Podcasts about sunoh

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

This video explores the ways in which a range of solutions from eClinicalWorks—including  eClinicalWorks healow Insights, their HEDIS module, their integrated AI assistant (Sunoh.ai), and their AI-powered healow Genie customer assistant—are easing clinical and administrative burdens.Esteban Gentle, Analyst at the multi-disciplinary Hendry Regional Medical Center in Clewiston, Florida, describes the challenges faced by modern medical institutions and how the eClinicalWorks and partner solutions address them.Learn more about Hendry Regional Medical Center: https://www.hrmc.us/Learn more about eClinicalWorks: https://www.eclinicalworks.com/Learn more about Sunoh.ai: https://sunoh.ai/Learn more about healow Genie: https://genie.healow.com/

Oak Orchard Health Center has been using the Sunoh.ai automated scribe, embedded with eClinicalWorks, for three months. In this interview, Chief Information Officer Jason Kuder describes results of a physician survey showing enthusiasm for the product.Pointing out that advances made in recent years by voice recognition, Kuder says that 100% of "providers love it" at the health center. Sixty percent of respondents to the survey are saving 1 to 5 minutes per encounter. Plus, they are more likely to close the notes in a timely fashion which has great downstream benefits from a revenue cycle perspective.Learn more about Oak Orchard Health Center: http://www.oakorchardhealth.org/Learn more about eClinicalWorks: https://www.eclinicalworks.com/Learn more about Sunoh.ai: https://sunoh.ai/Healthcare IT Community: https://www.healthcareittoday.com/

In this interview, Joao Fontoura, MD, Associate Medical Director and Director of Healthcare Informatics at Suncoast Community Health Centers, explains why their FQHC chose Sunoh.ai for their scribe, and how they won the clinicians over to use it.Located in Tampa, Florida, with a diverse population that includes many inner-city residents as well as migrant farmworkers, Suncoast was very price-conscious. Fontoura claimed that Sunoh.ai cost much less than other automated scribes. In addition, the integrations with eClinicalWorks clinched the deal.Learn more about Suncoast Community Health Centers: https://suncoast-chc.org/Learn more about eClinicalWorks: https://www.eclinicalworks.com/Learn more about Sunoh.ai: https://sunoh.ai/Healthcare IT Community: https://www.healthcareittoday.com/

Vous avez vu les mégalithes de Carnac, goûté le kouign-amann, dansé en fest-noz… Mais connaissez-vous l'incroyable histoire de la Bretagne ?Dans cet épisode, on remonte le fil du temps pour comprendre comment cette terre de traditions celtiques a su préserver son identité, malgré les conquêtes et l'uniformisation.Longtemps indépendante du royaume de France, la Bretagne a forgé un caractère unique. Découvrez cette histoire aussi riche que fascinante.***T'as qui en Histoire ? * : le podcast qui te fait aimer l'Histoire ?Pour rafraîchir ses connaissances, réviser le brevet, le bac, ses leçons, apprendre et découvrir des sujets d'Histoire (collège, lycée, université)***✉️ Contact: tasquienhistoire@gmail.com*** Sur les réseaux sociaux ***Instagram : @tasquienhistoireFacebook : https://www.facebook.com/TasQuiEnHistoireTwitter : @AsHistoire Tiktok : @tasquienhistoire *** Crédits sonores ***« Toute la Gaule est occupée par les Romains »Citation d'Astérix & Obélix: Mission Cléopâtre (Film d'Alain Chabat, 2002)https://shorturl.at/1cVhN « Roi de Bretagne, c'est pas une situation dégueulasse! »  (série Kaamelott d'Alexandre Astier)https://shorturl.at/uyT2u Asterix et les Vikings - Bande annonce@SNDhttps://www.youtube.com/watch?v=30q6OybaULg Le seigneur des anneaux : le retour du roi (Bande-annonce VF) (1mn07s)@LeSeigneurDesAnneauxhttps://www.youtube.com/watch?v=RCuDRcK0BBM « OK, puisqu'on peut pas discuter, on va faire un duel » (Extrait du film « La Classe américaine » de Michel Hazanavicius, 1993)https://shorturl.at/B3bep « Je suis le marquis de Pontcallec... » (Extrait du film « Que la fête commence » de Bertrand Tavernier, 1975)https://shorturl.at/Zy76f« Elle n'aura pas duré longtemps la république de Bretagne » (idem)https://shorturl.at/5S0fB Nantes: mobilisation monstre pour la réunification à la Bretagne@BFMTVhttps://www.youtube.com/watch?v=8uVIPsnowqw Musique de fin : SunoHébergé par Ausha. Visitez ausha.co/politique-de-confidentialite pour plus d'informations.

