Podcasts about Kosmo

This week's podcast is presented by Stephen and Jacquieline. We hear from: Witherspoon, with reflections on character development;Jo and John, wondering whether Helen or Pip is the more awful;And finally Katherine, feeling that the genetic testing storyline is dragging on a bit too long;We also have emails from Kosmo, Edna Cloud, David Moëd, Jane Brookbanks and Chris who is not in Indiana but on a train in New Mexico. As usual we will hear a roundup of the Dumteedum Facebook group, this week from Michelle, and the Tweets of the Week from Theo; plus the roundup of this Week in Ambridge, from Suey.Please call into the show using this link:www.speakpipe.com/dumteedum Or send us a voicenote via WhatsApp on: +44 7770 764 896 (07770 764 896 if in the UK) – Open the WhatsApp app, key in the number and click on the microphone icon. Or email us at dumteedum@mail.com How to leave a review on Apple podcasts: https://support.apple.com/en-gb/guide/podcasts/pod5facd9d70/mac***** The Patreon feed for Dumteedum is at www.patreon.com/DumteedumPodcast and the subscription rate is £5.00 per calendar month plus VAT. We recommend that you do not sign up to Patreon using the Patreon app, particularly on iPhones and iPads, as Apple appears to be imposing a 50% surcharge which goes to them, not us. The problem doesn't arise if you go to Patreon through a browser - even if you do this on an iPhone, and once you have signed up, you can still use the Patreon app to listen to the ad-free podcasts.***** Also Sprach Zarathustra licence Creative Commons ► Attribution 3.0 Unported ► CC BY 3.0https://creativecommons.org/licenses/..."You are free to use, remix, transform, and build upon the materialfor any purpose, even commercially. You must give appropriate credit." Conducted byPhilip Milman ► https://pmmusic.pro/ Funded ByLudwig ► / ludwigahgren Schlatt ► / jschlattlive COMPOSED BY / @officialphilman Hosted on Acast. See acast.com/privacy for more information.

Host Kosmo Esplan discusses the history of Northfield and Dundas baseball with Ira Carlson, Mike Allen, and Kevin Sevcik.

A soft focus, generative joy, and true freedom. Jonny Kosmo Jonny Kosmo- “In Stitches”- https://jonnykosmo-suncru.bandcamp.com "Jonny Kosmo is a songwriter, multi-instrumentalist, home recordist, licensed therapist, and the founder of the nonprofit counseling center and community art and music space Scribble in Highland Park, Los Angeles." Excerpt from https://jonnykosmo-suncru.bandcamp.com Jonny Kosmo: Bandcamp: https://jonnykosmo.bandcamp.com Instagram: @jonnykosmo Website: https://www.jonnykosmo.com Merch: https://gusbaldwin.bandcamp.com Records: https://jonnykosmo-suncru.bandcamp.com Scribble: Instagram: @scribble.community Website: https://www.scribblecommunity.com The Vineyard: Instagram: @thevineyardpodcast Website: https://www.thevineyardpodcast.com Youtube: https://www.youtube.com/@thevineyardpodcast

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

The world system (Kosmo's), have been deceived, it's influence tries to pull the people of God back into it by the flood that proceeds from the mouth of the serpent. Jesus warns us to be vigilant and watch that we be not deceived, the Apostle's also warned about the false teachers especially those that would be among us,

-

Et nach som er like crispy som en tortilla-chips! Kosmorama filmfestival har kommet og gått. Vi prater om alt som har skjedd og alle historiene vi har blitt fortalt under festen. Hva var bra? Var det noen partypoopers? Hva var festens midtpunkt? Var det oss? Lytt for høydepunkter, og takk for i år, Kosmo

Alvaro Orlando is a multifaceted filmmaker, actor, and dating coach whose work bridges entertainment and personal development. He wrote, directed, produced, and stars in the comedy feature film The Pickup Artist, a project directly inspired by his extensive real-world experience coaching individuals on dating, confidence-building, communication skills, and fostering genuine emotional connections. The film follows a hopeless romantic who, after a painful breakup, enrolls in a pick-up artist bootcamp—only to discover that such tactics may hinder authentic love. Through sharp humor, rapid pacing, and emotional candor, it critiques rigid modern dating “rules” while advocating for vulnerability, self-awareness, and authentic self-presentation.Orlando's authenticity in portraying dating dynamics stems from his background as a practicing dating and relationship coach. He has spent years guiding clients—both men and women—through challenges in attraction, interpersonal skills, and forming healthier relationships, often emphasizing practical strategies over superficial techniques. His coaching perspective informs the film's satirical take on pickup culture versus meaningful connection, positioning him as an insightful commentator on contemporary romance.As an actor, Orlando has built a credible career with roles in notable projects, including the Sundance-selected I Am Not a Hipster, the Lionsgate release Counterpunch (for which he received a Best Actor award at the 2013 Downtown L.A. Film Festival), and various television appearances. Earlier in his career, he gained public recognition by winning VH1's reality series The Pickup Artist (under the nickname “Kosmo”), an experience that highlighted his charismatic on-screen presence and quirky energy while engaging with dating-themed content.Currently, The Pickup Artist is scheduled for screenings at two festivals: the Golden State Film Festival (February 26 – March 6, 2026, at TCL Chinese Theatres 6) and the Hollywood Reel Independent Film Festival (March 4 – 14, 2026, at L.A. Live Regal Cinemas). Orlando's dual expertise makes him an engaging guest for segments exploring effective dating advice, the pitfalls of pickup artistry, modern masculinity and emotional honesty, red flags in early dating, and transforming personal experiences into comedic insight.

Mixed in London UK by IliasRo ARTISTS: Silver Panda & Ruback, Ruls, Sharon Gaziani, Halfreak,Metodi Hristov, Chriss Jay, Margarita Lahdou, KOBB , The Riddler, Cafius, Kosmo, Ginchy & DEADLINE, Balthazar & JackRock, Patrick Scuro, Roger Lavelle & YellowHeads, Veerus, Clif Jack, vasco UG, Woddy Wodpekker, Chris Drifter, MB Project, Sharon Graziani, RULS,

Host Kosmo Esplan talks with President Teddy Roosevelt, as impersonated by Adam Lindquist.

Host Kosmo Esplan talks with Sam Temple about the founding of Faribault, the city’s early history, and more.

