste that you'd like to be dealing with more than just, language. And then the question is how to do it. And despite, a huge investment in the computer vision space, right, as the research field computer [00:04:00] vision has been for decades, far, far larger than the language space, actually.[00:04:05] I think it's fair. Say that, vision, understanding sort of stalled out, right? You got to object recognition and then progress just wasn't being made right? If you look at any of these, vision language models, it's the language that's doing 90% of the work and the vision barely works. And so there's really an interesting research question as to why that is and at heart, the ideas behind Moon Lake are an attempt to answer that, believing that there can be a really rich connection between a more symbolic layer of abstracted understanding of visual domains, which aren't in the mainstream vision models, which are still trying to operate on the surface level of pixels.[00:04:50] swyx: I think one of your blog posts, you put it as structure, not scale. Is that, a general thesis?[00:04:57] Chris Manning: Yeah. Well, scale is good too.[00:04:58] swyx: Yeah. Scale is good. Too[00:04:59] lot,[00:04:59] Chris Manning: [00:05:00] lots of data is good as well and scale, but nevertheless, you want the structure Yeah. To be able to much more efficiently learn.[00:05:07] swyx: Yeah. The other thing I really liked also is you put out an example of what your kind of reasoning traces look like.[00:05:12] Right. Which you would distill is the word that comes to mind. I don't even think that's a good, good description, but it would involve, for example, geometry, physics, affordances, symbolic logic, perceptual mappings, and what, what have you. But like that, that is the kind of example that involves, let's call it spatial reasoning, role model reasoning as as compared to normal LM reasoning.[00:05:35] Yeah.[00:05:36] Defining World Models vs Video Generation[00:05:36] Vibhu: But also like taking it a step back. So how do you guys define world models? A lot of people see okay, you can do diffusion, you can do video generation. But, you guys put out quite a few blog posts. You put out a essay recently, we can even pull it up about efficient world models. You have a pretty like structural definition here, but for the general audience that don't super follow the space, right.[00:05:55] What's, what's the difference in what we see from like a video generation model to [00:06:00] a world gen A simulator? How do you kind of paint that last[00:06:02] Chris Manning: year? Yeah, so I think this is actually a little bit subtle because, people look at these amazing generative AI video models, SAWA VO three, one of these things, and they think Genie, they think, oh, this is amazing.[00:06:17] This is we've solved understanding the world because you can produce these generative AI videos, but. The reality is that although the visuals do look fantastic, those visuals actually are accompanied by an understanding of the 3D world, understanding how objects can move, what the consequences of different actions are, and that's what's really needed for spatial intelligence.[00:06:49] So I mean, a term we sometimes use is that you need action condition, world models. That you only actually have a world model if you can predict, [00:07:00] given some action is taken, what is going to change in the world because of it. And in particular, that becomes hard over longer time scales. So if you're simply, trying to.[00:07:12] Predict the next video frame. That's not so difficult. But what you actually want to do is understand the consequences, likely consequences of actions minutes into the future. And to do that, you actually much more of an abstracted semantic model of the world.[00:07:32] The Bitter Lesson & Data Abstraction[00:07:32] swyx: Yeah, the question comes where you want to have more structure than is available in just predicting the next token.[00:07:41] And typically, well, let's, let's call it the experience of the last five years has been that is just washed away by scale, right? So what is the right middle ground here that, you don't ignore the bitter lesson, but also you. Can be more efficient than what we're doing today.[00:07:57] Chris Manning: One possibility [00:08:00] is, look, if we just collect masses and masses and masses and masses of video data, this problem will be solved.[00:08:11] Under certain assumptions that could be true, but there are sort of multiple avenues in which it could not be true. The first is what's really essential is understanding the, the consequences of actions producing an action conditioned world model. And if you are simply, collecting observational video data, which is the easy stuff to collect, when you're sort of mining online videos, you don't actually.[00:08:41] Know the actions that are being taken to see how the video is changing. And so if you are never collecting directly actions and you are having to try and infer them from what happened in the observed video, that's not impossible. But it's very [00:09:00] hard and it's not really established that you can get that to work at any scale yet.[00:09:05] And so there's a lot of premium on collecting action condition video data, which is part of why there's been a lot of interest in using simulation so that you can be collecting data where you do know the actions, which isn't quite limited supply, but there's also in the limit of as much data as you could possibly have.[00:09:28] Maybe the problem is eventually solvable, but. Even though we collect huge amounts of text data is always at a great level of abstraction, right? Language is a human designed, abstracted representation where there's meaning in each token and it's representing and abstraction of the world, right?[00:09:51] As soon as you are describing someone as a professor, and as soon as you are saying that they're condescending, right? These are very [00:10:00] abstracted descriptions of the world. It's not at what you're observing as pixel level, and to get to that kind of degree of abstraction, starting from pixels is orders and magnitude of extra data and processing.[00:10:14] And so, although, we absolutely want to exploit, get as much data as possible, use the bitter lesson. Nevertheless, if there are ways in which you can work with five orders of magnitude less data than people working purely from pixels, you're gonna be able to make a lot more progress, a lot more quickly.[00:10:34] And that's the bet here. And so you could just say that's only wanting to be able to, do it more efficiently, do it more quickly, do it more cheaply. But I think it's actually more than that, I think. One should be making the analogy to how human beings work at one level. You know? Yes, we have these high [00:11:00] resolution eyes and we can look and see a scene like a video, but all of the evidence from neuroscience and psychology is that most of what comes into people's eyes is never processed.[00:11:13] Right. That you are doing fairly fine ated processing of exactly what you're focusing on. But as soon as it's away from that of yeah, there's another guy over there that you've sort of only processing top down this very abstracted semantic description of the world around you. And so, that's what human beings are doing.[00:11:33] They're working with semantic abstractions and so. I think it is just the right representation. ‘cause we also have other goals we want to be able to do, real time worlds. So that means there's a limit to how much processing you can do and we want to do long-term planning and consistency. And again, that favors abstraction.[00:11:55] I mean, I guess there was actually a recent. Blog posts that [00:12:00] came out from our Friends of physical intelligence and, they were sort of heading in the same direction they were saying Oh, to the pay[00:12:06] swyx: pay model.[00:12:07] Chris Manning: Yeah. Yeah. To maintain a long term memory of what's happening in the world. So we can, do longer term we actually storing text of what is, been happening in the world.[00:12:19] Right. It is not such a successful strategy of trying to keep it all at a pixel level.[00:12:24] Vibhu: And yeah, I mean, you can see it in video models like that Temporal consistency. We're at a scale of train on, all the video data we have. We have it for maybe 30 seconds, a few minutes. That's not the same as a game state played for half an hour.[00:12:37] Right. I thought you guys break it down pretty well. You have a, you have a blog post about. Building multimodal worlds with an agent. I dunno if you guys wanna talk about this. This is one of the things I read, I[00:12:48] swyx: thought, yeah, it's the thing I talked about with the reasoning chain. Yeah.[00:12:51] Vibhu: So there's like different phases to this.[00:12:53] It seems like it's more of an agent, a scaffold, very different approach than just, type in a prompt and you, you don't have the same consistency. [00:13:00] It also, like, for people that are listening, I, I would highly recommend reading it. It breaks down the problem in a different light, right?[00:13:06] So like, what do you need to consider when you're talking about video, like world game models, right? How would, what do you need to consider? What are the factors? What are the elements? What's the state? So I don't know if you guys have stuff to talk about for this one.[00:13:19] Fan-yun Sun: Yeah. Actually, I wanted to add on a little bit Yeah.[00:13:22] On our previous point, which is just like, change topics so quickly. I, I do feel like sometimes people confuse like, oh, like we're taking an an, an method with abstraction. That means they don't believe in bitter lesson. Like that's just false, right? Like we are believed is a bitter lesson. But then I feel like the question that we always discuss is like, what is the right abstraction level today?[00:13:42] The analogy I like to make is like, let's just say we can encode and decode. Represent all of images, videos, audio and bytes. Then the most bitter lesson approached is to train a next byte prediction model as opposed to the next token prediction model where it's just like, okay, it's natively multimodal, can just, but it's like, yeah, like [00:14:00] to, to Chris's point, it's like the scale and computing you need to achieve that.[00:14:03] So that's why we always come back to like, okay, what is the most efficient way to do it? And reasoning models to the point of this blog post is a showcase of like, Hey, we're actually just like reasoning about the world and reasoning about. The aspects of the world that CAGR that matter for me to learn what I want to learn from this role model.[00:14:21] swyx: Yeah, it's like you're improving the en encoder of whatever you're, trying to model. And like a better representation would just represent the important things in less space. Yeah. Which would just be more efficient.[00:14:33] Fan-yun Sun: Yeah.[00:14:34] swyx: So yeah, I, I, I fully agree that it is not, antagonistic to, bitter lesson.[00:14:38] I do wanna wanna mention one more thing. Is there any philosophical differences with the JPA stuff that, Yun is working on? I gotta go there. You, you, you, you're, you're imagining like some latent abstraction. I'm like, okay, fine. Let's, let's talk about it, right? Like it's an elephant in the room.[00:14:52] Chris Manning: Yeah.[00:14:53] JEPA & Philosophical Differences with LeCun[00:14:53] Chris Manning: There are philosophical differences. Jan Lacoon is a dear friend of mine, but. [00:15:00] He has never appreciated the power of language in particular, or symbolic representations in general. Yarn is a very visual thinker. He always wants to claim that he thinks visually and there are no words, symbols, or math in his head.[00:15:21] Maybe that's true of yarn. It's certainly not the way I think. Um. But at any rate, the world according to yarn is the basic stuff of the, the world and of intelligence is visual and language is just. This low bit rate communication mechanism between humans and it doesn't have much other utility and it's far inferior to the high bit rate video, that comes into your eyes.[00:15:53] And I think he's fundamentally missing a number of important things [00:16:00] there. Think of this evolutionary argument looking at animals, right? That the closest analogies, the things with chimps, right? So chimpanzees, have fairly similar brains to human beings. They have great vision systems, they have great memory systems.[00:16:18] They've got, better memory than we do of short term memories. They can plan, they can build primitive tools that, humans. Massively ahead in what we understand about the world, what we can plan, what we can build. And essentially what took off for us was that humans managed to develop language and that gave a symbolic knowledge, representation, and reasoning level, which just, okay if this sort of vaulting of what could be done with the intelligence in brains.[00:16:59] So the [00:17:00] philosopher Dan de refers to language as a cognitive tool and argues that, humans unique among the creatures in the world have managed to build their own cognitive tools and language is the famous first example. But other things like, mathematics and programming languages are also cognitive tools.[00:17:21] They give you an ability to. Think in abstractions, in extended causal reasoning chains. And that allows you to do much more. And we use that for spatial representation and intelligence and planning and gameplay as well. So we believe, and this is, underlying the specific technologies that Moon Lake is making, that symbolic representations are powerful.[00:17:50] And you want to use that in your understanding of the visual world when you want a causal understanding, when you want to maintain long-term [00:18:00] consistency and prediction. And as I understand it, that's just not in ya Koon's worldview. So I think that's the fundamental philosophical difference. Then there's the specific model.[00:18:11] He's been advancing jpa, that's a reasonable. Research bed is a direction as to, to head for building out a model of the visual world. To my mind, it's sort of one reasonable research bed. It's not really established. It's the best one that everyone should be following,[00:18:32] swyx: at least developed at scale, at Meta.[00:18:34] But it's not just vision, right? Like, I mean, JPA is a, just joint admitting prediction can be applied to anything really. And people have done it. The argument is that there is a latent representation or that is probably more. Suited to the task, then why not let machines do it for us instead of predefining it at all?[00:18:50] And isn't something like a JPA shaped thing the right answer? And if not, why not?[00:18:55] Chris Manning: So I think there's a part of jpa that's right, which is [00:19:00] you do want to have a joint. Embedding that gives you a consistent model of the world. And Jan's argument is you can never get that from auto aggressive language models ‘cause they're sort of left to right churning out one token at a time.[00:19:22] I guess this is where we're the research arguments of the field, I'm not actually convinced that's right. ‘cause although the token production is this auto aggressive, process that's heading, left to right, I guess don't have to be left to right. But anyway, in sequence of tokens we could have right to left Arabic.[00:19:40] But although that's true, all of the weights of the model that are internal to the transformer, they are a joint model of the model's understanding of the world. And so I think you can think of the weights of the model as a form of. Joint representation, [00:20:00] and therefore it is plausible to think that could be the basis of a world model, which avoids, ya's objections.[00:20:10] swyx: I think I follow, and obviously that would touch on what Moon Lake eventually ends up doing as well. Right. Like, which it's hard to tell because you put out the end results, but we don't know the inputs that go into it. So it's, it's, that's something that we have to figure out over time.[00:20:25] Vibhu: Yeah. I mean, I guess this kind of breaks down some of the outputs. Do you wanna walk us through it?[00:20:31] Reasoning Traces & Interactive Worlds[00:20:31] Fan-yun Sun: Yeah. So this, this really just walks us through the reasoning traces of like, okay. So that just say, if we wanna build a world in this context, it's really just a game demo that, that shows the, the variety of interactions that this world model can build.[00:20:45] And yeah, it's really just a reasoning traces of like, okay it prompted to create a bowling game. Like how did it achieve what you saw? That level of causality, interaction and consistency, right? So yeah, this is almost just like a, an example of [00:21:00] like a reasoning traces. Very[00:21:01] swyx: detailed.[00:21:01] Fan-yun Sun: Yeah.[00:21:01] Vibhu: Very, very detailed.[00:21:02] You gotta you don't even realize it, right? Like when a video is generated, what happens when a ball strikes a pin, right? So first, like you, there's audio in that, like audio triggers happens, score increments, the world changes. Like pins have to start dropping. There's a timer that goes on. It's just like very similar to how now we're used to reasoning for language models.[00:21:20] There's a whole state of what happens. So geometry, physics, all this stuff. And then yeah, there's kind of that single prompt. So asset, ation all this stuff. It's like a, it's a nice view to see what's going on.[00:21:32] swyx: I think Sun is also too polite to point out that, both like Google's genie, demos as well as world Labs is marble, do not have interactive worlds.[00:21:41] Fan-yun Sun: That's the benefit of having a reasoning model, right? Like, because you can, you can say, oh, like maybe in this particular context, I want to learn how to bowl. And then you can say, okay, then what is it important when it comes to learning how to bowl? Okay, maybe it's like I need to understand the, the basic of like, physics and I want to throw it over [00:22:00] them.[00:22:00] I wanna know that when I, when it resets it's a new game. So I know that yeah, basically, you know to pick up the ball, you know that ball's gonna cause the pins to fall down. You know that what's important to this particular bowling game is to score and you know that the score corresponds to the number of pins that fell down.[00:22:19] So it's just like, if it's a model that sort of knows what it. Looks like, knows what a bowling game looks like, but doesn't actually allows you to practice over and over again and to understand that, oh, like what it takes to actually get a high score. Then it sort of doesn't actually allow you to learn what you set out to learn within the world model.[00:22:38] And I think this is really just one example of showing like the advantages of the approach that we're taking over most the, let's call it the zeitgeist, is today, when people talk about clinical role models,[00:22:51] Chris Manning: right? So it sort of seems like the question to ask when there's a world model is.[00:22:58] Can I not [00:23:00] only just wander around the world and look at the beautiful graphics, can I interact with the objects in the world and see the right consequences of actions?[00:23:11] Vibhu: And you also understand what the consequences would be if you do something right. So it's not just like, okay, there's one thing if I pick it up, something will happen.[00:23:19] But, there's 50 options and I know I can expect, I can infer what would happen if I do any of them. Right. So very different when you can actually see it play around with it.[00:23:28] swyx: There,[00:23:28] Beyond Unity: Cognitive Tools for World Building[00:23:31] swyx: there's two cheeky elements of that. I mean, the, the, the I guess, less ambitious one is, let's really establish for listeners, why is this fundamentally different than writing Unity code, right?[00:23:40] Like just creating a model to translate a prompt into Unity code[00:23:44] Fan-yun Sun: so there is an underlying physics engine. Yeah. In that sense, there's some overlapping things to Unity, but the way we think about it is like physics engine. Tools or code are cognitive tools like borrowing Chris's term, right? Like tools [00:24:00] that the model can employ as means to an end.[00:24:04] So today maybe you say, okay, in this particular context we care about physics, we care about the long-term causality consequences. Then yes, we deploy it, employ physics engine, and then maybe tomorrow we say, okay, we're we're training that. Just say drones where we only care about really fluid dynamics and the visual aspect of the world.[00:24:25] Then, then yeah, maybe we don't actually, the model actually doesn't have to use a physics engine. Or maybe it employs other types of representation or physics engine to achieve the task. So yes, writing code for Unity is sort of similar to a tool that our A model can employ, but our goal is for a model to take a representation conditioned reasoning.[00:24:46] Approach or process.[00:24:47] swyx: Yeah,[00:24:47] Fan-yun Sun: internally.[00:24:48] swyx: Yeah. Using these things as just like general two calls. Right. Which I think is very interesting. The other more ambitious one is, some kind of recursive element where it becomes multiplayer, right? Like here, there's a single player element, you're not [00:25:00] modeling any other people involved.[00:25:01] And that is a whole other thing.[00:25:04] Fan-yun Sun: But in fact, we can really do multiplayers. Oh yeah, okay. I haven't seen any double situations. So just actually just like prompt our, our model to say, Hey, like configure to multiplayer. Then it'll do like this. You'll be able to configure multiplayer[00:25:16] swyx: great[00:25:17] Fan-yun Sun: persistency database for you.[00:25:18] Easy. Yeah.[00:25:19] Vibhu: So what, what are like some of the current limitations in where we're at? So there's one approach of like, okay, scale up video predictors. Obviously there's data issues. With approaches like this, is it data constraints? What are like the next steps? Is it real time? Like, so there's one side of, write an agent to write Unity code, but okay, I want to be streaming a game real time.[00:25:38] I want to have characters being also like agent, but where, where do we kinda see this scaling up? Right?[00:25:44] Fan-yun Sun: Yeah, there's definitely a data constraint. Like the more data, the, the better. This reasoning model can almost basically act as humans to like operate a variety of tools and softwares to build whatever's necessary.[00:25:57] And then there's a sort [00:26:00] of fidelity constraint, which we're actually solving with another model, which we can talk about later. But it's like, it's not as easy to get to photorealism with the approach that we're taking. But we think there are better solutions to that, which is we can dive into later.[00:26:14] Later.[00:26:15] Vibhu: The one one thing you note here is it's a diffusion model, right? So there's, there's a few approaches, diffusion caution, splatting, yeah, so Ry diffusion model, you guys wanna[00:26:25] Fan-yun Sun: Yeah.[00:26:25] Vibhu: Introduce,[00:26:26] Fan-yun Sun: yeah, totally.[00:26:26] Rie: Neural Rendering & Skins for Worlds[00:26:26] Fan-yun Sun: So within our world modeling framework, we think there are two models that we train, right?[00:26:31] Like, there's the multimodal reasoning model that we just talked about that essentially handles. Mainly the, the causality, the persistency and logic determinism of the world. And then RY is our bet on saying, okay, like while all those model, can take care of all these things that we just talked about, it's limitations compared to existing, say, video models, is that it doesn't have as high of a pixel [00:27:00] ality right off the gate, right?[00:27:02] And EE is to say, Hey, we can actually take whatever persistent representation that we generate with our multimodal reasoning model and learn to restyle it into photo photorealistic styles or arbitrary styles you want. So this model is almost to say, Hey, I'm going to respect the persistency and interactivity of the world that you created, but my only job is to make sure that its pixel distribution is close to what we want.[00:27:29] Vibhu: Yeah.[00:27:30] swyx: Great example right there. You kept the KL divergence.[00:27:33] Fan-yun Sun: Oh. Where,[00:27:34] swyx: no, no. I mean this, this is a, a classic like, how you don't stray too far from the source material as you, you kept the kl, which is Oh yeah. Kind of cool. Yeah.[00:27:43] Fan-yun Sun: Yeah.[00:27:44] swyx: I mean, and the[00:27:44] Chris Manning: difference is, and I mean sun was pointing at this, where sort of saying it's in one way a more difficult path, but a better path that, typically the diffusion models are producing the whole scene and it looks lovely, [00:28:00] but there isn't spatial understanding behind it, which is allowing for the real time graphics gameplay, the spatial intelligence, understanding the consequences of worlds where this is, taking a path where it is assuming an abstracted semantic model of the world's state.[00:28:20] And then the diffusion model is then being used on top of that to produce the high quality graphics.[00:28:27] swyx: Is there an intended practical, or business use for this, or is it like a, like a demonstration of capabilities?[00:28:34] Fan-yun Sun: We actually believe that this is gonna be the next paradigm of rendering. So it's gonna replace how ra raizer, it's gonna replace DLSS today because it not only has these pixel prior that's learned from the world such that you can literally play any game in photo realistic styles, which is a lot of people's desire when they do GTA, right?[00:28:51] Like,[00:28:51] Vibhu: all the mods, all the people adding perfect lighting and all this.[00:28:54] swyx: So[00:28:54] Fan-yun Sun: skins[00:28:55] swyx: for worlds, let's call it[00:28:56] Fan-yun Sun: skins, let's call it skin for worlds. I,[00:28:58] Vibhu: it's also like, you can call it skin, you can call it [00:29:00] customization. You can play it how you want, right?[00:29:01] Fan-yun Sun: Yeah, exactly. And I think another thing that we really pointed out specific specifically in this blog is the programmability of it, right?[00:29:09] So what this means is that this render historically render is always a derivative of the game state, right? You're saying, oh, here's the game state, I'm rendering out a frame. But here I'm saying actually this render can be part of the gameplay loop. I can say something along the lines of, if upon getting 10.[00:29:26] Apples, I'm gonna, my weapon of choice, my bullet's gonna turn into apples. And that's, that's possible because we can say, we can basically dynamically have certain game state trigger the, the preconditions to the render such that the rendering is now part of the game loop too. One thing is to just say, okay, it's, it's, it's the appearance.[00:29:47] But the second thing is also to say there's these novel interactions that are possible because this render now has actually priors of the world.[00:29:57] swyx: It is up to the artist to figure out what to do with it.[00:29:59] Fan-yun Sun: It [00:30:00] is up to the creators. Yes.[00:30:01] swyx: Yeah.[00:30:01] Fan-yun Sun: And I also think that's actually another big argument that we're making and the reason that we're picking, taking the bet we're baking is that a lot of the times, whether it's for embody AI gaming, like you want a layer where human can inject their intentions.[00:30:15] So, for example, let's just say in the context of gaming, it's obviously like my creative intent, but maybe in the context of embodied ai, it's like, oh, like I take this foundational policy and I want to actually fine tune it to deploy in my house. So you want to almost say, inject, have a layer where human can say, oh, here's the distribution of things I want to create to achieve my goal.[00:30:35] And I think 3D graphics as it as it is today, is basic, the layer for people to say, Hey, what do I care about in this world? And it allows, basically human intent to be expressed in these worlds much more explicitly and distributionally as opposed to just saying, Hey, I'm gonna generate like, arbitrary.