Why Fei-Fei Li Is Betting on Spatial Intelligence

Key Takeaway

Apply the “spatial context” principle to any creative or operational project today: before generating options, capture the constraints that make the result coherent—reference images, measurements, sequence, location, and intended viewpoint. Then create from that shared context instead of issuing isolated prompts or instructions. The episode’s broader lesson is that useful AI is not merely fluent generation; it preserves the structure of the world, so outputs stay consistent, editable, and reusable across iterations.

Episode Overview

Martine Casado speaks with World Labs co-founders Fei-Fei Li, Justin Johnson, and Ben Mildenhall about Atlas, a world model designed around “new view prediction.” They explain how Atlas combines generative modeling with 3D reconstruction, using spatially grounded camera poses to create consistent views from sparse image inputs. The conversation also covers creative workflows, simulation for robotics, scaling laws, dynamics, and the path from static 3D scenes toward interactive 4D world models.

Full Transcript

Transcript of Why Fei-Fei Li Is Betting on Spatial Intelligence from A16Z. Auto-generated from episode audio; may contain minor errors.

On the path to spatial intelligence, generating pixels that are truly spatially contextualized and grounded, that is the very hard step that Atlas has taken. We know LLMs are built on next token prediction. We've seen video models as being built on next frame prediction. Atlas is really new view prediction. This is the real place where AI can actually unlock a ton of value for people in their process. We're seeing like 50, 100x reduction. There was a famous shot in the first Matrix movie where Neo is falling down.

They had hundreds of cameras viewing that angle on a green screen. On Atlas, we can do this with just three cameras. No studio capture, no green screen, no expensive calibration. No one has ever seen this result. When you set out to do this, did you know it was going to work? I was pretty sure. Each time we made the model bigger, and each time we trained it for longer, it got significantly better. Does that mean we're going to get 4D video? Can I go walk around?

Language models are built around predicting the next token. What happens when a model instead learns to predict the next view of the world? In this episode, Martine Casado sits down with World Lab's co-founders Fei-Fei Li, Justin Johnson, and Ben Mildenhall to discuss Atlas and the broader challenge of building AI that can reason about physical space. They explain how Atlas combines generation and 3D reconstruction, why the team chose new view prediction as its underlying primitive, and what they learned trying to scale an approach that hadn't been tested before.

They also get into what's still missing, including richer dynamics and interaction, and how world models could eventually connect simulation with robotics and planning. Underlying it all is a bigger hypothesis. Could new view prediction play a similar role for spatial intelligence that next token prediction has played for language? So big day yesterday, you launched a new frontier model, which has got amazing reception, which is still coming in. I think maybe a good way to structure this conversation, let's just talk about exactly what that was, and then we'll go back to history and work our way back up.

So maybe, Justin, you want to talk about what was launched yesterday, why it's significant. Yeah, so Atlas is our new next generation world model. It has three basic things. It can generate, reconstruct, and simulate the world. So within that, there's a couple different major capabilities. It has really good camera condition generation, so you can input an image together with a camera trajectory and steer the model and have it generate video frames for any perspective you want. It's really good at sparse 3D reconstruction. You can input one or multiple up to 100 frames that are views of the real world and use those to reconstruct the real world.

And that reconstruction can take the case either of novel video flying through the space or an explicit 3D reconstruction of the space. Then finally, it can be used for simulation. And for this, we show off these awesome bullet time videos, which got a lot of attention online. And then also robotic simulation. What's a bullet time video? A bullet time video. This comes from The Matrix. There was a famous shot in the first Matrix movie where Neo is like, Yeah, exactly. So and then remember in that famous shot, he's falling down.

It's in slow motion and the camera flies all the way around. The way that they did that shot is they had a ring of hundreds of cameras. So then he fell over in the studio. They had hundreds of cameras viewing that angle on a green screen. And then they use those hundreds and hundreds of cameras to make that famous shot in Matrix. But now with Atlas, we can do this with as few as three cameras. So no studio capture, no green screen, no expensive calibration. We can literally stick three iPhones on tripods, use these to take sort of a video of something happening, like someone shooting a basket, someone dropping a strawberry into a bowl of milk.

And then from those three iPhone videos, we can then reframe the shot and imagine like freeze time, have the camera fly in as the milk is splashing up and get these amazing frozen time views. And we can do this with just a couple of cameras. What is the simplest description of what Atlas does? What goes in and what comes out? Yeah, so one of the really core principles of Atlas, the most fundamental thing is it does new view prediction. And this is a really fundamental primitive that we think is super exciting, a super new primitive for base models that no one's ever done before.