Host Kosmo Esplan talks with St. Olaf Choir Director Dr. Anton Armstrong about the history of the St. Olaf Choir and his career with St. Olaf.

This week's podcast is presented by Stephen and Michelle We hear from: · Fiona, who is worried about a possible generational gap;· Tracy from California, who isn't very impressed with Susan; · Witherspoon, who sympathises with Henry;· Love Jazzer's Singing, who loved the scene in the Bull between Chris and Carly; · Glyn, who is hoping for conflict at the castle;· Natan from Portland, a first time caller-innerer, we think - who has really enjoyed this week; · and finally Globe-Trotting Richard, who starts with a defence of the bread delivery man; And we have emails from Kosmo and our Vicky. As usual we'll hear a roundup of the Dumteedum Facebook group, this week from Jacquieline, and the Tweets of the Week from Theo, plus the round up of this Week in Ambridge, from Suey. Please call into the show using this link:www.speakpipe.com/dumteedum Or send us a voicenote via WhatsApp on: +44 7770 764 896 (07770 764 896 if in the UK) – Open the WhatsApp app, key in the number and click on the microphone icon. Or email us at dumteedum@mail.com How to leave a review on Apple podcasts: https://support.apple.com/en-gb/guide/podcasts/pod5facd9d70/mac ***** The new Patreon feed for Dumteedum is at www.patreon.com/DumteedumPodcast and the subscription rate is £5.00 per calendar month plus VAT. ***** Also Sprach Zarathustra licence Creative Commons ► Attribution 3.0 Unported ► CC BY 3.0https://creativecommons.org/licenses/..."You are free to use, remix, transform, and build upon the materialfor any purpose, even commercially. You must give appropriate credit." Conducted byPhilip Milman ► https://pmmusic.pro/ Funded ByLudwig ► / ludwigahgren Schlatt ► / jschlattlive COMPOSED BY / @officialphilman Hosted on Acast. See acast.com/privacy for more information.

LEIVA, DUNCAN DHU, ESTOPA, AITANA, SFDK, LIA KALI, PROSPA, KOSMO KINT, PAUL KALKBRENNER, SANGUIJUELAS DEL GUADIANA y más Disfruta con 1 dosis diaria de Estación GNG, gracias a todos los que dia tras dia nos seguis dando vuestro apoyo bien en formato radio FM en directo ó bien escuchándonos en reposición en formato podcast. Cada dia sois más los que nos elegís en podcast y sólo podemos decir gracias de corazón por ello. Seguimos abiertos a vuestras sugerencias en el teléfono de la productora musical; 693938377. Envíanos tus mensajes y comentarios, cuéntanos desde donde nos sigues, nos encanta poneros y escuchar vuestras voces en el programa. PAZ Y MUSICA.

DAVID GAUSA presents SUTIL SENSATIONS RADIO / N#480 TRACKLIST OCTOBER 31st 2025 / 31 OCTUBRE 2025 THE 1st BLOCK Disclosure, Chris Lake + Leven Kali 'one2three' - Disorder RSquared 'Fantasy' - Defected Kolsch 'Nacht Und Traume' (taken from 'KINEMA' LP) - IPSO Kaz James 'On Fire' - Cercle Marsolo 'Spaceship' - Positiva Paul Kalkbrenner, Depeche Mode 'DREAMING ON' (taken from 'THE ESSENCE' LP) - Columbia / B1 Disclosure feat. Anderson .Paak 'NO CAP' - Disorder Honey Dijon feat. Chloe Bailey 'The Nightlife' - SOS TRACK OF THE WEEK / TEMA DE LA SEMANA Prospa ft. Kosmo Kint 'Love Songs' - CircoLoco Records 100% CLUB TRACKS Supernova 'Kayomusique' (taken from 'Got Some Lovin' EP) - Deeperfect TSHA 'Revolution' - Jackfruit Sam Shure 'Manifest' - TAU Locky & Luke Dean 'Supa Smoov' - Dance Traxx LDN CHASEWEST 'Scream!' - Solid Grooves Max Styler 'You & Me' - Nu Moda THE LAIDBACK ROOM / LA SALA 2 Fred Again.., Caribou, Menor Teteu 'Facilita' - Atlantic Records UK Makez feat. Ben Westbeech & Obi Franky 'REARRANGE YOURSELF' (taken from 'Arriving Home Elsewhere' LP) - NO ART DAVID GAUSA IN THE MIX: #CANELAFINA TAKEOVER Benja, Franc Fala 'Colombian Shipment' - Siamese Sharam 'Get Wild' (Andrea Oliva & Jaquet Remix) - All I Need Colyn, Read the News 'See the Light' - belonging Nic Fanciulli 'Lalo's Groove' (Marco Carola Edit) - Saved Frankey & Sandrino 'Please' (Echonomist Remix) - Rekids Christian Nielsen, Pavel Petrov 'Blame' (taken from 'Four To The Floor 46' VA/EP) - Diynamic Kevin de Vries & Jast 'Born Like That' - Afterlife THE CLASSIC / EL CLASICO Kim English 'Nitelife' (Masters At Work 1994 Nite Mix) - Nervous --- If you want to know more about DAVID GAUSA, visit: Si quieres saber mas de DAVID GAUSA, visita: http://www.davidgausa.com http://instagram.com/davidgausa http://www.facebook.com/davidgausa http://twitter.com/davidgausa http://soundcloud.com/davidgausa http://www.mixcloud.com/davidgausa http://www.youtube.com/davidgausa http://www.sutilrecords.com http://www.facebook.com/sutilrecords

Host Kosmo Esplan talks with former Northfield Raiders Football Head Coach and current Offensive Coordinator Bubba Sullivan about the history of Northfield Raiders Football.

Hvordan får man hverdagsmiddagen til at fungere, når ulvetimen ruller ind, behovene er mange og sanserne står på vid gab? I denne panelsnak sætter vi spot på middagsmåltidet i børnefamilien. Vi snakker om, hvad panelet selv er vokset op med, hvad de har taget med videre, og hvilke rutiner de selv har skabt - eller forsøger at skabe omkring måltidet. Vi taler om at balancere forventningerne, om arbejdsfordelingen i køkkenet, og om hvilke ingredienser, der skal til, for at middagen kan blive en hyggelig stund og et mødested for familien - også på dage, hvor det går stærkt. Vores panel består af: Kogebogsforfatter Helene Plett-Forchammer, mor til Dannie 3 år og Kosmo 1 år. Jurist og journalist Julie Teglhus, mor til Holger 8, Helmut på 4 og Fernanda på 1 år. Leder af formidling Katrine Nør Andersen, mor til Aksel Bille på 6 og Ejner Bror på 1 år. Rabatten på 10% hos Lalandia gælder ved ophold i perioden 09.10-20.10.2025 og kun for nye bookinger foretaget direkte hos Lalandia i perioden 22.09-05.10.2025. Kampagnekoden Moon10 skal oplyses ved booking, og rabatten kan ikke kombineres med andre tilbud eller allerede indgåede lejemål.