[00:30:54] And it's like just prompts,[00:30:55] swyx: it's one of those things where like, I think you, you're going to build up a series of models, right? [00:31:00] This is just one of, this is probably like the highest utility or heaviest, frequency one, I don't dunno what to call this. Where like you Yeah. You can immediately drop this in on any game and you don't need anything else that.[00:31:10] That you guys do. But, I, I could see, I could see that I think the, the human intent is something that people are not even used to because we're so used to static worlds or, worlds that just don't react, or, I don't know. It's, it, you're kind of blowing my mind right now with like, I'm, I wonder if you've talked to people at GDC Hmm.[00:31:27] And what are they gonna do with it?[00:31:30] Fan-yun Sun: Yeah. Now the stance that we take on this front is like, we're not gonna be more creative than our users to ship[00:31:35] swyx: it out.[00:31:35] Fan-yun Sun: Yeah. But we wanna make sure that we're building things in a way that really allows them to express their intent.[00:31:41] swyx: The thing that you said about, here's the distribution that I want.[00:31:45] I think text may be too low of a bandwidth to. To really demonstrate, because I, I, there, I'm, I'm probably just gonna want to drop in a bunch of, reference assets and then you can figure it out from[00:31:58] Vibhu: there. But you probably wanna do a, a mixture of [00:32:00] both, right? Like you throw in a few images. I wanted this style.[00:32:02] Yeah. I want it to look like this. So it, it's, it's a mixture, right?[00:32:05] Chris Manning: I, I think it's a mixture. I mean, yeah, I mean there's clearly a visual component of this, and it's not that, everything can be text. ‘cause of course you want to give a visual look, but there's also a massive amount of giving the overall picture of the look of the world and the behavior of things that you can express in a few words of text.[00:32:32] And it be very time consuming and difficult to do via visual means. So I think, yeah, you want a combination of both.[00:32:40] Evaluating World Models[00:32:40] Vibhu: So one question I kind of have is, how do we go about evaluating world models? So like, there's many axes, right? One is like, okay. I have preferences. How well do we adhere to prompts? One is the simulation.[00:32:50] One is like do things, is there core logic that's broken? So coming from we know how to evaluate diffusion, there's fidelity, there's [00:33:00] stuff like that. But what are some of the challenges that most people probably aren't thinking about?[00:33:04] Fan-yun Sun: Yeah, I think this is like a great question and probably one of the hardest questions in role models because like, I think it always comes back to what are you building this role model for?[00:33:13] And depending on your end goal and purpose, the evaluation should defer. So in the context of games, then the most direct way of measuring is how much behind are people actually spending in this world that you create? And if your goal is to say, for example, in the context that we just talked about, like, hey, deploying, deploying action in body, a agent, then your, your end.[00:33:33] Metric is then, okay, after training in these worlds that you generate how robust it is to when you actually deploy to the target environment. But then, it's, it's hard to measure these end metrics. So today people have like these proxy metrics that I call that basically try to measure what we really care about, which is the end metrics, but then frankly it's different for every use case.[00:33:57] Yeah,[00:33:57] Vibhu: which seems like quite a challenge, right? Like in [00:34:00] in language models or video models. Image models, your benchmarks are proxies, right? People aren't actually asking instruction, following tool use questions. They're proxies of how well it will do downstream. But for this, so like, should teams, should companies have their own individual benchmarks outside of games?[00:34:16] If you think of stuff like, okay, video production, movies, stuff like that, that also want to use world models. Should, should they sort of internalize like. Their own proxy. Is this something you guys do? Where, where does that connect[00:34:28] Chris Manning: go? Yeah, I think this whole space is extremely difficult as things are emerging now.[00:34:35] And I mean, it's not only for world models, I think it's for everything including text-based models, right? ‘cause in the early days it seemed very easy to have good benchmarks ‘cause we could do things like question answering benchmarks and could you answer the question based on these documents and the various other kinds of, do pieces of logical reasoning or math.[00:34:58] But again, these are sort of. [00:35:00] And there were sort of visual equivalents of things like object recognition, right? For these small component tasks. These days so much of what people are wanting to do also with language models is nothing like that, right? You're wanting to, have an interaction with the language model and get some recommendations about which backpack would be best for you for your trip in Europe next month.[00:35:25] And it's not the same kind of thing, right? And it's not so easy to come up with a benchmark as to does this large language model give you an effective interaction for guiding you in a good way for shopping, right? So, and it's the same problem with these world models. So if we take the game design case, well success is that a game designer can.[00:35:57] Produce what they are [00:36:00] imagining in a reasonable amount of time. And that's really the kind of macro task. That's a very hard thing to turn into a benchmark and I think a lot of this is actually going to turn into people walking, walking with their feet. Right? I mean, I guess that's what's happening, at the large language model level, right?[00:36:23] When people are choosing to use, GPT five or Gemini or clawed, individuals are trying out these different models and deciding, oh, I like the kind of answers that GT five gives me, or no, I feel like I get more accurate detail from Claude, right?[00:36:43] Vibhu: It's a lot of[00:36:43] Chris Manning: vitech, a lot of people just using it.[00:36:45] It's vibe checking. I realize that, but it's actually whether. People feel it's giving them utility in what they want. Right.[00:36:52] Vibhu: And the the interesting thing there is like a lot of people prefer the visual, right? This looks pretty, which is not the objective of what this is [00:37:00] for, right? It's if a, if a game designer is working on something, they care about the game engine, right?[00:37:04] The state, it's, it can look whatever. You can fix that up later. Or you can have a really good game state and you can quickly edit it to 20. 20 different versions, like Keep State,[00:37:14] Chris Manning: right?[00:37:14] Vibhu: So[00:37:14] Chris Manning: that's a really important distinction, for and for speaking to Moon Lake strength, right? So, yeah, great visuals are lovely to look at for a few seconds, but gains are really all about the concept, the game play.[00:37:33] And a lot of the time that doesn't actually even require great visuals. I mean, there are just lots of very successful games which have relatively primitive visuals, and there are other games where people have spent millions producing photo realistic, visuals, and the game sucks, right? So, keeping those two axes apart is really important in thinking about what's important in a [00:38:00] world model for different uses.[00:38:02] swyx: This conversation is reminding me of some game review and fiction discussions I've, had in my sort of non-AI related life. Some, for some people might know Brandon Sanderson, who's a very famous, fiction author, had, is is a big game reviewer. And he, he's a big fan of video games where you change one thing about a normal what you might assume about, about the world.[00:38:22] For example, Baba is you, I don't know if you might have come across that, where like the rules change as you play the game. And also like where, you can do things like reverse time selectively or like change gravity selectively. And I think this is also reminds, reminds me of other kinds of world models that are created by authors.[00:38:38] Where Ted Chang is, is my typical example where he'll take the world that, you know today, but change one thing about it and, but then create a consistent world based on that. Which is long-winded answer of me to, of. For me to say is it's it easy to create alternative roles that don't exist, but you change one thing and then let's, let's run a whole bunch of people through it to see if it works.[00:38:58] Chris Manning: My first dance will [00:39:00] be, that seems a lot easier and more conceivable to do using Techn technology like Moon Lakes than with some of the other world models out there, where the sun can actually make it happen. I'll let him give a second answer.[00:39:15] swyx: If I guess for you, you're constrained by the game engine tool, right?[00:39:18] Like at the end of the day, that's the, that's the thought, partner that you have. If I ask for something where like, if it never is allowed to reverse time or if gravity only ever works one way, then well that's it. But sometimes gravity might change,[00:39:33] Fan-yun Sun: but it's a lot easier to change with code as opposed to a model that is learned primarily on data of.[00:39:42] Real world and virtual worlds that are, I guess, like for example, junior, like there's actually trained on a lot of real world data and a lot of virtual gaming data, and it's hard to say maybe it's easier to say, okay, I wanna change the visuals in like the time period of, of the world. Like, you can't change gravity, for [00:40:00] example.[00:40:00] Vibhu: I feel like you can to light bounds, right? Everything comes down to like, code is a better way to execute it, but the models aren't that diverse and creative, right? You can say, okay, make gravity slower. It can do that, but it's limited to your representation of how you text it out, right? Like they're, they're only gonna do a few iterations, whereas programmatically, if there's a game engine under the hood, you can kind of go wild, right?[00:40:22] So one of the, I dunno, one of the limitations of most models is that they're very overtrained to one style. Right. And extracting diversity is pretty difficult. At least that's something we've seen.[00:40:35] Fan-yun Sun: I mean, are there examples you have in mind where you Existing models? Yeah. Like it would be easier to do that's not using code.[00:40:43] Certain types of creative intent or like transition state transitions,[00:40:47] swyx: Clipping, other models, other wo models are very good at clipping through things. Clipping my, my, my legs clipping through a rock because it's, it's just, it's just bad. [00:41:00] Like, you would have to struggle very hard with your stuff to actually make that happen.[00:41:04] Which I think is maybe a topic that you actually prepared on, Gian Splatting versus, the other stuff.[00:41:09] Vibhu: Yeah. Yeah. It's just for those not super familiar, right? There's a, there's gian splatting, there is diffusion. Like what works, what scales up. I feel like in February when Soro one came out the blog post was literally titled like,[00:41:21] swyx: you bring it up.[00:41:22] You never know.[00:41:23] Vibhu: World, world, video generation models are world simulators. It's super bitter lesson pilled. Yeah, emer, a lot of it is emergence, right? So, not to go through their blog post, basically their whole thing was as you scale up all this consistency, all this stuff just kind of solves, it's a very simple premise, right?[00:41:41] They just scaled up, diffusion, and from there, this is, this is Feb 2024, how much can we, it's already been two years, which is basically five years. How much more in AI time do we need to just scale up or, or do we hit a data cap? But I think we already talked about this a lot, right? Like this is back to the beginning discussion of what's [00:42:00] appropriate for the time.[00:42:01] And that seems like your approach, right?[00:42:03] Fan-yun Sun: Yeah. The point I'm trying to make is that they're very many, many different types of world simulators and like having a world simulator that can produce pixel coherency is very, very useful for games and, marketing and all these things, but it's not as useful as people think when it comes to causal reasoning.[00:42:25] When it comes to embodied ai. Yeah, like it this title is true. We're not saying that it's, it's like, not a great world simulator, but actually in the blog that we, we, we, we wrote, the bet is more so that there are gonna be disproportionately large share of value of real world tasks or, and virtual tasks where high resolution pixel fidelity is not needed.[00:42:47] Yes. Video models have their values.[00:42:50] swyx: Yeah. This is at the absolute limit of my physics understanding, but one example that comes to mind is basically having to solve like ba the equivalent of a three [00:43:00] body problem in a deterministic Well, where the video models, which is approximated good enough. Yeah.[00:43:08] Right. Like there's, there's some point at which your approach kind of runs into like the you now have to simulate the world. Please, thank you very much. And like you're trying to do that, but only to the extent that the game engine lets you and like game engines cannot do some things.[00:43:23] Fan-yun Sun: Yeah, no, I mean, I think the interesting or more technical question here actually is where do you draw the boundary between.[00:43:32] What's handled with, let's say, diffusion prior and what, when? What's handled with symbolic priors?[00:43:38] swyx: Yes.[00:43:38] Fan-yun Sun: Okay.[00:43:38] swyx: Okay.[00:43:39] Fan-yun Sun: Right. Let's go there. Because this, this boundary can actually be fluid. Like I think like maybe what you're trying to get at is like, okay, people are saying pixel prior, everything. But what we're saying is, okay, there's a boundary that we draw where this is where we think provides the most economical value for the domains and things that we care about today.[00:43:59] [00:44:00] And I actually do think, and it's something that we do internally all the time, which is like, okay, given new equations that we learn or new elements of the world and that we, we learn, or maybe some other knowledge that we acquire in the process of developing the models. Should we still be maintaining this line exactly as it is today?[00:44:22] Or should we move it a little bit left or a little bit right? Right. Like sometimes that we realize that, oh, like maybe customers or, or folks like want certain things that are better handled with preop pryor as opposed to, symbolic prior than,[00:44:34] swyx: yeah. Your, your skin thing is a, is a example moving it, right.[00:44:37] Yeah.[00:44:37] Or left. Yeah,[00:44:37] Fan-yun Sun: exactly.[00:44:38] swyx: I dunno what the, the left right is.[00:44:39] Fan-yun Sun: Yeah, yeah, yeah. No the, the model.[00:44:42] swyx: Yes.[00:44:42] Fan-yun Sun: Actually we have a few iterations of them. They're actually at slightly different[00:44:45] swyx: I know boundaries. You should, you should do that. That's a cool dimension to show.[00:44:49] Fan-yun Sun: Yeah.[00:44:50] swyx: Is quantum mechanics the diffusion prior of our world?[00:44:55] Right. It's like that's the boundary of classical mechanics versus quantum. Right? Like, that's it. At one [00:45:00] point God plays dice and the other point doesn't.[00:45:02] Fan-yun Sun: I dunno if Chris, you wanna say it, but I think, I think generally I feel like physics is better with symbol P priors.[00:45:08] Chris Manning: Even quantum physics.[00:45:09] Fan-yun Sun: Even quantum physics.[00:45:11] swyx: Yeah. This is starts against to, MLST territory is, is what I call it, where, he, he likes to get philosophical. We, we we're quite friendly.[00:45:18] Vibhu: I mean, we need to get, we need to get singularity. I heard some of that.[00:45:23] swyx: No, no, I think that is actually really helpful and man, I just want you to productize this like, as a product guy, I'm just like, oh, also[00:45:32] Vibhu: a gamer, I[00:45:33] swyx: wanna, it's like a researcher, like, it's cool.[00:45:35] Like this is a, the theoretical, like you have a very good, I don't know, like the way of thinking about these things, but I just wanna see you like, express it. I do think like your fundamentally things when, when you leave open new tools, like, okay, use, use human intent to incorporate it into how you render.[00:45:52] Artists are gonna have to take like two to three years to figure out what to do with this. And you just don't know.[00:45:57] Chris Manning: Right. But I think, this is, [00:46:00] gives a much more approachable and controllable world for the society, which is the beauty, the beauty of, NLP, that that will enable it to be adopted and used.[00:46:10] And we are very hopeful about that. Yeah,[00:46:13] Fan-yun Sun: yeah. Yeah. I mean, we are, we are very focused actually on commercialization in the sense that like we do, we do really believe in the data flywheel app approach. Yeah. Where, we put this in the hands of the creators and the users and then they will teach us when, what capability our model should improve.[00:46:27] And that's why we are, we are actually, like products and beta[00:46:31] swyx: Yeah. Focusing on gaming. What, what's like the adjacent thing to gaming[00:46:34] Fan-yun Sun: embody adjacent, basically. So maybe we can, we can I'll maybe start with where we see the platform in three years. Yeah. Which is like, okay. The users would tell us what they want to achieve.[00:46:45] The end goal could be, Hey, I just, I wanna make something to teach my kids the value of humility. Or it could be, Hey, I wanna fine tune my, drones to be really good at rescue situations. I could be vacuum robots. I want to like train [00:47:00] my manipulation or like vacuum robot to be very robust to my office, right?[00:47:04] But it's like, whatever it is, scenario robust to[00:47:06] swyx: my office[00:47:07] Fan-yun Sun: or like navigate very robustly in my office. But then it's like, whatever end goal that you want, our role model will say, okay, given what you want to achieve, let me generate a distribution of environments such that I can train and evaluate whatever it is you want.[00:47:24] Yeah. Right. Maybe for the purpose of games, it's just the end simulation and that's the end product for certain policies. It's like I can train it within these environments and then help you see where your policy is failing or not. Yeah. And then, so I think,[00:47:37] swyx: so in that case, much more of a training tool.[00:47:40] Than in other training[00:47:41] Vibhu: evaluation? Both. Right?[00:47:43] swyx: Sure. Same. Same thing.[00:47:43] Fan-yun Sun: Yeah, same thing. I think it's just this role model that allows people to train any policy that can act in any multimodal environments.[00:47:51] swyx: Would it be harder to reward hack? Is there an angle here where it is harder to reward hack? Like it's just, I'll just put it generally because I think that's a, that's obviously a key [00:48:00] problem that a lot of people face when in training agents in these environments, and I don't know, can you solve it?[00:48:07] Chris Manning: I think not necessarily. To the extent that there's a mis specified reward that. It seems like it could be hacked in a more symbolic world or in a more pixel based world. I dunno if Sun's got any thoughts, but I don't think that's really being solved.[00:48:26] swyx: The other thing that comes to mind is just you could just build a better sawa as a video generator model, right?[00:48:31] Because then you, you would move the diffusion, side a bit more further to the right. I think if I got the directionality correct. And that's it.[00:48:40] Vibhu: It's better on domains, right? Like on consistency over now, or for sure it exists versus something doesn't, right.[00:48:46] Chris Manning: So[00:48:46] swyx: yeah. Yeah. Is[00:48:49] Vibhu: is a question more like, like[00:48:51] swyx: I'm just riffing on like, how do you, what can you build, you know?[00:48:54] Oh, with the stuff that you have. I do think that the minor, the academic does go immediately to training [00:49:00] and in eval evaluation, but like art tends to take unusual directions. Like you might end up,[00:49:06] Chris Manning: okay. Yeah. But the question is, can you use this piece of software to develop compelling gameplay and. I don't think you can take SOAR and produce compelling gameplay, right?[00:49:19] If you want to have a world that you can wander around in a bit, you are good. But what are your abilities to have gameplay mechanics implemented the way you'd like them to be and to have things stay, with the long-term history of your gameplay that influences future actions. I think there's just nothing there for that.[00:49:39] swyx: Yeah, I do tend to agree. I, I'm just trying to sort of test the boundaries. I would also make the observation that as AAA games industry has developed the line between what is a movie and what is a game has blurred. And you, you, you do end up basically producing a two hour movie as part of your game.[00:49:57] Fan-yun Sun: No, honestly, there, there's so many actually [00:50:00] applications in adjacent markets that our world model can go into. Yeah. But yeah, it, it's sort of fun to riff, riff on. Although on the execution side, we we, we need to stay focused with like, okay, what are the capabilities we want to unlock over time?[00:50:11] And there's a roadmap for that. But yeah, if we're just riffing on sort of like the possibilities, I feel like, whether it's endless Yeah, it's like classic[00:50:18] swyx: and the embedding for a possibility and endless in my mind, it's very close. Yeah. I do wanna, focus on one, like weird choice. I, I don't know if it's weird.[00:50:28] Maybe I'm, I got something here. Audio, right? You could have just said no audio And audio in my mind has a lot of recursion, whereas in video you can just do recasting and that's much computationally much simpler. Audio just seems way harder. I don't know if you wanna just comment on just the special 3D audio.[00:50:46] Problem. Did you really have to do it? I guess you do to be immersive, but like a lot of people do treat it as like, well, you just stick a, a tt S model on top of[00:50:57] Vibhu: Well, there's a lot more to game audio than [00:51:00] just speech. Right. It's not just[00:51:01] swyx: tts. Yeah. Tts. S Fxt, GM Spatial in my mind Echoes[00:51:06] Chris Manning: Yeah.[00:51:06] swyx: And reflections.[00:51:07] And I, I don't even know what's, what else? I don't know what, what other problems in this space.[00:51:13] Fan-yun Sun: Yeah, I think this point like the, it's sort of a more, more pointing to the benefits of using an game engine as a tool that's available to the model, right? Because like part of the spatial audio is from the code that is underlying the simulation.[00:51:32] And while we do give our model access to other types of audio models as. Tools.[00:51:39] swyx: None of them would be spatial, I think.[00:51:41] Fan-yun Sun: But that's exactly sort of more 0.2. We're giving our model an abstraction or a suite of tools such that it's able to achieve that. And you can argue that sort of spatial is like a, like a emergence out of the, the tools that we and abstraction that we provide to the agents.[00:51:59] And I think that's the beauty of [00:52:00] this, this, this approach is like there's a lot of things kind of like how human's built technology and they're like Lego blocks that build on top of each other. And it's the same thing here. There's gonna be things that sort of just sort of emerges from being able to put these things together in like combinatorially interesting ways,[00:52:14] Chris Manning: right?[00:52:15] So this integrated audio model exploits the understanding and semantics of the Moon Lake world, right? And whereas in general for the Gen AI video models. There's no actual integration across to audio at all, right? That someone might stick some music or stick a soundscape or whatever else on top of their video.[00:52:44] So it's not a silent video, but they're in no way connected into a consistent world model. And there's nothing that's okay. An action is happening in the video. Therefore there should be a sound that's [00:53:00] coming from this part of the visual field.[00:53:03] swyx: Yeah.[00:53:03] Vibhu: Is that different than Sora too? Does it not have audio?[00:53:06] Not to say it's not like[00:53:08] swyx: amazing[00:53:08] Vibhu: isn't a spatial[00:53:09] swyx: audio.[00:53:09] Vibhu: It doesn't,[00:53:10] swyx: no. I've played around it with it enough. It just sounds like someone put an 11 laps voice on top of it and just tried to do the lip sync.[00:53:18] Vibhu: Oh, yeah. I've seen, okay. Generate a dog at the beach and reactions to big wave and move[00:53:23] swyx: around.[00:53:23] It's definitely like, so have the dog, have the dog move away from camera and see if the, the song goes down. It doesn't. ‘Cause they don't have facial audio.[00:53:32] Fan-yun Sun: We do want to basically like we, our moral model, like the one we're training is basically towards the goal of having a combined latent representation across all these different modalities.[00:53:42] Right? Such that it can like reason across these different modalities. So for example, if I close my eyes and like you play a video, you play a sound of like a car skidding away from me. I almost can like, visually extrapolate that trajectory in my mind. And I think that type of capability, we want our model to be able to reason, right?[00:53:59] And that's the reason that [00:54:00] we're sort of taking this multimodal reasoning approach. It's like we want this combine late in space that can[00:54:05] swyx: Yeah. Oh, you said late in space. We like that. Here we have to play the, the bell Every time that someone says late in space, no, you gotta train daredevil one. Where you, you, you, it's only audio, but you have to work out.[00:54:15] Where everything is.[00:54:19] Cool. I I think that that was, that was about it for our Moon Lake coverage. I do think that we have like a couple of, Chris Madden questions on, on IR and, just any, any other sort of attention topics or n NLP topics.[00:54:31] Vibhu: Okay.[00:54:31] swyx: Go ahead.[00:54:32] Chris Manning's Journey: From NLP to World Models[00:54:32] Vibhu: Well, no, I mean, yeah, it's just fun. We talked a bit about how you guys met, but you basically, you, you were like the godfather of NLP per se, right?[00:54:39] You spent the whole career from early embeddings, early early attention. You did 2015 attention for machine translation, everything. You, you had information retrieval, so RAG before rag, we just wanna shout that out and admire a lot of that. Right? So what prompted the switch over to world models?[00:54:56] How, how'd all that come about?[00:54:58] Chris Manning: To some answer it [00:55:00] is, the enthusiasms and creativity of students, but there's a bit of a history there, right? So, yeah. So clearly most of my career has been doing stuff with language and how I got into research was thinking, ah, this is just so amazing how humans can produce speech and understand each other in real time.[00:55:21] And somehow they managed to learn languages from their kids. How could this possibly happen? And so, yeah, starting off I was very focused on language, but as it sort of got into the 2000 and tens, I started, going, I'd been working on question answering, and then I started to get, interest in visual question answering.[00:55:42] And that was an area where it was very noticeable. That the visual understanding was bad. Right. These were the days when like, it sort of seemed like there's almost no visual [00:56:00] understanding. You were just getting answers that came from priors. So, if you asked how many people are sitting at the table, it'd always answer two regardless of how many, how many people you could see in the picture.[00:56:11] And so it seemed like, oh, these models actually aren't able to get semantic information outta