Central Virginia Health Services knows how crucial it is to automate tasks at scale. According to Kimberly Ferguson, Director of Clinical Operations, their community health centers treat one-third of all Virginia residents, some 46,000 users per year. In this video, Ferguson describes how the Sunoh.ai medical scribe helps their physicians become more productive, form more patient relationships, and reduce burn-out.One of the most interesting things Ferguson did when implementing Sunoh.ai was to leverage an after hours work report from their eClinicalWorks EHR.  This report more commonly known as the "pajama time" report showed when clinicians were working and what they were working on.  After-hours use ("pajama time") was very high when they began, and most of this overtime was spent entering documentation.  Ferguson and the team leveraged this report to identify who could benefit the most from Sunoh.ai.  Plus, they used it to track how after hours work changed after implementing Sunoh.ai.Learn more about Central Virginia Health Services: https://www.cvhsinc.org/Learn more about eClinicalWorks: https://www.eclinicalworks.com/Learn more about Sunoh.ai: https://sunoh.ai/Healthcare IT Community: https://www.healthcareittoday.com/

[SPONSORED] Are AI scribes living up to their hype? Is interoperability finally improving the lives of patients and clinicians? In this video, we dig into how ambient AI and real-world interoperability are giving clinicians time back, reducing documentation stress, and improving care with fewer clicks.Hear directly from Dr. Seth Eaton, Medical Director at MedPeds, as he shares how his team is using eClinicalWorks and tools like Sunoh.ai and healow PRISMA to solve major workflow pain points—without additional burden on staff. You'll learn how AI Scribes is helping catch things doctors miss and how one missed MRI detail led to better care.

Send us a textSPIRITUAL perspectives on current events and how MANIPULATING natural systems, the importance of balancing INTELLECT with INTUITION in decision-making, and the collective sensitivity to truth and resonance in spirituality. The conversation this week emphasizes the need for awareness and discernment in navigating complex issues. In this conversation, the speaker explores themes of empowerment, timing, and the spiritual aspects of personal growth. They discuss the importance of respecting the process of change, the role of emotions like anger in healing, and the significance of service in finding fulfillment. The dialogue emphasizes the need for organization and awareness of personal boundaries while navigating group dynamics. The conversation culminates in an inspiring story of a 90-year-old woman dedicated to animal rescue, illustrating the profound impact of service and the importance of staying true to one's purpose.Season 1 Episode 19 of "...Discerning News."hosted by Teresa Shantz, Author and Podcast Host,  Tom Shantz, "The Spiritual Businessman" along with Tiger Coll, D.D., President, Wayshowers College (SM)."The thoughts and insights shared here are crafted solely to nurture your personal and spiritual evolution, serving as gentle suggestions and guiding lights.  By choosing to continue your journey with us, you embrace complete responsibility for your own growth, state of consciousness, and well being."Links to Stories:Dimming the Sunhttps://www.independent.co.uk/news/uk/home-news/block-sunlight-british-scientists-global-warming-b2740295.htmlCanadian Electionhttps://www.bbc.com/news/articles/cn4jd39g8y1o90 Year Old Saves over 10,000 Animalshttps://www.goodnewsnetwork.org/90-year-old-who-has-saved-over-10000-animals-at-sanctuary-has-Join Tom and I for our monthly Intuition NOW series. There is a FREE 90 minute version and our EXPANSION Experience focusing on one of your four psychic perceptions for a small investment. Find out when the next ones are happening here! Ready to FEEL more FREEDOM within? Access the FREE video series created by The Wayshowers College here!Support the showHi! I'm Teresa. I have created this podcast to support "unseen" aspects of your life. You can call this the spiritual side. The podcast offers interviews of authors, healers, and thought leaders, for a positive higher spiritual perspective. Including ourselves! Our mission is to stimulate your inner wisdom, meaning, and enthusiasm for your unique journey. My husband Tom and I are also certified Spiritual Educators, and Consultants, who help make spirituality practical. We work spiritual awareness and sensitivity in all areas of our life for positive living. Through TNT ( Teresa n' Tom :) SpiritWorks, we can help you tap into your own Inner Guidance system on a daily basis, create a healthy balance between Thought and Feeling, and discover a stronger connection between you and your personal Spirit Guides through your Inner and Outer communication system: your Four Spiritual Gifts. Unlock ways to make the spiritual part of life practical. Connect with us at TNT SpiritWorks today! Follow us on:

Trey Davis from Sun Life Health talks about power of Sunoh.ai in medical documentation. Learn how this AI technology captures diverse dialects with precision, enhancing the accuracy of medical records. Discover how Sunoh.ai is enhancing healthcare by saving providers valuable time and significantly improving patient communication.

Before we dove into their use of an AI medical scribe, I had to take a minute to talk about their Student Health Center's experience using eClinicalWorks as their EHR and how they leveraged it to address some of the unique challenges and opportunities that student health faces.  Hussain made a compelling case for the value that eClinicalWorks offered their college health organization. Also, I was happy that a student health center was embracing an AI medical scribe like Sunoh since student health can often be slow adopters of the latest technology.  That's why I was especially curious to learn why and how Hussain and his team decided to roll out Sunoh in their organization.  Plus, he shares with us his staff's inital reaction to Sunoh. Learn more about Indiana University Student Health Center: https://healthcenter.indiana.edu/index.html Learn more about eClinicalWorks: https://www.eclinicalworks.com/ Health IT Community: https://www.healthcareittoday.com/

One of the biggest announcements at the eClinicalWorks Annual Conference was the advancement of the Sunoh.ai medical scribe product that automates the creation of clinical notes for the clinician.  If you've followed us for a while, you know we're big fans of everything that's happening with AI Medical Scribes and the impact for good they can have on clinical documentation. Of course, while it is great to hear about AI medical scribes in general, it's always better to hear the first hand experience of actual medical practices that are using these products.  In this case, we sat down with Geli Brown, Senior Director of Quality Management at HHM Health, to talk about her organization's experience rolling out Sunoh to their clinicians.  Learn more about HHM Health: https://www.hhmhealth.org/ Learn more about Sunoh.ai: https://sunoh.ai/ Health IT Community: https://www.healthcareittoday.com/

One of the hottest topics in healthcare and particularly at the HIMSS 2024 conference is ambient clinical voice.  We haven't seen this much universal interest in a health IT product since the government offered $36 billion in stimulus money for EHR software.  However, this feels very different since healthcare organizations are evaluating ambient clinical voice solutions on their merit versus chasing government money.  They're doing this because the benefits of this technology are so impactful on doctors and patients. While at the conference, I had a chance to sit down with Saurabh Singh, VP of Sunoh, and Rakhee Langer, VP of Sunoh.ai, to learn more about how Sunoh.ai has progressed since we last did an overview video of their solution.  They share with us some interesting perspectives on how ambient listening is changing the healthcare landscape.  Plus, they share some great stories from their end users who are using the product including one where a doctor is able to get home early to their family.  These stories illustrate the impact of this solution. Learn more about Sunoh: https://sunoh.ai/ Healthcare IT Community: https://www.healthcareittoday.com/

According to Saurabh Singh, VP of Sunoh, the success of ambient clinical voice depends on much more than the accuracy of the recording. Sunoh "checks the boxes" when it comes to meeting the needs of physicians' workflows and differences. Sunoh's solution can take input from many different sources: mobile devices, and laptop or desktop computers. This makes it easy to deploy in different rooms and settings. At the end of a clinical session, Sunoh generates a structured note tailored to the EHR within 30 to 60 seconds. Note generation is fully automated. The doctor can edit the note manually or using voice detection, and the results are fully integrated into the EHR. (They currently support eClinicalWorks, but are working with other vendors to support more EHRs.) Learn more about Sunoh.ai: https://sunoh.ai/ Health IT Community: https://www.healthcareittoday.com/