✦ The late great Radcliffe Bailey was a painter, sculptor, and mixed media artist who produced work that was personal, global, beautiful, complex, and resonated in a way that stayed with you long after you'd seen it. He was a citizen of the world and Atlanta's own. On September 26, the Auburn Avenue Research Library will host a panel entitled "Southern Ground: The Legacy of Radcliffe Bailey and the Future of Black Southern Art." It's absolutely free, and there will be a discussion that honors Bailey's work and explores his enduring influence on contemporary Black Southern art. City Lights Collective Co-Host Jon Goode sat down with curator Karen Comer Lowe, who will be moderating the panel, and artist Shelia Pree Bright, who will sit on the panel, to discuss Bailey, his life, his art, his importance, and the upcoming panel. ✦ City Lights Collective member Shane Harrison spends his days at Arts ATL looking for cultural events to share with readers. He joins us weekly to share highlights, and today his mix includes The Atlanta Indian Film Festival and the Sweet Auburn Music Fest. ✦ ✦ Atlanta author Julie Olivia's new romance novel, "If It Makes You Happy," is described as Gilmore Girls meets the "Pumpkin Spice Café"—but a lot steamier. The slow-burn story is set in 1997 in the small town of Copper Run, Vermont, and tells the story of a recently divorced innkeeper and her new, seemingly perfect next-door neighbor. WABE arts reporter Summer Evans spoke with Olivia about this recent release. ✦ Visual artist and music enthusiast Kosmo Vinyl bought his first LP when he was nine and spent the next several decades immersed in music before beginning his professional career at London's pioneering indie label, "Stiff Records." In 1979, Kosmo started working exclusively with "The Clash" and stayed by their side until the punk icons disbanded in 1986. Over the years, Kosmo's record collection became legendary. In 2014, he began posting about his favorite releases on social media for his series, "Kosmo's Vinyl of the Week." In January, he began joining City Lights weekly to share the stories behind the records he treasures. ✦ Atlanta artist and puppet creator Chantelle Rytter is known for weaving magic into the streets of Atlanta. If you've ever been to the Atlanta Beltline Lantern Parade, then you've likely seen her in action. Here on the City Lights Collective, she covered our "Collective Joy" beat, talking about events that bring community together in the most beautiful, artistic, and sometimes quirky ways. On Saturday October 4, Rytter and the Krewe of the Grateful Gluttons will host "Where the Weird Things Are," an event that's set to transform the Old Fourth Ward Park. Now this isn't your typical parade — it's an entirely unique experience- a stationary "upside down parade" where giant mystical creatures come to life, and we get to parade around them. City Lights collective co-host Kim Drobes recently caught up with Rytter to learn more about the Collective Joy that awaits us on October 4.See omnystudio.com/listener for privacy information.

✦ The Out on Film festival has not only been a place where the diverse voices of the LGBTQ+ community can see themselves on the big screen, but it has also served as a safe haven, a place of education, and a family reunion. City Lights Collective co-host Jon Goode sat down with Festival Director Jim Farmer to discuss the origins of the event and what you can expect from Out on Film today. ✦ For the last several years, a tiny yet momentous structure has popped up on sites of significance throughout Atlanta, inviting visitors to step inside moments of history. Charmaine Minniefield's "Praise House" Project replicates gathering spaces of worship that glued Black communities together since the days of slavery and beyond. The next installation for "The Praise House" will be at South View Cemetery in Lakewood Heights on September 21. There, they will honor the victims of the 1906 Atlanta Race Massacre, an outburst of horrific violence that killed dozens of Black citizens. WABE arts reporter Summer Evans spoke with Minniefield about this new site of remembrance. ✦ City Lights Collective member Shane Harrison spends his days at Arts ATL looking for cultural events to share with readers. He joins us weekly to share highlights, and today his mix includes the latest in the "Off the Wall" film series and a look at this weekend's Japan Fest. ✦ Visual artist and music enthusiast Kosmo Vinyl bought his first LP when he was nine. He spent the next several decades immersed in music and began his professional career at London's pioneering indie label, "Stiff Records." In 1979, Kosmo started working exclusively with "The Clash," who were once billed as The Only Band That Matters, and stayed by their side until the punk icons disbanded in 1986. Over the years, Kosmo's record collection became legendary. In 2014, he began posting about his favorite releases on social media for his series, "Kosmo's Vinyl of the Week," and he joins us weekly to share the stories behind the records he treasures. This week, he tells us about Hoagy Carmichael's "Hong Kong Blues." ✦ Atlanta's own Improvement Movement has been making waves across the city and beyond with lush vocal harmonies, clever arrangements, and a sound that refuses to sit neatly in one genre. Now, they're bringing that energy to the main stage at this year's Shaky Knees Festival. City Lights Collective producer Josh Thane spoke with keyboardist Zach Pyles and drummer Tony Aparo from the band ahead of their upcoming Shakey Knees performance about how they came together, the influences behind their music, and what's next for this rising Atlanta favorite.See omnystudio.com/listener for privacy information.