Der Große Preis von Japan hat die Vor- und Nachteile des neuen Formel-1-Reglements schonungslos offenbart. Ja, das Racing ist an und für sich besser als letztes Jahr gewesen. Engere Duelle, besseres Hinterherfahren, Überholmanöver auch an Stellen, an denen sonst nicht überholt wurde. Aber auf der anderen Seite steht eine entwertete Qualifikation, ein heftiger Unfall von Oliver Bearman und immer lauter werdende Kritik von Weltmeister Lando Norris & Co. an die FIA, dass nicht auf die Fahrer gehört wird. Kevin Scheuren und Dennis Lewandowski gehen die wichtigsten Punkte des Wochenendes in Suzuka nochmal durch, angefangen natürlich vom nächsten Sieg des Shootingstars Kimi Antonelli, ... WERBUNG Du möchtest ein Auto kaufen oder dein Auto verkaufen und vorher checken lassen? Schick carVertical deine Fahrzeugidentifikationsnummer und carVertical erstellt daraus einen Bericht. Einfach den Promotion-Code GRID20 eingeben und sofort 20 % auf den ersten Report sparen. Geh auf carVertical.de und probier es aus!Dieser Podcast wird vermarktet von der Podcastbude.www.podcastbu.de - Full-Service-Podcast-Agentur - Konzeption, Produktion, Vermarktung, Distribution und Hosting.Du möchtest deinen Podcast auch kostenlos hosten und damit Geld verdienen?Dann schaue auf www.kostenlos-hosten.de und informiere dich.Dort erhältst du alle Informationen zu unseren kostenlosen Podcast-Hosting-Angeboten. kostenlos-hosten.de ist ein Produkt der Podcastbude.