So we know LLMs are built on next token prediction. We've seen video models as being built on next frame prediction. Atlas is really new view prediction. That given some number of views of a scene or a description of a scene, those go into what we call a spatial context that describes implicitly what is the world that we want to talk about. Then you can point a virtual camera at an arbitrary point in space and time and Atlas will understand what that world is supposed to look like from that position in space and time.

Ben, there are video models out there all claiming to be world models and all claiming to have novel views. Can you maybe tease apart more concretely how this is different from the myriad models that have come before? Yeah, I think what Justin was saying about the spatial context aspect is super important here. So there's many video models. A lot of video models actually got their claim to fame from their single image input or their start to last frame interpolation. Now we're starting to see models that can do this kind of omni-referencing with 20, 30, 50 images.

But what's key with Atlas is that it actually has a kind of like spatially grounded meaning to every frame you put into it. So it's not just an image that the model is going to interpret whatever way it wants or you can kind of try to argue with it in the text prompting and get it to do something specific. With Atlas, every image actually has an associated three-dimensional camera pose and that means that you can perform this task of reconstruction with an extremely high degree of precision.

So if we had four views of this room, one at each corner, you can put those into the model and then get an exact replication of everything you see in this room. And it's not going to guess what's in the other corner, like a relationship between things. It's just going to reproduce exactly what you give it. And you can also do that in a kind of creative or imaginative sense too. If you take two photos from different AI generations or real-world locations, you can actually position and stage those to build these kind of intentionally directed fly-throughs that are really governed by exactly the precise place that you put the content you want and where the camera is going to look and travel.

Which is very different, I think, than the kind of more slot machine effect you get of having to retry generations over and over with just that kind of higher level of text control you get with video models. Is this just kind of an obvious scaled-up version of a traditional video model or is it a new architecture? I think it's a pretty new thing for a couple different reasons. One that we talk about is it does both generation and reconstruction jointly in the same model. Like Ben was saying, this thing can take a couple views of this room and then reconstruct everything in this room exactly as you see it.

And historically, reconstruction has been its own subfield in computer vision with its own specialized task, its own specialized models. And generation is what all the text-to-video models are really good at, like all the big diffusion models we've seen in the last couple of years. And those are great for creative applications. I want to imagine something that's never been there before. But now with Atlas, for the first time, we're putting these two different parts of visual intelligence together in one model. So it can do both 3D reconstruction and generation together in one architecture.

So to do that, we had to make a couple changes. One is we had to make it multimodal from the start. So this thing natively works on text, it works on images, it works on videos. It also works on camera poses as a native input to the model, which I don't think anyone's ever done at the pre-training phase before. And it uses 3D as a native modality that it works on. So this thing from the beginning was designed to be natively multimodal in a way that no one else.

Sorry, I don't know this space super well. By 3D, is this like depth or models? What does that mean? Yeah, so the formulation we used so far is depth maps. So right now, when you have a frame that has a virtual camera telling its position in 3D space, that camera position and camera parameters are a native input to the model. And then attached to that camera position, you can have both RGB telling you what does that position in space look like? And you can have a depth map that tells you what is the spatial structure of that position in 3D space.

So then text, image, video, 3D cameras are these modalities that this thing all does jointly in a multimodal way. I want to add something because I think what Justin just said is actually so important. And also what Ben said that it's underappreciated. It's the first time we have a unification of pixel generation and pixel reconstruction. In the world of computer vision, this field has been around for more than half a century. Sitting here, having been in this field for decades, I cannot tell you how many PhD theses have been written on the problem of reconstruction or novel view synthesis.

And also, our field traditionally has multiple tracks. You go to a computer vision conference, you have the pixel generation track, you have some recognition track, and you have 3D reconstruction track. This is an elegant model that unifies the problem of reconstruction and generation by anchoring on the viewpoint estimation. And that's just incredibly powerful. Can we take a step back and then maybe you just fill something out? So when you started the company, I remember you saying you want to tackle spatial intelligence. And now we have this new model.

And so as a layperson, it feels very general to me. You've got an expert prediction, and this is next new view prediction. So you can get one set of views and you get a new view. Maybe you pencil out how this is a significant step to this general problem of spatial intelligence. Maybe by starting to describe what spatial intelligence is. Well, spatial intelligence eventually must enable us to both generate what the space is, reason within it, and being able to edit and interact within it. Now we can argue, is it 3D or 4D?