✦ Atlanta Symphony Orchestra will perform a special one-night-only concert on Friday, September 19, and everything on the program is special. Superstar pianist Lang Lang will be the soloist for Beethoven's Majestic Emperor Concerto, and the internationally acclaimed conductor Gemma New will direct the ASO in two works by Mozart. WABE icon and City Lights Collective member Lois Reitzes recently spoke with New to discuss the exhilarating beauty of Beethoven's and Mozart's work. ✦ City Lights Collective member Shane Harrison spends his days at Arts ATL looking for cultural events to share with readers. He joins us weekly to share highlights, and today his mix includes the world premiere of Atlanta playwright Topher Payne's latest comedy, and four upcoming performances from the Atlanta Ballet at the Cobb Energy Performing Arts Centre. ✦ Atlanta's catching its annual case of mural mania once again with the upcoming Forward Warrior Festival. The all-day creative celebration is this Saturday, September 13, in Cabbagetown. Each year, the walls of Wylie Street, right by the Krog Street Tunnel, are transformed with works of new art. Atlanta artist Peter Ferrari founded the festival, and when he spoke with City Lights Collective co-host Kim Drobes, he discussed both the history and the future of community-driven events. ✦ Visual artist and music enthusiast Kosmo Vinyl bought his first LP when he was nine. He spent the next several decades immersed in music and began his professional career at London's pioneering indie label, "Stiff Records." In 1979, Kosmo started working exclusively with "The Clash," who were once billed as The Only Band That Matters, and stayed by their side until the punk icons disbanded in 1986. Over the years, Kosmo's record collection became legendary. In 2014, he began posting about his favorite releases on social media for his series, "Kosmo's Vinyl of the Week," and he joins us weekly to share the stories behind the records he treasures. Today, he shares the story behind the New Miles Davis Quintet's version of "Just Squeeze Me." ✦ Robert Frost once urged us to "take the road less traveled." Atlanta photographer Geo Gerard chose a different path—riding his bike along every road within the I-285 perimeter. From 2020 to 2022, he documented the journey, capturing everyday moments of awe, joy, and humor. The result is "All the Roads Taken," a new exhibit on view at Gallery 100 through September 25. WABE arts reporter Summer Evans spoke with Gerard about the project. ✦ Have you ever been curious about the people running in groups along the sidewalk or on the sidewalk or along the beltline? Well, City Lights Collective member and WABE Studios intern Oli Turner decided to lace up her sneakers and catch up with some of Atlanta's many run clubs. See omnystudio.com/listener for privacy information.

✦ Food is a story—its origins, makers, and how recipes travel globally. The series "ChefATL," produced by SCAD, explores the stories behind the foods that inspire Atlanta chefs. In collaboration with WABE, SCAD students spotlight Atlanta restaurateurs each episode. WABE arts reporter Summer Evans spoke with SCAD student Astrid Sims, and Dear and the Dove owner Terry Koval to learn more about the show, which involved over 100 students across nine different SCAD degree programs. ✦ Local music artists across genres are coming together for a festival that organizers say is "by Atlanta and for Atlanta." City Lights Collective Co-host Kim Drobes has more on this weekend's Mainline Music Festival. ✦ Each Friday, the Atlanta Contra Dance community comes together at the Decatur Recreational Center to experience the joy of dancing to live music. City Lights Collective member Gillian Anne Renault has more on this high-energy dance that has a low bar of entry. ✦ City Lights Collective member Shane Harrison spends his days as executive editor of ArtsATL looking for cultural events to share with readers. He joins us weekly to share highlights, and today his mix includes a breakdown of the Atlanta Contemporary Music Collective's season opener, a new exhibition at The Sun ATL, and the Brookhaven Porchfest. ✦ Visual artist and music enthusiast Kosmo Vinyl bought his first LP when he was nine. He spent the next several decades immersed in music and began his professional career at London's pioneering indie label, "Stiff Records." In 1979, Kosmo started working exclusively with "The Clash," who were once billed as "The Only Band That Matters," and remained by their side until the punk icons disbanded in 1986. Over the years, Kosmo's record collection became legendary. In 2014, he began posting about his favorite releases on social media as part of his series, "Kosmo's Vinyl of the Week," and he joins us weekly to share the stories behind the records he treasures. Today, he tells us the story behind Cornershop's "Brimful of Asha." ✦ Artist, illustrator, and educator Faith Ringgold showed us our world through the eyes of young children in every medium you can think of –books, paintings, drawings, sculptures, even quilts. She trained and has been widely honored in the fine art and academic circles of New York City. Ringgold worked as an art teacher in New York City public schools for decades, focusing her work on those exceptional children, who have remained her lifelong muse. Now, the High Museum is presenting the most comprehensive exhibition to date of Faith Ringgold's art, featuring pieces from her children's books, including never-before-seen works. Curator Andrew Westover took a moment to chat with City Lights Collective producer Josh Thane about this extensive collection, which is on view through October 12.See omnystudio.com/listener for privacy information.

Host Kosmo Esplan talks with Tim Freeland about the broader events surrounding the September 7th, 1876 bank raid in Northfield.

✦ Brunching in Atlanta is practically a sport, and many of us don't know how to play. There are strategies involved—arrive early to beat the rush of a crowd, or maybe you're a diner that prefers to make reservations. BUT in this economy, who has the money to drop $80 to $100 on breakfast food and drinks every weekend? In our new mini-series, "Brunchin' on a Budget," we look at several delicious AND affordable brunch spots in Atlanta. On today's installment of "Brunchin' on a Budget," WABE Arts Reporter Summer Evans heads to Memorial Drive to highlight Homegrown. ✦ City Lights Collective member Shane Harrison spends his days at Arts ATL looking for cultural events to share with readers. He joins us weekly to share highlights, and today his mix includes House in the Park, The Atlanta Black Theater Festival, and a preview of Dragon Con. ✦ Dee Dee Bridgewater embodies jazz. She takes jazz standards and makes them her own while being true to the original composition. This is something she's done before and since releasing her debut album in 1974. No stranger to Atlanta, Ms. Bridgewater returns to the Rialto Center for the Arts on September 6 to the delight of all. Ahead of her concert, City Lights Collective Co-Host Jon Goode sat down with Ms. Bridgewater to discuss her new album, her return to Atlanta, and to share a laugh or three. ✦ Get ready for some cinematic chaos, VHS Deathmatch is coming to Monday Night Garage on September 26th. Part screening, part comedy showdown, the event takes the best (and worst) of B-movie VHS tapes and pits them head-to-head for ultimate bragging rights. City Lights Collective producer Josh Thane spoke with organizer Kristopher Bolz about the madness audiences can expect at the Deathmatch. ✦ Kosmo Vinyl is a visual artist and lifelong music lover. He bought his first LP when he was just nine years old and went on to spend decades immersed in the world of music. He got his start at London's groundbreaking indie label Stiff Records, and in 1979, he began working exclusively with The Clash—staying with the band until they disbanded in 1986. Today, Kosmo's legendary record collection fuels his social media series Kosmo's Vinyl of the Week, and he joins us every Wednesday to share the stories behind the records he treasures. Today, he tells us the story behind Creedence Clearwater Revival's 1969 hit, "Born on the Bayou." ✦ Ebony magazine debuted in 1945 and quickly became an inspiring celebration of Black life, culture, and achievement. The monthly magazine thrived for over seven decades, and within its pages lived the iconic column, "Fashion Fair," created by Eunice W. Johnson. "Mrs. Johnson," as all reverently called her, is the subject of the children's book, "Miles of Style," Eunice W. Johnson and the Ebony Fashion Fair." The book is the first by Atlanta author Lisa D. Brathwaite, and when City Lights Collective co-host Kim Drobes spoke with the author last year, Brathwaite explained how she first learned about Mrs. Johnson.See omnystudio.com/listener for privacy information.