Once more unto the Harbour Bazaar as this month Steven Hastings & Davey Hal wonder how we got here and present a Solo themed show, with a focus on David Byrne and his triumphant recent live shows plus new music from Special Friend with new single Clipping on Skep Wax and friend of the Bazaar Julian Ball coming into to share the skinny of his new americana themed solo show ‘Sweethearts Of The Radio' Watch out! You might get what you're after PLAYLIST Pimples and Braces - Ric Gary Backwater - Brian Eno In Love - Prince The Jezebel Spirit - Brian Eno & David Byrne Life During Wartime - Talking Heads Heaven - Talking Heads Houses in Motion - Talking Heads My Apartment Is My Friend - David Byrne & Ghost Train Orchestra The Lonely One - Tom Jones Clipping - Special Friend I Just Can't Get Over Losing You - The Lemon Twigs Tattoo'd Lady  - Rory Gallagher Growing Up and I'm Fine - Mick Ronson Return of the Grievous Angel - Gram Parsons In Spite of Ourselves - John Prine & Iris DeMent Glass, Concrete & Stone - David Byrne We Three (My Echo, My Shadow, And Me) - The Ink Spots SHIP FULL OF BOMBS THAMES DELTA INDEPENDENT RADIO If you would like to support the station and are able to do so then please pledge only what you can genuinely afford at www.patreon.com/sfob Please like and subscribe from wherever you stream your music and podcasts.