This week we're traveling to South Korea to meet the characters of Love Alarm! Jo-Jo hides from her boyfriend, Hye-Yeong has a crush, and Sun-Oh moves home. Amy and Gina discuss Black Mirror, robot cars, and fanfiction. Follow us! Instagram: @notanotherteendrama Twitter: @teendramapod Amy: @foreveramyf Gina: @gina.pasquinelli

In this episode, Nas and Ori discuss the infamous “Love Alarm”. The ladies were divided on their thoughts which created many hilarious debates including if Sun-Oh and Jo-Jo's first kiss was romantic or cringey! They also discussed toxic male leads, the many plot holes in Season 2, and Ori shamelessly loving Season 1. . . . Timestamps: K-Catch Up (01:04), The Rundown (10:26), First Impressions (13:23), Main Characters Discussion (17:04), Swoonworthy Moments (31:00), Tearjerkers (37:20), CringeFest (41:22), Funny Moments (50:21), Hot Takes (51:40), Lessons Learned (1:03:42), Ratings and Rankings (1:07:11)

20220727 - Covid, Monkeypox, & The Sun, Oh My! by Kevin McCullough Radio

The versatile music composer, music producer, singer, lyricist Mikey McCleary, talks to Host Eva Bhatt about his musical journey till date, and his creative discipline. Besides his prolific work on soundtracks for ad-films, background scores and songs for Bollywood he is also well known for his re-interpretations of Bollywood classics under the stage name of The Bartender, most notably 'Khoya Khoya Chand' and 'Hawa Hawai' from Shaitan. Having worked as a music arranger on Lucky Ali's iconic albums , ‘Sifar' & ‘Sunoh', Mike McCleary talks about his work chemistry and learning from Lucky Ali, with whom he has collaborated, once again on ‘Intezaar'. He also talks about his experience of working with Ankur Tewari for ‘Jeene Mein Aaye Maza' in Gully Boy.  Write to the host - at eva.bhatt@9xmedia.in or Follow her on Instagram  @evabhattpodcast Facebook: 9XM.in  Twitter: @9XMHaqse  Instagram: 9XMIndia 

Lucky Ali, one of the most loved artists whose voice has defined Indian pop music and has captured the imagination of music lovers across generations & for decades, is on this episode, to share his heart out on music, life lessons, and ‘Intezaar', his latest offering for his fans! After his successful collaboration with renowned composer/producer & brother-in-law Mikey McCleary in albums like Sifar & Sunoh, the 'O Sanam' singer is back with a series of singles, starting with Intezaar. Known for his distinctive sound & soulful but strikingly simple ballad-style singing, as well as his elusiveness, Lucky Ali shares some of his personal experiences & tips for music lovers & aspiring artists. He also talks about some fond memories about his late father, the iconic comedian Mehmood!  Write to the host - at eva.bhatt@9xmedia.in or Follow her on Instagram  @evabhattpodcast Facebook: 9XM.in  Twitter: @9XMHaqse  Instagram: 9XMIndia 

True feelings are timeless and real feelings are price less . Remix ft - Rizwan Song - O Sanam Poetry Written by Rizwan VOICE - Rizwan Singer - Lucky Ali Album - Sunoh Follow - #Rizophobia #luckyali #osanam #sunoh Contact us on - rsaiyed@gmail.com

Dave Simonett - The Sun Oh Yeah

So Love Alarm (Season 2) has finally ended... So was it as good as Season 1? Was there any drama? Was it worth the watch or is it a wasted watch? We'll let you know all about Kim Jojo, Sun Oh, and Hye Yeong and that interesting love triangle. Join us while we give the deets and our tipsy opinions of the final two episodes. Catch Love Alarm Season 1 & 2 on Netflix. Twitter - 2SistasT TikTok - 2Sistas_n_Their_Dramas --- Support this podcast: https://podcasters.spotify.com/pod/show/2sistastheirdramas/support