✦ Break out your Flux Capacitor because when this show hits 88 miles per hour, you're going to see some serious…. stuff. That's right, “Back to the Future, The Musical” is coming to the Fox Theater this September. Bob Gale, co-writer of the original movies who helped bring to life Marty McFly and Doc Brown, has adapted the story for the stage, giving these beloved characters a whole new dimension. City Lights Collective producer Josh Thane sat down with Gale, along with Atlanta native and cast member Cartreze Tucker, to talk about translating this cinematic classic into live theater magic. ✦ Quilting has a long, rich history that crosses many different cultures and eras. For African Americans, creating quilts served not only as a means of survival and communication but also as a tool to share stories and showcase their artistry. O.V. Brantly created the Atlanta Quilt Festival 17 years ago to preserve and promote African American quilting and textile art. The juried exhibition has grown to over 100 quilts on display at the Southwest Arts Center and is on view through September 6. WABE arts reporter Summer Evans went down to check out these vibrant pieces of artwork. ✦ City Lights Collective member Shane Harrison spends his days at ArtsATL looking for cultural events to share with readers. He joins us weekly to share highlights, and today his mix includes The Weeknd at Mercedes-Benz Stadium, A Strange Loop at Actor's Express, and two shows that highlight the silver screen at The Booth Western Art Museum. ✦ Visual artist and music enthusiast Kosmo Vinyl bought his first LP when he was nine. He spent the next several decades immersed in music and began his professional career at London's pioneering indie label, "Stiff Records." In 1979, Kosmo started working exclusively with "The Clash," who were once billed as The Only Band That Matters, and stayed by their side until the punk icons disbanded in 1986. Over the years, Kosmo's record collection became legendary. In 2014, he began posting about his favorite releases on social media for his series, "Kosmo's Vinyl of the Week," and he joins us weekly to share the stories behind the records he treasures. This week, he shares the story behind "Roadrunner" from The Modern Lovers. ✦ Known for his vibrant, retro-inspired illustrations, Atlanta-based artist Derek Yaniger's work is a delightful blend of mid-century modern aesthetics, vintage comic book style, and rock 'n' roll culture. His art often features bold lines, striking colors, and a playful sense of nostalgia, making him a standout in the world of contemporary illustration. Yaniger's journey has taken him through a variety of creative industries, from ad agencies to Marvel comics to Cartoon Network. He has a special place in his heart for Atlanta's pop culture convention Dragon Con and has collaborated on artwork that combined the ethos of the convention with his signature style. You can see Derek and his art next week in the Comic and Pop Artist Alley at Dragon Con, and he recently joined City Lights Collective Co-host Kim Drobes to discuss his artistic process, influences, and his attachment to our city's longest-running fan-based convention.See omnystudio.com/listener for privacy information.

✦ Once a month in Grant Park, there is a night of music where community appears, and genres disappear. A night where no one, not even the musicians, knows what's going to be played. Collaboration and discovery are the name of the game when The Biological Misfits are on the bandstand. The Biological Misfits were put together by Craig M Garrett and featured the late great Malcolm Jamal Warner on bass. City Lights Collective Co-Host Jon Goode sat down with Craig to discuss music, community, and, of course, Malcolm. ✦ After raising 27 million dollars, Fernbank Museum of Natural History is set to embark on a two-year transformation, the biggest since it opened over 30 years ago. WABE arts reporter Summer Evans has the story. ✦ What do you dream of when you dream? That line comes up multiple times in Atlanta-based author Van Jensen's novel, "Godfall." And the answer, well, if you're Jensen, you dream of a unique story premise so compelling that it will start a bidding war for the TV rights. “Godfall” follows the story of David Blunt, the sheriff of a small Nebraska town during the time leading up to, and following, what should have been an extinction event – a miles-long object falling from space destined to crash into the Earth. That idea alone doesn't seem so unusual. However, when you discover what the gigantic object from outer space IS, then the book orbits into a world of its own. When City Lights Collective co-host Kim Drobes spoke with Jensen, the author explained how the idea for the novel originated. ✦ City Lights Collective member Shane Harrison spends his days at Arts ATL looking for cultural events to share with readers. He joins us weekly to share highlights, and today his mix includes surreal shadow puppetry and the Center for Puppetry Arts, Jimmie Vaughan of the Fabulous Thunderbirds, and some Canadian Comedy at Atlanta Symphony Hall. ✦ Visual artist and music enthusiast Kosmo Vinyl bought his first LP when he was nine. He spent the next several decades immersed in music and began his professional career at London's pioneering indie label, "Stiff Records." In 1979, Kosmo started working exclusively with "The Clash" and stayed by their side until the punk icons disbanded in 1986. Over the years, Kosmo's record collection became legendary. In 2014, he began posting about his favorite releases on social media for his series, "Kosmo's Vinyl of the Week," and he joins us weekly to share the stories behind the records he treasures. This week, he tells us the story behind The Elgins' "Put Yourself in My Place." ✦ If you're looking for a close-to-home adventure, you might consider the North Georgia Mountains. Karen Warren is a long-time journalist and resident of the area, and her book, "100 Things to Do in the North Georgia Mountains Before You Die," outlines places to visit, restaurants to try, and day trips to take. When WABE arts reporter Summer Evans spoke with the author, Warren explained the inspiration behind the book.See omnystudio.com/listener for privacy information.