In 2026, AI content is everywhere and trust is dropping fast — which is exactly why livestreaming is becoming the most underpriced move for independent artists.In this episode, we sit down with Courtney Knecht (GaryVee's official livestream producer) to break down the Indie Artist Livestreaming Blueprint: how to get started, which platforms to use, retention tactics that keep viewers locked in, and how to turn livestreaming into income + content + real fans.If you're an indie artist who wants deeper fans, more reach, and more revenue — this one's a must-watch.FREE ACCESS to "100 VIRAL CONTENT IDEAS FOR MUSICIANS": https://forms.gle/zGWuUrLA8mBfqz7F8JOIN OUR DISCORD:https://discord.gg/rTAYsPcyEYWANNA WORK WITH US? Make us an OFFER! https://forms.gle/tVdon5vyoGAqPjx6AGET 30% OFF DISTROKID:http://distrokid.com/vip/onemoretimeFOLLOW Courtney:https://www.instagram.com/knechtthedot/FOLLOW One More Time:https://www.instagram.com/onemoretime.fmhttps://www.tiktok.com/@onemoretime.fm0:00 Intro1:58 Meet Courtney + Cam Newton setup story4:02 Authenticity vs AI + the future of live6:47 Biggest streamers today + why it's still early10:16 What top 1% streamers do (show up as yourself)12:24 Consistency mindset: 10% beats 0%14:13 Planned vs freestyle + embracing “real” moments19:03 Retention hacks: names, chat, reset the room22:19 Sponsor: DistroKid23:09 Live shopping + TikTok affiliate basics29:42 The most slept-on platform for indie artists32:16 Start with your phone (Streamlabs + starter upgrades)35:17 What artists miss without live (real fan connection)38:11 Cadence: weekly lives + special events40:01 Top live formats for musicians44:14 Monetization masterclass: gifts, subs, gamification49:19 Leveraging the streamer ecosystem (gifted subs billboard)51:07 Bieber example + underpriced attention tactics54:17 Clipping pages + manufacturing distribution56:07 How to get booked on streams + streamers as press stops1:01:22 GaryVee lessons + forgiveness mindset1:09:48 Rapid Fire Rampage ft. Courtney Knecht