So Love Alarm (Season 2) finally dropped... Welp... Seems like it could be a wasted watch folks. We'll let you know all about Kim Jojo, Sun Oh, and Hye Yeong and that interesting love triangle. Join us while we give the deets and our tipsy opinions of the next two episodes. Catch Love Alarm Season 1 & 2 on Netflix. Twitter - 2SistasT TikTok - 2Sistas_n_Their_Dramas --- Support this podcast: https://podcasters.spotify.com/pod/show/2sistastheirdramas/support

So Love Alarm (Season 2) finally dropped... Is it going to be as good as Season 1? What new drama will unfold? Will it be worth the watch or a wasted watch? We'll let you know all about Kim Jojo, Sun Oh, and Hye Yeong and that interesting love triangle. Join us while we give the deets and our tipsy opinions of the first two episodes. Catch Love Alarm Season 1 & 2 on Netflix. Twitter - 2SistasT TikTok - 2Sistas_n_Their_Dramas --- Support this podcast: https://podcasters.spotify.com/pod/show/2sistastheirdramas/support

Episode 144. For Valentine's Day, we watched season one of the Korean drama series Love Alarm. Jojo's high school is obsessed with a new app called Love Alarm that can read your feelings and "ring the alarm" of your crush whenever you come near them. Jojo doesn't need an app to tell her how she's feeling: she has a crush on the hottest boy in school, literal fashion model Sun-Oh, but may also be interested in Sun-Oh's best friend Hye-Jeong. As we follow these characters over four years, the world around them is still wondering who even developed Love Alarm and how it'll change how people love each other.The Whatnauts present The Review Show, a weekly book club style podcast for all sorts of pop culture. We cover a variety of genres and mediums — movies, TV shows, comics, anime, manga, audio dramas — picking out a specific piece of entertainment that we can cover in a week's time. Every episode, your intrepid co-hosts Kyle and Melissa dive into the media of the week (with a spoiler warning!), give recommendations, and take turns pitching the next topic. For one episode a month, we check in with continuing coverage on a longer title, like a full TV series or comics run, and follow it all the way to the end. Join us for fun discussions on a wild variety of entertainment you should know!Check out our other podcasts here, or wherever you get your podcasts. If video is more your thing, then check our YouTube channel. And if you like what we do, support us on Patreon to unlock early access to most of our podcasts as well as exclusive episodes and more. You can find us on Twitter and we would love to have you join us on our Discord server as well.