✦ In good art, there is often beauty, offense, challenge, common ground, and that special little something that stays with you long after you've experienced it. When City Lights Collective co-host Jon Goode went to The Balzer theater to see the True Colors theater's presentation of "Ain't No Mo," by playwright Jordan E Cooper, he didn't know what he was in for but left knowing he'd just seen some good art. ✦ The 8th annual "Middle Age Cabaret: Cougar Club is a sizzling mix of burlesque, comedy, aerialists, and more. WABE arts reporter Summer Evans takes you to the cabaret. ✦ When thinking of foods that are deeply rooted in the American South, Grits might immediately come to mind. City Lights Collective members and food contributors Akila McConnel and Chef Asata Reid have the story behind the creamy porridge's history, AND how grits became a classic Atlantan dish. ✦ Alex "Cost One" Acosta lives at the intersection of art and community outreach. His non-profit organization, Soul Food Cypher, uses freestyle rap and lyricism as tools for empowerment. By showcasing the positive aspects of rap through cypher events and tournaments, the organization provides lyricists with a nurturing environment where their voice and artistry can grow. This year marks the 13th anniversary of their first freestyle cypher, and their next event is August 24, at Create ATL in Adair Park. When Soul Food Cypher founder Alex Acosta and Cypher member Rio Nkosi recently spoke with City Lights Collective Co-host Kim Drobes, Acosta painted a picture of a typical Cypher event. ✦ Visual artist and music enthusiast Kosmo Vinyl bought his first LP when he was nine. He spent the next several decades immersed in music and began his professional career at London's pioneering indie label, "Stiff Records." In 1979, Kosmo started working exclusively with "The Clash" and stayed by their side until the punk icons disbanded in 1986. Over the years, Kosmo's record collection became legendary. In 2014, he began posting about his favorite releases on social media for his series, "Kosmo's Vinyl of the Week," and he joins us weekly to share the stories behind the records he treasures. Today, he tells us the story behind X-Ray Spex's "Germ Free Adolescents." ✦ City Lights Collective member Shane Harrison spends his days at Arts ATL looking for cultural events to share with readers. He joins us weekly to share highlights, and today, his mix includes Monster-rama, The Black Martial Arts Cinema Double Feature at the Plaza, and a flute quartet at the Supermarket.See omnystudio.com/listener for privacy information.

Host Kosmo Esplan discusses the history of Northfield High School’s biennial production Rock & Roll Revival with Ray Coudret (director of the production since 2013), and Shari Setchell (choreographer since 2003).

✦ If you're looking for your next much-needed laugh, Atlanta comedian Joel Byars has plenty of them ready for you at his "Funny Fridays" comedy showcase. The next event in the series is scheduled for August 22 at the Sandy Springs Performing Arts Center and will feature performances by Lace Larrabee, Carlos Rodriguez, and Emily Holden. Byars recently joined WABE arts reporter Summer Evans to talk more about why he's committed to making our Fridays funny. ✦ Last May, when the pizzeria-arcade chain Chuck E. Cheese announced plans to retire its famous animatronic bands, the backlash was swift. After hearing this outcry, the company promised to keep a few of the bands across the nation. You may be surprised to hear that there was an outcry over Animatronics, but the art form, which brings mechanical and electronic figures to life, continues to hold the public's attention. In fact, the University of North Carolina School of the Arts offers a graduate concentration in Animatronics. It's true. If you're a fan of life-like, magical, moving figures with Dead Eyes (Jon's words, not mine), you don't have to travel far to get your fix. City Lights Collective member Wesley Boutilier brings us the story of a Six Flags Over Georgia ride that recently underwent a significant animatronic upgrade. ✦ Local artist Carl Janes knows that making art isn't a solo effort—it's as much about community as it is about creativity. Over the years, he has helped carve out spaces for Atlanta's local music and arts communities to gather, perform, and thrive—including his former East Atlanta home, The Secret Spot, and more recently, his location in Underground, called Inner Space. For his latest endeavor, he has teamed up with local brewery Halfway Crooks to curate a diverse Summer Sunday Concert series, which will run throughout August. City Lights Collective producer Josh Thane recently sat down with Janes learn why he's bringing his Inner Space outdoors. ✦ City Lights Collective member Shane Harrison spends his days at Arts ATL looking for cultural events to share with readers, and he joins us weekly to share highlights. Today, his mix includes Black Writers Weekend 2025, and True Colors Theatre Company's adaptation of Jordan E. Cooper's Ain’t No Mo’. ✦ Artist and music enthusiast, Kosmo Vinyl. He spent several decades immersed in music and began his professional career at London's pioneering indie label, "Stiff Records." In 1979, Kosmo started working exclusively with "The Clash" and stayed by their side until the punk icons disbanded in 1986. Over the years, Kosmo's record collection became legendary. In 2014, he began posting about his favorite releases on social media as part of his series, "Kosmo's Vinyl of the Week," and he joins us weekly to share the stories behind the records he treasures. Today, Kosmo discusses the story behind Ann Peebles’ “I Can’t Stand the Rain.” ✦ The game of Pinball has seen a resurgence in popularity over the last decade, and for those who love the game, August 1 is considered National Pinball Day. City Lights Collective co-host Kim Drobes brings us the story behind the celebration.See omnystudio.com/listener for privacy information.

✦ From street corners to collectors' closets, sneakers have become more than just footwear. They're currency, they're conversation starters, and they're Culture. In Atlanta, sneakers have found their way into exhibitions, college degrees, and even job opportunities. WABE arts reporter Summer Evans recently laced up to learn more about the billion-dollar industry behind the kicks that turn heads and spark hype. ✦ It's time to check in with our artistic community and hear from an artist in their own words. Today, we're catching up with poet Lauren Doriahna. She's an Atlanta lyricist, and she's here to share the rhyme and reason behind the art of language. ✦ City Lights Collective member Shane Harrison spends his days at Arts ATL looking for cultural events to share with readers. He joins us weekly to share highlights, and today, his mix includes a few options for Comedy and details on a 3-band show at the Garden Club with a few of Georgia's finest. ✦ Five Eight is playing the Garden Club with Magnapop, Anna Kramer, and Easy Now on Saturday. Five Eight emerged from the Athens scene in the late 1980s with live shows fans described as "brilliance bordering on a train wreck," delivered with frontman Mike Mantione's trademark honesty and immediacy. As mentioned, there's a documentary called "Weirdo: The Story of Five Eight," created by filmmaker and music journalist Marc Pilvinsky, which was filmed over a nine-year period. Ahead of the Five Eight show this Saturday, we listen back to Kim's 2024 conversation with Five Eight's Mike Mantione and documentarian Marc Pilvinsky. ✦ Artist and music enthusiast Kosmo Vinyl spent several decades immersed in music and began his professional career at London's pioneering indie label, "Stiff Records." In 1979, Kosmo started working exclusively with "The Clash" and stayed by their side until the punk icons disbanded in 1986. Over the years, Kosmo's record collection became legendary. In 2014, he began posting about his favorite releases on social media for his series, "Kosmo's Vinyl of the Week," and he joins us weekly to share the stories behind the records he treasures. Today, he tells us the story behind Them's version of "It's All Over Now, Baby Blue." ✦ In his YouTube documentary series "Our Voices, Our Lives," Atlanta-based filmmaker William Feagins Jr. shines a light on our city's creatives of color. The program has been running for 7 years, and City Lights Collective member Jacob Smulian recently spoke with the award-winning documentarian to learn more about the celebratory project.See omnystudio.com/listener for privacy information.