See omnystudio.com/listener for privacy information.

See omnystudio.com/listener for privacy information.

Pour la huitième édition, le Festival des Langues Françaises à Rouen propose de découvrir une quinzaine de nouveaux autrices et auteurs...et autant de manières de dire le monde. Durant quatre jours, ce festival met à l'honneur des textes, parmi lesquels ceux d'Aline César et d'Israël Nzila, lauréat du Prix Théâtre 2025. Ces textes sont lus devant des spectatrices et spectateurs, une première étape primordiale avant la mise en scène.  Reconnaissance : Damas de Aline César entre fiction et réalité Avec Reconnaissance : Damas, l'autrice Aline César raconte l'histoire d'une jeune femme abandonnée par ses parents, placée à la DDASS et à la recherche de ses origines entre les deux rives de la Méditerranée « Une autofiction entre fiction et réalité » sur le mode de l'enquête avec des choses réelles et d'autres qui sont fictionnées nous précise l'autrice. D'abord convaincue de ses origines algériennes, elle va découvrir qu'elle a également des origines syriennes. Elle va s'interroger sur l'histoire collective et se questionner sur les relations complexes qu'entretiennent ces trois pays, une histoire méconnue...  Son texte sera lu à Rouen devant un public : « C'est une étape de travail très importante. On confronte le texte aux spectateurs et aux spectatrices avec un propos aussi intime, quel est le ressenti du public ? » Elle a, elle même, mis en lecture son texte.  « Clipping » d'Israël Nzila, les traumatismes de la guerre « Clipping » est un mot technique qui évoque une distorsion sonore, une saturation des sons lorsqu'on dépasse le volume normal. Le texte « Clipping » d'Israël Nzila joue sur cette notion de distorsion et explore les traumatismes de la guerre. Le texte qui a remporté le Prix RFI Théâtre raconte l'histoire de Do, une femme dont l'enfance a été saccagée par la guerre. En errance sur un marché de Lubumbashi, en République Démocratique du Congo, elle affirme avoir perdu son bébé dans la foule mais est-ce la réalité ou une hallucination ? Est-elle folle ?  Israël Nzila a grandi à Lubumbashi. La guerre, il ne l'a vécue que de loin mais en a ressenti toutes les conséquences avec l'instabilité économique et les conflits politiques qui en ont découlé. Cette mise en espace de son texte lui permet d'éprouver les « souffles que j'ai mis dans les mots. Je voulais nommer cette violence avec la langue. La langue porte une histoire qui influence nos mentalités.»  « Le théâtre, c'est l'intimité partagée » C'est Anne-Sophie Pochet, metteuse en scène qui a effectué ce défrichage du texte « Clipping ». Ce n'est plus tout à fait une lecture ni tout à fait un spectacle. « C'est une specture : on est à mi-chemin entre spectacle et lecture », nous explique-t-elle. Pour elle, l'enjeu était de faire entendre au public la nature du texte et sa qualité littéraire, et faire resonner sa théâtralité. Invités :  - Israël Nzila, auteur congolais, lauréat du Prix RFI Théâtre 2025 pour sa pièce Clipping. Son texte sera lu au festival à Avignon le 15 juillet 2026 dans le cycle « Ça va, ça va le monde ! ». - Aline César, autrice, metteuse en scène, historienne de formation et chargée de cours à l'institut d'Études Théâtrales de Paris III « relier le passé à la lumière du présent ». - Anne-Sophie Pauchet, metteuse en scène et comédienne.  Le Festival des Langues françaises à Rouen jusqu'au samedi 28 mars 2026. Programmation musicale : l'artiste congolaise Céline Banza avec le titre « Fille parfaite ». Elle a été lauréate du Prix Découvertes en 2019. 