The Beatles stopped recording 50 years ago, Spiderman will still be shootin webs in the MCU, Amazon releases tons of new smart devices and getting stuck in a bathroom will divert a plane. Trending Beatles Abbey Road 50th Anniversary  September 26, 1969 Come Together Something Octopus’ Garden Here Comes the Sun Oh! Darling Last album recorded by the Beatles Let It Be was final LP released, but entirely recorded before 1969   Plot twist: Spider-Man is sticking with the MCU for at least two more films Marvel and Sony have made up and combined forces for 2 more films July 16, 2021 is the next installment  Spiderman can also appear in Marvel films now Interesting reason to divert a plane https://twitter.com/tompodolec/status/1177042955091271681     Funny tweet https://twitter.com/shashashasha/status/1176886711747526658 Funny, but… interesting.  Keyboard warriors rant?   Amazon Event   Echo Loop Discreetly vibrates for notifications Titanium ring  Essentially an entire Echo in miniature: inside the titanium frame are two microphones Invite Only $129   Echo Frames $180 Look very similar to Bose Frames  Allows Alexa smart assistant to operate on them Invite-only  Android phone only    Echo Buds Works with Alexa Feature Bose noise reduction technology They plan to have Alexa give specific directions through the buds later this year, how to get to Whole Foods, even down to a specific aisle where an item is 5 hours of battery off a single charge 20 hours total including the case  $129   Alexa Smart Oven Scan packages A combination of microwave, convection cooker, air fryer, and food warmer. “Scan to cook” feature on packages from wholefoods Bundling echo dot with it $249   Ring’s indoor camera  The Ring Indoor Cam is a new, smaller, and cheaper version of the Stick Up Cam. It’s intended to only be used indoors, and is only offered in a wired version, so it’s cheaper at $59.99   Echo Flex Smallest Echo device yet Plugs into outlets - contains microphone for Alexa connected commands $24 You can add on attachments like motion detector and night light for an extra $14   Eero Router setup in 10 minutes or less Dual Band Radio System and support for Eero Secure and Eero Secure Plus Premium Subscriptions Turn wifi off for specific devices or turning on Guest wifi for people coming over $99 or $249 for three pack   Echo Glow Smart lamp for kids Can blink in patterns or glow in campfire mode   Echo Studio High-End smart speaker Supports Dolby Atmos and 3D audio Most “Innovative Speaker” they have every built Aiming to provide Lossless music in the Amazon music streaming service     Celebrity voices  Samuel L. Jackson can be your new Alexa voice Yes there is an explicit version of his voice New multilingual modes for families that speak different languages in a single house New frustration AI, Alexa understands when you are getting frustrated when she can’t find something you are looking for.    6 Pack Pick Em’ CFB: Duke vs Virginia Tech // VT -2.5 Penn State vs Maryland // Penn State -7 NOPE Michigan vs Rutgers // Rutgers +28  Auburn vs Mississippi State // Auburn -10 Mississippi vs Alabama // MISS +38 Wisconsin vs Northwestern // WIS -24.5 NFL: BAL vs CLE // BAL -3.5 KC vs DET // KC -4.5 PIT vs CIN // PIT -3.5 MIN vs CHI // MIN +3  NYG vs WAS // NYG -2 IND vs OAK // IND -6 EPL: Liverpool vs Sheffield // Liverpool -275 Chelsea vs Brighton // Chelsea -230 Tottenham vs Southampton // Tottenham -230 Leicester City vs Newcastle United // Leicester City - 195

The Beatles stopped recording 50 years ago, Spiderman will still be shootin webs in the MCU, Amazon releases tons of new smart devices and getting stuck in a bathroom will divert a plane. Trending Beatles Abbey Road 50th Anniversary  September 26, 1969 Come Together Something Octopus’ Garden Here Comes the Sun Oh! Darling Last album recorded by the Beatles Let It Be was final LP released, but entirely recorded before 1969   Plot twist: Spider-Man is sticking with the MCU for at least two more films Marvel and Sony have made up and combined forces for 2 more films July 16, 2021 is the next installment  Spiderman can also appear in Marvel films now Interesting reason to divert a plane https://twitter.com/tompodolec/status/1177042955091271681     Funny tweet https://twitter.com/shashashasha/status/1176886711747526658 Funny, but… interesting.  Keyboard warriors rant?   Amazon Event   Echo Loop Discreetly vibrates for notifications Titanium ring  Essentially an entire Echo in miniature: inside the titanium frame are two microphones Invite Only $129   Echo Frames $180 Look very similar to Bose Frames  Allows Alexa smart assistant to operate on them Invite-only  Android phone only    Echo Buds Works with Alexa Feature Bose noise reduction technology They plan to have Alexa give specific directions through the buds later this year, how to get to Whole Foods, even down to a specific aisle where an item is 5 hours of battery off a single charge 20 hours total including the case  $129   Alexa Smart Oven Scan packages A combination of microwave, convection cooker, air fryer, and food warmer. “Scan to cook” feature on packages from wholefoods Bundling echo dot with it $249   Ring’s indoor camera  The Ring Indoor Cam is a new, smaller, and cheaper version of the Stick Up Cam. It’s intended to only be used indoors, and is only offered in a wired version, so it’s cheaper at $59.99   Echo Flex Smallest Echo device yet Plugs into outlets - contains microphone for Alexa connected commands $24 You can add on attachments like motion detector and night light for an extra $14   Eero Router setup in 10 minutes or less Dual Band Radio System and support for Eero Secure and Eero Secure Plus Premium Subscriptions Turn wifi off for specific devices or turning on Guest wifi for people coming over $99 or $249 for three pack   Echo Glow Smart lamp for kids Can blink in patterns or glow in campfire mode   Echo Studio High-End smart speaker Supports Dolby Atmos and 3D audio Most “Innovative Speaker” they have every built Aiming to provide Lossless music in the Amazon music streaming service     Celebrity voices  Samuel L. Jackson can be your new Alexa voice Yes there is an explicit version of his voice New multilingual modes for families that speak different languages in a single house New frustration AI, Alexa understands when you are getting frustrated when she can’t find something you are looking for.    6 Pack Pick Em’ CFB: Duke vs Virginia Tech // VT -2.5 Penn State vs Maryland // Penn State -7 NOPE Michigan vs Rutgers // Rutgers +28  Auburn vs Mississippi State // Auburn -10 Mississippi vs Alabama // MISS +38 Wisconsin vs Northwestern // WIS -24.5 NFL: BAL vs CLE // BAL -3.5 KC vs DET // KC -4.5 PIT vs CIN // PIT -3.5 MIN vs CHI // MIN +3  NYG vs WAS // NYG -2 IND vs OAK // IND -6 EPL: Liverpool vs Sheffield // Liverpool -275 Chelsea vs Brighton // Chelsea -230 Tottenham vs Southampton // Tottenham -230 Leicester City vs Newcastle United // Leicester City - 195