Host Kosmo Esplan discusses the history of the Northfield Vintage Band Festival with Artistic Director and Founder Dr. Paul Niemisto, President of the VBF Board Dan Bergeson, Vice President of the VBF Board Randy Ferguson, and VBF Board Secretary Joy Riggs.

✦ It's hard to believe that just a two-hour drive north of Atlanta, just past the end of 985 on Highway 441, brings you to a place where art, nature, and history converge in the most beautiful ways. City Lights Collective Member Zachary Brown recently hit the highway to learn more about the Hambidge Center. ✦ Atlanta's first-ever Halal Food Festival is coming to Atlantic Station on Saturday. Mouthwatering food such as tandoori chicken, shawarma sandwiches, kebabs, and gyros is just some of the cuisines being served by the over 80 vendors. ✦ What do you get when you mix sketch comedy, improv, and Georgia-grown talent with a dash of storytelling? That would be Sketchy Business ATL, a live showcase from Trilith Institute, the non-profit part of Trilith production studios. City Lights Collective producer Josh Thane sat down with event host Christian Noel alongside Trilith Institutes co-founder Jeffrey Stepakoff to find out more. ✦ WABE's Sounds Like ATL documentary series dives into the heart of Atlanta's music scene. Each week, it spotlights a local artist, sharing their creative process and a few live performances. You can catch new episodes every Wednesday on the YouTube channel, @WABE ATL. Today, we preview the recent episode with Uriel UMC. ✦ What will the world look like 100 years from now? This question about the future inspired artist T.W. Pilar and creative technologist Ivan Reyes to construct the exhibition "Technoterria," an immersive exhibit currently on view at the Georgia Tech Library. ✦ Visual artist and music enthusiast Kosmo Vinyl bought his first LP when he was nine. He spent the next several decades immersed in music and began his professional career at London's pioneering indie label, "Stiff Records." In 1979, Kosmo started working exclusively with "The Clash" and stayed by their side until the punk icons disbanded in 1986. Over the years, Kosmo's record collection became legendary. In 2014, he began posting about his favorite releases on social media for his series, "Kosmo's Vinyl of the Week," and today, he shares the history of Tom Waits' song, "Jockey Full of Bourbon." ✦ City Lights Collective member Shane Harrison spends his days at Arts ATL looking for cultural events to share with readers. He joins us weekly to share highlights, and today, his mix includes a Plazadrome event with former TCM 
Underground host and film historian Millie De Chirico, and a daytime dance party hosted by drag superstar Lady Bunny.See omnystudio.com/listener for privacy information.

✦ Summertime is officially upon us, and there’s nothing better to help cool you off on hot Atlanta days than ice cream. City Lights Collective food contributors Akila McConnel and Chef Asata Reid know this well, and they’re taking us back to 1870 to learn the history of ice cream in our city. ✦ Praised by jazz legends Ramsey Lewis and Les McCann, Atlanta jazz pianist Joe Alterman has never been a gatekeeper. He knows that jazz is for everyone, and it’s not rocket science – in the words of Duke Ellington, “If it sounds good, it is good.” Now, Joe Alterman is lending his voice, wisdom, and impeccable taste to WABE listeners with a brand-new radio show, “The Upside of Jazz,” with the first episode airing July 12th at 7pm. He’ll also be performing live at Eddie’s Attic on July 10th. ✦ City Lights Collective member Shane Harrison spends his days at Arts ATL looking for cultural events to share with readers. He joins us weekly to share highlights, and today, his mix includes things to do even if you’re not one of the three hundred thousand Atlantans heading to Mercedes-Benz Stadium for Beyoncé’s four-night stand. ✦ Visual artist and music enthusiast Kosmo Vinyl bought his first LP when he was nine. He spent the next several decades immersed in music and began his professional career at London’s pioneering indie label, "Stiff Records." In 1979 Kosmo started working exclusively with "The Clash" and stayed by their side until the punk icons disbanded in 1986. Over the years, Kosmo's record collection became legendary, and in 2014, he began posting about his favorite releases on social media for his series, "Kosmo's Vinyl of the Week," and he joins us weekly to share the stories behind the records he treasures. This week he shares the history behind Mongo Santamaria’s version of “Fever.” ✦ City Lights Collective co-host Jon Goode tells us about his recent visit to The Book Bird, an Avondale Estates nook, that sales physical books, and closes down so that you can open up. See omnystudio.com/listener for privacy information.

Host Kosmo Esplan discusses the history of the Riverwalk Market Fair with Market Fair Manager Derek Meyers, Riverwalk Market Fair Board Chair Martha Kasper, and local artist and longtime Riverwalk Market Fair vendor Kathy Miller.

Patří mezi vyhledávané autory a producenty a s jeho jménem jsou spojené třeba seriály Kosmo nebo Comeback. Jaký humor je mu blízký? A proč už se nechce pouštět do tvrdé satiry? Poslechněte si rozhovor s Tomášem Baldýnským v sérii Česká satira.