Pour la huitième édition, le Festival des Langues Françaises à Rouen propose de découvrir une quinzaine de nouveaux autrices et auteurs...et autant de manières de dire le monde. Durant quatre jours, ce festival met à l'honneur des textes, parmi lesquels ceux d'Aline César et d'Israël Nzila, lauréat du Prix Théâtre 2025. Ces textes sont lus devant des spectatrices et spectateurs, une première étape primordiale avant la mise en scène.  Reconnaissance : Damas de Aline César entre fiction et réalitéAvec Reconnaissance : Damas, l'autrice Aline César raconte l'histoire d'une jeune femme abandonnée par ses parents, placée à la DDASS et à la recherche de ses origines entre les deux rives de la Méditerranée "Une autofiction entre fiction et réalité sur le mode de l'enquête avec des choses réelles et d'autres qui sont fictionnées nous précise l'autrice. D'abord convaincue de ses origines algérienne, elle va découvrir qu'elle a également des origines Syrienne. Elle va s'interroger sur l'histoire collective et se questionner sur les relations complexes qu'entretiennent ces trois pays, une histoire méconnue... Son texte sera lu à Rouen devant un public : "C'est une étape de travail très importante, on confronte le texte aux spectateurices et avec un propos aussi intime, quel est le ressenti du public ?Elle a elle même mis en lecture son texte.  Clipping d'Israel Nzila, les traumatismes de la guerre "Clipping" est un mot technique qui évoque une distorsion sonore, une saturation des sons lorsqu'on dépasse le volume normal. Le texte Clipping d'Israël Nzila joue sur cette notion de distorsion et explore les traumatismes de la guerre. Le texte qui a remporté le Prix RFI Théâtre raconte l'histoire de Do, une femme dont l'enfance a été saccagée par la guerre. En errance sur un marché de Lubumbashi, en République Démocratique du Congo, elle affirme avoir perdu son bébé dans la foule mais est-ce la réalité ou une hallucination ? Est-elle folle ? Israël Nzila a grandi a Lubumbashi. La guerre, il ne l'a vécue que de loin mais en a ressenti toutes les conséquences avec l'instabilité économique et les conflits politiques qui en ont découlé.Cette mise en espace de son texte lui permet d'éprouver les souffles que j'ai mis dans les mots. Je voulais nommer cette violence avec la langue. La langue porte une histoire qui influence nos mentalité.  "Le théâtre, c'est l'intimité partagée"C'est Anne-Sophie Pochet, metteuse en scène qui a effectué ce défrichage du texte Clipping. Ce n'est plus tout à fait une lecture ni tout à fait un spectacle. C'est une specture : on est à mi chemin ente spectacle et lecture nous explique-t-elle. Pour elle, l'enjeu était de faire entendre au public la nature du texte et sa qualité littéraire, et faire resonner sa théâtralité   Invités : Israël Nzila, auteur congolais, lauréat du Prix RFI Théâtre 2025 pour sa pièce Clipping. Son texte sera lu au Festival à Avignon le 15 juillet prochain dans le cycle "Ca va, ça va le monde !" Aline César, autrice, metteuse en scène, historienne de formation et chargée de cours à l'Institut d'Etudes Théâtrales de Paris III "relier le passé à la lumière du présent".Anne-Sophie Pauchet, metteuse en scène et comédienne.  Le Festival des Langues françaises à Rouen jusqu'au samedi 28 mars. Programmation musicale : l'artiste congolaise Céline Banza avec le titre fille parfaite. Elle a été lauréate du Prix Découvertes en 2019. 

For patient referrals: call 602-521-3090What if one of the most overlooked heart valve conditions finally had a minimally invasive solution? In this episode of Beyond the Rounds, we explore tricuspid valve disease — often underdiagnosed and undertreated — and the emerging transcatheter therapies that are transforming care. Dr. Nolan Fisher sits down with interventional cardiologist Dr. Paul Sorajja to discuss how innovations like the TriClip procedure are improving quality of life for patients who previously had limited or high-risk treatment options.Often referred to as the “forgotten valve,” the tricuspid valve can quietly lead to significant symptoms, including fatigue, edema and organ dysfunction. With advances in catheter-based repair techniques, clinicians now have new tools to treat tricuspid regurgitation without open-heart surgery — offering meaningful symptom relief with low procedural risk.This episode explores how these therapies work, which patients may benefit, and how evolving data is shaping the future of valvular heart disease treatment.This episode is designed for physicians, advanced practice providers and clinicians seeking a practical understanding of transcatheter valve therapies and the management of tricuspid disease.What We Cover• Why tricuspid valve disease is frequently missed or undertreated• The difference between valve repair vs. replacement• How transcatheter therapies (like TriClip) work• Patient selection and when intervention is appropriate• The role of imaging and echocardiography in diagnosis• Understanding symptoms of tricuspid regurgitation• Cardiorenal syndrome and systemic effects of valve disease• Clinical trial insights, including the TRILUMINATE study• Why quality-of-life improvements matter — even without mortality benefit• The importance of a multidisciplinary “heart team” approachKey Topics for CliniciansTricuspid regurgitation (TR)Valvular heart diseaseStructural heart interventionsTranscatheter valve repairTriClip procedureCardiorenal syndromeRight-sided heart failureEchocardiography in valve diseaseInterventional cardiology innovationMultidisciplinary heart team careAbout Our GuestDr. Paul Sorajja is an interventional cardiologist and Director of Interventional Cardiology at Banner - University Medicine Heart Institute. He is a nationally recognized leader in structural heart disease and has been at the forefront of developing transcatheter valve therapies, including early work in tricuspid valve repair. Dr. Sorajja trained at Mayo Clinic, where he spent two decades advancing minimally invasive cardiovascular treatments and leading clinical research.He sees patients at:Banner - University Medicine Heart Institute755 East McDowell Road, Floor 4Phoenix, AZ 85006Banner Health Center plus at Arcadia4200 East Camelback Road, Suite 202Phoenix, AZ 85018Phone: 602-521-3090Fax: 602-521-3661How to Refer a PatientBanner Health providers: Use Cerner's Ambulatory Referral Management (ARM) tool.Community providers:Fax referrals to 602-521-3661 or call 602-521-3090 to schedule a patient for evaluation.DisclaimerThis podcast is intended for educational purposes only and is designed for a clinical audience. Any patient scenarios discussed are modified and de-identified to protect privacy. No protected health information (PHI) is disclosed. The information presented should not replace independent medical judgment or individualized patient care decisions.Subscribe to Beyond the Rounds for physician-focused conversations on clinical innovation, specialty collaboration and evolving standards of care.

El Gran Premio de Australia no solo abrió la temporada 2026… también nos dio el primer gran caso de estudio técnico del año.En Paddock Lab, Alex Escalera y Memo Rojas analizan a fondo lo que pasó en Melbourne: desde el fenómeno del clipping que afectó la velocidad punta de varios equipos, hasta la ventaja que encontró Scuderia Ferrari en la arrancada gracias a su configuración de turbo.La carrera tuvo más de 120 rebases, pero también dejó grandes preguntas: ¿fue un espectáculo real o un efecto del nuevo reglamento?Además, desmenuzamos el momento clave del domingo: el error estratégico de Ferrari durante el VSC. Con Charles Leclerc liderando la carrera y George Russell recuperando ritmo, la decisión de no entrar a pits terminó costándole más de 16 segundos y, posiblemente, la victoria.Telemetría, estrategia, energía, arranques y decisiones en pit wall… todo lo que definió la primera carrera del año, explicado a fondo en Paddock Lab.

Ok this one might be a litttttle late but better late than never right?! That's right your eyes don't deceive you, you are seeing a brand new episode of MBFRC after nearly a year and what better way to come back than counting down our individual top 10 albums of last year. Even if it's not very timely it just felt like the right place to start. So help us get this podcast ball rollin again by looking back at the incredible music that came out in 2025.Hosted on Ausha. See ausha.co/privacy-policy for more information.

Per the phenomenon in current-day Formula 1, Phil and Josh return for E306 of the GSP to discuss and recap all the major motorsports events of the weekend. IndyCar's recent race at Phoenix with a Penske Pole/Win sweep, Rasmussen's almost win, Palou's issues, and points recap heading to Arlington. NASCAR's Cup and O'Reilly Series results from Phoenix with another Penske Pole/Win sweep, tire issues, Gibbs team pit call gone wrong, and plenty of yellows; Justin Allgaier gets around Jesse Love late to give JRM two consecutive wins with both series heading to Las Vegas Formula 1's Australian Grand Prix showcased a spirited battle between Mercedes and Ferrari, but George Russell showed up when it counted for pole and a race win. Phil and Josh go through other major stories heading to Shanghai for the first sprint weekend of the season. Other racing series mentioned include Supercross, F2/F3, Supercars, and NHRA, WRC, Indy NXT and F1 Academy with their respective upcoming races and highlights. Race previews and picks for F1, IndyCar, and NASCAR - plus Josh's Sim Segment provide additional insights for listeners.

W 403. lekcji Kwadransu na angielski zostajemy przy tworzeniu nowych słów, ale tym razem będziemy odbcinać fragmenty wyrazów, aby otrzymać ich krótsze wersje. Dowiesz się takżę jak wyglądają pełne wersje wyrazów takich jak memo, demo, czy decaf i dlaczego fridge jest wyjątkowy.------Rozdziały--------(0:00) - Start(0:19) - Intro(1:01) - Rodzaje clippingu(2:47) - Budujemy skróty(10:52) - Rozwijamy skróty(17:39) - Outro----------------------Jeżeli doceniasz moją pracę nad podcastem, to zostań Patronem KNA dzięki stronie https://patronite.pl/kwadrans. Nie wiesz czym jest Patronite? Posłuchaj specjalnego odcinka: https://kwadransnaangielski.pl/wsparcieDołącz do naszej społeczności na stronie https://KwadransNaAngielski.plLekcji możesz słuchać na Spotify albo oglądać na YouTube.Wszystkie nowe wyrażenia z tej lekcji w formie pisemnej są dostępne na stronie https://kwadransnaangielski.pl/403#polskipodcast #kwadransnaangielski #angielski

Youtube video linked below!https://www.youtube.com/watch?v=ixElTKJaqq4Links & Socials here:https://linktr.ee/haleygutz

Youtube video linked below!https://www.youtube.com/watch?v=mrcHv5I_AlMLinks & Socials here:https://linktr.ee/haleygutz

Please welcome to A Year In Horror, special guest Jonathan Snipes from the band Clipping. He is also a composer of many a fine soundtrack. We talk about the 1983, superhero sequel Superman III. Does it deserve its jump the shark status, does it hold up? Let's find out. 

(00:00:00) Ted Hawkins - Watch Your Step / 1982 (00:28:36) Dinosaur Jr. - You're Living All Over Me / 1987 (01:02:23) clipping. - There Existed an Addiction to Blood / 2019

Mark Hamilton sits down to recap the first week of pre-season testing in Bahrain and talk about the latest news in the world of F1. Hit that subscribe button and tune in for the full, unfiltered breakdown! You don't wanna miss this!