Ei Sun OH is a Senior Fellow at Singapore Institute of International Affairs and former Senior Fellow at the S. Rajaratnam School of International Studies, Nanyang Technological University, Singapore, where he researches on the political economy of Asia Pacific, and Southeast Asia’s interactions with China. Previously, Ei Sun served as Political Secretary to the Prime Minister of Malaysia. Ei Sun Oh believes that in Southeast Asia, the success of a business operation still depends on the state-of-the-art of politics. The political risk connected with electoral cycles, for instance, needs to be taken into consideration for businessmen that want to thrive in a difficult environment.

Andrew is BACK baby!!! We talk about ghosts, Europe, fun in the sun, and Seth is rude YET again. Enjoy!!! Please call or text us. 224-323-6956

Sunoh Radio is Edinburgh's first Asian radio station. Tonight from 6-8pm Mithilesh will play music and speak to a couple of the organisers of Dusherra 2018 which takes place on Sunday

10 - 15 - 17 - Sun - Oh The Blood Of Jesus by Pastor Darrell Morgan

In about a month’s time, add a few days, the BJP will complete three years in office at the centre. Three years is long enough for hidden agenda to assume concrete form. In taking stock, former finance minister P Chidambaram lists the things that have gone awry for the people of this country. In a dispassionate tone – shorn of political rhetoric - he identifies the single emotion that has come to grip people of India: fear. This is the emotion that is being stoked by storm troopers of the state. In executing a unilateral cultural text, these storm troopers are telling the people what to eat, what to talk, whom to marry and how to behave. How does one respond to a context like this? We especially want to thank Fr Richard Rego at St. Joseph's College Autonomous, Bangalore for accommodating Sunoh and enabling this podcast.

Harini Nagendra speaks to Sunoh on her latest book, Nature in the City, in which she traces the natural history of Bangalore and dispels many myths surrounding the name of Bengaluru.

We spoke to Albert Lichtblau at the oral history conference in Bangalore. He is from Vienna, Austria, and has followed the life of a working class Jewish family that fled to Kenya. He also shares with us an uplifting tale of a concentration camp survivor. Here he is in conversation with M K Shankar, Cofounder of Sunoh.