This week's podcast is presented by Jacqueline and Stephen. We hear from:· Witherspoon, who has never really liked Miranda;· and Claire from Clapham, who has really liked the silverback action this week; We also have emails from Kosmo and from Chris in Indiana.Plus a roundup of the Dumteedum Facebook group, this week coming from Michelle, the Tweets of the Week from Theo and the Week in Ambridge from Suey.Please call into the show using this link:www.speakpipe.com/dumteedum Or send us a voicenote via WhatsApp on: +44 7770 764 896 (07770 764 896 if in the UK) – Open the WhatsApp app, key in the number and click on the microphone icon.Or email us at dumteedum@mail.comHow to leave a review on Apple podcasts: https://support.apple.com/en-gb/guide/podcasts/pod5facd9d70/mac*****The new Patreon feed for Dumteedum is at www.patreon.com/DumteedumPodcast and the subscription rate is £5.00 per calendar month plus VAT. And don't forget to cancel your existing Patreon subscription if you have one, as we will continue to put the podcast out on that feed through February to give Patreons time to transfer over.*****Also Sprach Zarathustra licenceCreative Commons ► Attribution 3.0 Unported ► CC BY 3.0https://creativecommons.org/licenses/..."You are free to use, remix, transform, and build upon the materialfor any purpose, even commercially. You must give appropriate credit."Conducted byPhilip Milman ► https://pmmusic.pro/Funded ByLudwig ► / ludwigahgren Schlatt ► / jschlattlive COMPOSED BY / @officialphilman Hosted on Acast. See acast.com/privacy for more information.

Comedian Ali Siddiq joins us ahead of his Atlanta performance at the Fox Theatre on June 13. Plus, Kosmo Vinyl shares the story of Gill-Scott Heron’s version of “Me and the Devil,” and we listen back to Lois’s 2023 conversation with Metropolitan Museum of Art president Daniel H. Weiss about his book, “Why the Museum Matters.”See omnystudio.com/listener for privacy information.

Former First Lady of Atlanta Valerie Jackson reminisces about her time as a WABE host and shares some highlights from Mayor Maynard Jackson’s career. Plus, we hear from music enthusiast Kosmo Vinyl for “Kosmo’s Vinyl of the Week.” We also listen to Lois Reitzes’ conversation with Indigo Girls’ Emily Saliers as part of her “Farewell Favorites.” They discuss the Indigo Girls’ documentary “It’s Only Life After All.”See omnystudio.com/listener for privacy information.

Comedians and co-authors Amber Nash and Greg Tavares discuss their new book, "Improv for Couples: Fun Games for You and Your Partner." Plus, we hear about SCAD Fashion's 2025 runway show, and Kosmo Vinyl stops by with the story behind Tennessee Ernie Ford's "Sixteen Tons."See omnystudio.com/listener for privacy information.

Host Kosmo Esplan talks with local history buffs Susan Hvistendahl and Jeff Suave regarding their in-depth history of the St. Olaf Band founded on October 5, 1891.

Host Kosmo Esplan talks with Dr. Timothy Mahr who conducted the St, Olaf Band for 29 years.

 Host Kosmo Esplan talks with local history buffs Susan Hvistendahl and Jeff Suave regarding their in-depth history of the St. Olaf Band founded on October 5, 1891. 

 Host Kosmo Esplan talks with Dr. Timothy Mahr who conducted the St, Olaf Band for 29 years. 

John McCutcheon discusses his latest album “Field of Stars.” Plus, Kosmo Vinyl stops by with the story behind “Human Behavior” by Bjork, and voice actor and comedian Euguene Mirman stops by ahead of his upcoming stand-up show at Terminal West on May 3.See omnystudio.com/listener for privacy information.

Author Gene Kansas discusses his new book “Civil Sights: Sweet Auburn, a Journey through Atlanta’s National Treasure,” plus Kosmo Vinyl stops by with the story behind John Barry’s theme for “Midnight Cowboy.”See omnystudio.com/listener for privacy information.

Host Kosmo Esplan discusses the history of Northfield puppets and talks with former Northfield elementary school guidance counselor Doug “Puppet” Peterson, who used puppets to teach valuable lessons to students, along with his wife Mary Kay Peterson. The puppets are displayed at the Northfield History Center.

Among Beethoven’s concerto compositions, The Triple Concerto is the least often played work. Still, on April 3 and 4, the Atlanta Symphony will feature Beethoven’s Concerto for Violin, Cello, and Piano with Concertmaster David Coucheron, Acting Principal Cellist Daniel Laufer, and pianist Julie Coucheron. The trio of soloists joined Lois to discuss the upcoming concerts. Plus, the annual DIY FEST returns on April 3, spotlighting the Punk Rock Collection at Emory University’s Rose Library, and Kosmo Vinyl stops by to share the story behind Horace Andy’s “Skylarking.”See omnystudio.com/listener for privacy information.

Artist Amanda Williams details "We Say What Black This Is," the new exhibition at Spelman College Museum of Fine Art through May 24. Plus, Kosmo Vinyl shares the story behind Sandy Posey's 1966 hit, "Born a Woman. "Kim Sonderman, executive director of the Southeast Regional Sea Turtle Network, and film director Eleanor Church discuss the "Changing Tides Ocean Film Festival," coming to Georgia State's Cinefest Film Theatre on March 22.See omnystudio.com/listener for privacy information.

Meisa Salaita, Atlanta Science Festival co-founder and co-executive director, discusses the connections between art and science at this year’s festival, which runs from March 8-22 at various venues. Plus, Kosmo Vinyl tells us about Nina Simone’s “My Baby Just Cares for Me” for the latest installment of “Kosmo’s Vinyl of the Week,” and Karen Kelly, director of exhibits and education at the Children’s Museum of Atlanta, details “XOXO: An Exhibit about Love and Forgiveness,” on view through May 4.See omnystudio.com/listener for privacy information.

Joe Stephenson, director of the new film “Midas Man,” discusses the biopic, which screens as part of the Atlanta Jewish Film Festival on February 23, March 1, and March 3. Kosmo Vinyl talks about Everything but the Girl’s “Hatfield 1980,” DreTL details his time on the Netflix series, “Rhythm and Flow, plus we hear about “The Specific Stroll,” an analog immersive exhibit celebrating Edward Gorey on his 100th birthday,” which opens at Mother Lode ATL on February 22.See omnystudio.com/listener for privacy information.

Director Matt Torney and actor Andrew Benator discuss the Atlanta premiere production of “The Lehman Trilogy,” presented by Theatrical Outfit and the Bremen. The show opens today at the Balzer Theatre at Herren’s and runs through March 2. Jon Ludwig, former artistic director of the Center for Puppetry Arts, talks about the new Disney plus documentary “Jim Henson: Idea Man,” and Kosmo Vinyl stops by. Later, pianist and Ensemble Vim co-founder Choo Choo Hu and MOCA GA archivist and Director of Collections and Exhibitions Stacey Savatsky, detail the second annual “Spark” showcase at MOCA GA on February 10.See omnystudio.com/listener for privacy information.