Youtube video linked below!https://www.youtube.com/watch?v=h_T_hakJCJoLinks & Socials here:https://linktr.ee/haleygutz

On today's MJ Morning Show:MJ is disturbedTwisted Sister's Dee Snyder calls it quitsMorons in the newsMJ is still disturbedOlympicsCreepy MJ taking surreptitious photos The cat left in a couchNew iOs update Comments about Michelle on YouTube LiveCelebs using SEOFester's toenail clippings in the morning show officeMJ & Michelle headed to see Boy GeorgeGuthrie kidnapping updateMcDonald's employee tells customer to leave drive-thruMJ's take on "Landman"MJ went to the bluefin cuttingGrandma showersBailey's class went to a breweryMJ's disturbed feeling (again!)Home Depot sink displayHas fester gotten a new mattress yet? Listener wants to knowRed Lobster newsBest beaches this year from TripAdvisorMJ finally got an electric bill?Guy smashes wrong car in a parking lotSpicy chicken sandwich thrown during argumentBuffalo Wild Wings is allowed use 'boneless chicken wings' on their menuA dad found out his Amazon Echo was recording and storing Hard drive manufacturer says their supply is nearly sold out because of A.I.See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

William Layden is Co-founder and CEO at Rune, a company building modular, behind-the-meter micro data centers that plug directly into solar and wind plants. These units operate on a fully electric, DC-to-DC architecture—bypassing the traditional grid and unlocking new economics for compute at renewable energy sites.In this episode of Inevitable, Layden explains how solar clipping and curtailment leave vast amounts of clean power stranded—and how Rune's “RELIC” units turn that waste into usable compute. The conversation dives into DC architecture, Bitcoin as a beachhead market, and why traditional data centers are ill-suited to an era of distributed energy. Layden also unpacks why modular infrastructure may be the fastest path to deploying AI-scale compute at the edge of the energy transition.Episode recorded on Jan 27, 2026 (Published on Feb 17, 2026)In this episode we cover: (0:00) Intro(3:19) An overview of Rune(7:15) How energy flows and gets los in today's power stack(10:50) Clipping: the hidden inefficiency in solar(14:17) Curtailment: why the grid rejects clean energy(20:47) Starting with Bitcoin before scaling to AI workloads(25:50) Which compute loads can run interruptibly(27:26) Rune's business model and value to power producers(33:16) Where Rune operates and who's backing it(36:10) Why modular, DC-native design matters for scaleLinks:William Layden on LinkedIn: https://www.linkedin.com/in/william-laydenRune: https://www.rune.energy/ Enjoyed this episode? Please leave us a review! Share feedback or suggest future topics and guests at info@mcj.vc.Connect with MCJ:Cody Simms on LinkedInVisit mcj.vcSubscribe to the MCJ Newsletter*Editing and post-production work for this episode was provided by The Podcast Consultant

Etiquette, manners, and beyond! This week, Nick and Leah are enjoying a well-deserved break, but they'll be back next week with an all-new episode. In the meantime, here's one of their favorite episodes from the archives in which they answer listener questions about faking wedding start times, asking for gifts back, clipping nails in church, and much more. Please follow us! (We'd send you a hand-written thank you note if we could.)Have a question for us? Call or text (267) CALL-RBW or visit ask.wyrbw.comQUESTIONS FROM THE WILDERNESS:Is it rude to put a fake start time on a wedding invitation?What's the polite way to tell someone "when" to stop pouring wine?How do I politely decline someone's offer to share a hotel room?Is it OK to ask for a gift back after someone dies?What do you do if you only remember a dog's name but not the owner's?Etiquette Crime Report: Clipping nails in churchTHINGS MENTIONED DURING THE SHOWA "Standard Pour" of wineYOU ARE CORDIALLY INVITED TO...Support our show through PatreonSubscribe and rate us 5 stars on Apple PodcastsCall, text, or email us your questionsFollow us on Instagram, Facebook, and TwitterVisit our official websiteSign up for our newsletterBuy some fabulous official merchandiseCREDITSHosts: Nick Leighton & Leah BonnemaProducer & Editor: Nick LeightonTheme Music: Rob ParavonianADVERTISE ON OUR SHOWClick here for detailsTRANSCRIPTEpisode 227See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Youtube video linked below!https://www.youtube.com/watch?v=KAiZJxjzLaMLinks & Socials here:https://linktr.ee/haleygutz

HABLANDO ACELERAO, EN ESTE PODCAST TE PONDRÁS AL DÍA DE TODO LO QUE ESTÁ SUCEDIENDO EN LA FÓRMULA 1 Y MOTORSPORTS.Síguenos en instagram @puertoricoracingsportsBUSCA NUESTRA TIENDA www.prracingshop.com Busca nuestro website de noticias www.prrsnews.comModelos a escala www.topdiecaststore.comMercancia de F1 con @oteromotorsports Auspiciado por :High Category, los mejores productos para el cuidado de tu auto.Síguelos en instagram @highcategory#f1 #formula 1 #podcast

00.00.00: We Want Your C & B's 00.04.34: Wild Witnesses 00.13.19: Legendary Kid Saved His Family (+ When You Saved Yours) 00.20.04: Space Maaaaaaan 00.24.00: Rog v Creech at Clip and Climb 00.36.00: Reattaching Body Parts 00.46.19: More C & B's 00.48.19: Random Remedies 00.56.33: Stats Incredible

Youtube video linked below!https://www.youtube.com/watch?v=PWZ3MUlpMkkLinks & Socials here:https://linktr.ee/haleygutz

Eric of Landscape returns to chat about Noon...Moon??? Well, both! https://www.landscape.fm/moon KEANU Matrix Mixer Module: https://afterlateraudio.com/products/keanu Support Pod Mod PATREON (https://www.patreon.com/podularmodcast) LOUSY FALCON ALBUM: https://podularmodcast.bandcamp.com/album/forty-eight-feathers-a-collection-of-live-performances Thank you Novation: https://us.novationmusic.com/products/circuit-tracks# Signal Sounds: https://signalsounds.com/ Expert Sleepers: https://expert-sleepers.co.uk/ waveform magazine: https://waveformmagazine.com/

Jared opens Ticked Off Tuesday from Delray and immediately roasts himself for showing up to “the hottest restaurant in Delray” on Christmas Eve…only to realize his reservation was for January 1, 2026. He then spirals into beach-walk social awkwardness and floppy-hat groups refusing to go single file. The big vent is Delta, where he claims the airline hides his hard-earned upgrades in the app like a toxic partner gaslighting him about their “benefits.” Listener complaints bring the chaos: a hungover flyer forced to watch a seatmate bite and display nail clippings like tiny trophies, a university worker exhausted by parents doing adult kids' basic tasks, and a mother-in-law who treats dinner parties like an HGTV intervention. Overall, petty grievances, Florida sunshine, and Jared turning everyday annoyances into a full-on comedy sport!Jared is on tour!

THE BEST SHOW LIVE SHOWS APPROACH! And the Four Horseman reunite as a group once again. They discuss movies at length, Pat's story, and many other things. Experimental hip hop trio clipping. perform a blistering set in the Forever Dog Theater! They join Tom for a chat afterwards. Plenty of great calls from some heavy hitters as well as a few new folks. All in all, an absolute GREAT Best Show! The Best Show is celebrating 25 years with a live show extravaganza for the ages. Coming to NYC, Philly, LA, and Chicago this Fall!Tickets go on General Sale Friday July 18th at 10am local timeSat 10/11 - Brooklyn - Bell House ⁠⁠⁠⁠⁠⁠https://www.ticketmaster.com/event/300062ED179148EC⁠⁠⁠⁠⁠⁠Mon 10/13 - Philly - Union Transfer⁠⁠⁠⁠⁠⁠https://www.axs.com/events/1052919/the-best-show-tickets?skin=uniontransfer⁠⁠⁠⁠⁠⁠ Wed 10/15 - LA - Lodge Room⁠⁠⁠⁠⁠⁠https://www.lodgeroomhlp.com/shows/best-show-25th-anniversary-at-lodge-room⁠⁠⁠⁠⁠⁠Tues 10/21 - Chicago - Thalia Hall⁠⁠⁠⁠⁠⁠https://www.ticketweb.com/event/best-show-25th-anniversary-at-thalia-hall-tickets/13876034?pl=thalia3⁠⁠⁠⁠⁠⁠SUPPORT THE BEST SHOW ON PATREON! WEEKLY BONUS EPISODES & VIDEO EPISODES!⁠⁠⁠⁠⁠https://www.patreon.com/TheBestShow⁠⁠⁠⁠⁠WATCH THE BEST SHOW LIVE EVERY TUESDAY NIGHT 6PM PT ON TWITCH⁠⁠⁠⁠⁠https://www.twitch.tv/bestshow4life⁠⁠⁠⁠⁠FOLLOW THE BEST SHOW:⁠⁠⁠⁠⁠https://twitter.com/bestshow4life⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠https://instagram.com/bestshow4life⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠https://tiktok.com/@bestshow4life⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠https://www.youtube.com/bestshow4life⁠⁠⁠⁠⁠THE BEST SHOW IS A FOREVER DOG PODCAST⁠⁠⁠⁠⁠https://thebestshow.net⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠https://foreverdogpodcasts.com/podcasts/the-best-show⁠⁠⁠⁠⁠HEARD IT ON THE BEST SHOW PLAYLIST⁠⁠⁠⁠⁠https://open.spotify.com/playlist/2XIpICdeecaBIC2kBLUpKL?si=07ccc339d9d84267⁠⁠⁠⁠⁠See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.