Another boisterous hour of music to show what little I've accomplished this month with my life. In jest though. Actually this month was exceedingly good in terms of what I've managed to do, school, work, etc are plodding along a staid course and I managed to do enough extracurricular math on the side to test out of math class and into math 206. Thrilling right?So on to the tunes. This month I want to highlight for your listening enjoyment my new favorite obscure band The Godz - a group hailing from NYC their infinitely weird take on music was unable to secure the necessary interest of times and the group has since faded to an odious obscurity. For my part in reviving this tragic tale I hereby swear to play too much of them for anyone who has actual taste in music. Also the last track has a bounty on it - $50 to the first person to name it and the artist. 01. Love - Stephanie Know WhoLove is back for another round with this frighteningly paranoid lovers perception of infidelity. Good times!02. 1910 Fruitgum Company - 1, 2, 3 Red LightSaccharine sweetness oozes around the doughy flesh tinged corners of this nearly unbearable pap. Nothing against the original artists - who as I understand it were actually rather accomplished set musicians later shoe horned by managers into the role of a late 60's easy-pop boy band for the interests of shear greed alone. This track, amazingly, is not the worst they have offer - no that would be the infamous "Simon Says" a song so mundanely trite I had forgotten I'd ever heard it until I listened to it again while doing research for this month.03. Human Beinz - Nobody but MeSo the sound of easy-pop done right? The Human Beinz and the machine staccato of drums that opens to the loose rising riffs of guitar capped on top by the melodic "No, No, No, No, No" vocals. Jangling it's way into your heart. 04. G.P. Chiti & S. Montori - Desperation and Money (Cindelic Records)60's Italian b-grade movie soundtracks kick just that much ass. 05. Jennifer Gentle - Take My HandAnother Italian act, by God but this one is good and - drum roll - contemporary to myself with an nicely kicking album with American distributor sub pop.06. Beck - We Dance Alone (acoustic)Recently recorded over at WXPN as a part of NPR backed World Cafe. A good listen to those who doubt song craft of this eclectic musician.07. The Godz - Lay in the SunOh man it doesn't get any further out than that. The perfect protopunk psychedelic sound.08. Thee Headcoats - All My Feelings DeniedMan there is a lot of noise going on in here - my apologies to anyone not entirely blinded by the sheer fire of the manic force that is Billy Childish.09. Johnny Pate - Can't Even Walk in the Park. Johnny Pate, a long lived and ranging career - there is more beneath the surface of this soundtrack than just the glittering funk one might expect. Beginning as a jazz bassist in the thirties by the forties he'd even cut his own Blue Note session. The fifties saw him break the Billboard top 20, playing tuba and setting up arrangements. This lead him to fame and success with Curtis Mayfield and B.B. King and finally landing a gig in Hollywood for the music production of "Shaft in Africa".10. Meri Wilson - Telephone ManOh shit - the CD BABY strikes again! Meri is still making music and it turns out that the Friendly Staff of CD Baby are pedaling her wares. I didn't find this till it was too late to put in the audio for the month. Apologies and excuses to all involved.11. Soft Machine w/ Hibuo AnemoneThey once lit the madness of the masses with swirling psychedelic sounds swaths and jazz ornamentation. Now they are just known as the nearly made its and also rans - a shame since they really had something else going on.12. Cat Empire - Two ShoesThis is the Year of Cat Empire - my prediction is the pods will leverage interest into the band that will then jettison them into the lower hundred of the Billboard and MRM. Did I totally miss them when they came to town? yes. Did my friend Andre actually do PR for the shows and try to get me to go by bringing over CDs and Posters? yep. Do I regret?I regret nothing. Well maybe a little.13. Nash - Aggregation Damn it all I can't find anything about these guys, a shame as they sound like they really bust out the kicks. Favorite line: "A child is Born / Where's He Born? / In the SUUUUUUUUN!"14. Moving Sidewalks - 99th FloorFuture ZZTop frontman lays down the Texas tracks and precedes Jimi Hendrix on stage? Hallucinatory terrain surly.15. Harry Nilsson - 1941Harry claims The Beatles were his fans. Well I guess that makes sense. There is a strong English story telling thread that the two groups share.16. The Majority - One ThirdThe problem here is not just obscurity but obscurity combined with common search terms. Yes searching for One Third Majority often pulls up references to democratic processes. 17. The Coasters - Down Home GirlA laid back cover with a funk dollop from the one and onlys. 18. Mystery Track - I don't even know. ARGH frustrated by the complete failure of my ability to know who the hell I am listening to - I hereby offer a $50 dollar bounty for the first person who can name this artist and song. Good song too.backing track - Le Fluer da Musique image from: Audiogalaxy (holy shit - Audiogalaxy! I thought they killed you)