Ultimately, it's 4D with the time dimension. But even just 3D, these are the fundamental tasks that one has to do, or spatial intelligence has to enable. And then we talk about, with that, you can render, you can simulate, and you can plan actions. But to do that, a fundamental problem to solve is to understand the geometry and structure and the physics of the space. And I do believe Atlas is a significant step forward because now with every single frame, you can generate and estimate an important piece of information, which is the viewpoint, the camera pose.

And that is the most critical information one needs about the geometry of the space. And that can lead to all the emergent behaviors we see in the downstream of the model, which we showed in the blog. So on the path to spatial intelligence, generating pixels is definitely an early step, which we have seen with what you call gazillions of models. But generating pixels that are truly spatially contextualized and grounded is absolutely another major step. And that is the very hard step that Atlas has taken. We definitely have, you know, we can just keep going here, right?

Like there is the fourth dimension of time, which will bring in dynamics, and there is more higher fidelity simulation and delineation of the space. So this is part of the roadmap of spatial intelligence. Great, yeah. I mean, I definitely want to dig into where this is going. But first, maybe let's talk about getting here. How long has WorldLabs been in existence? Two and a half. Two and a half, yeah. And so you've actually released models before. So why don't you just jump right to Atlas? Great question.

It's so magic, right? Justin's team needs a lot of chips. Yeah, they need a lot of GPUs to actually scale this thing up. So last year we released our Marble world model, and that was the first kind of big major world model that we put out. That powers our current Marble product. And Marble is really cool. Marble can take images, it can take videos, it can take text prompts and use these to generate 3D worlds. But one of the biggest differences between Marble and Atlas is exactly what is that output modality?

So Marble was really focused on Gaussian splats as an output representation. So whatever you're inputting, it's going to output a 3D world, represent it as a Gaussian splat. And Gaussian splats are really useful, right? They're really nice, they're easy to render, they can render efficiently on mobile devices, on VR devices, they can interoperate with game engines, with simulation engines. So there's a lot of nice things about Gaussian splats. But, you know, I think that was kind of a bottleneck in the previous Marble model. So what we did with Atlas is redesign the thing a little bit.

And we realized that we need to bifurcate these modalities earlier and actually have all these modalities working in a more unified way in the model. So now with Atlas, the fundamental primitive is not, like, you could generate a Gaussian splat world. The fundamental primitive is, as we said, new view prediction. And that can generate RGB frames, that can generate 3D, and we can use those to generate beautiful Gaussian splat worlds when you need them. But we don't need to bottleneck our outputs through the Gaussian splats when we don't need to.

And that actually took a lot of, you know, blood, sweat and tears to understand, like, what are all the pros and cons of these different representations. That's one part of it. The other part is you've got to, like, climb the scaling ladder, right? You've got to, like, work your way up and, like, do smaller experiments, do smaller models, like, to build your conviction on what's going to work and what's going to scale. And there's, you know, if you could instantly know the right thing that's going to scale, you know, you should just do that.

But when we started the company, the world was a very different space. There was no scaling law of spatial intelligence. Right. So, like, when we started the company, like, the world was in a very different place. The tech was in a very different place. We had a lot of ambitions about where we wanted it to go. But it took a couple iterations for us to hit upon this formulation that we thought is actually, like, this is the one, this is the one that can scale up.

You know, Ben, you know, being the creator of Nerf and doing a lot of 3D and reconstruction, so it's not so obvious to me that, like, if you have multiple views, that you actually end up with a 3D thing. But, like, you've kind of, like, made a career of ending up with a 3D thing. So maybe talk a little bit about, like, kind of that step. Yeah, yeah. Yeah, I mean, as you said, I've spent many, many years of my career, the vast majority of my career, actually working on producing 3D things from images.

And it's actually something we talked about a lot early on in the company, even if, like, is this going to be the approach that produces 3D, right? Are we going to synthesize multiple views and then build 3D out of that? Are we going to try to go direct to 3D? Like, there's been a lot of uncertainty in the field around, like, which of those approaches kind of will win out or will kind of, like, reap the best advantages earlier on. But I did have a lot of conviction just from seeing the kind of power of what I would almost call the brute force scaling.

Scaling in a very, very, very small baby scale, not like a real model scaling, but the scaling of dense reconstruction that we had seen happening over the past three years before. So basically, we... Why is dense reconstruction dense? Yeah. Because I know we're going to talk about sparse, and I want to make sure that people understand what is dense and what is sparse. Yeah, so I think this is actually, even on the kind of, like, business and commercial side, I think been one of the challenges of productizing 3D reconstruction technology at a fundamental level, right?

People kind of don't, in a casual sense, like, you think I took three photos of this object or I took six photos of this room. Like, I look at the photos. I can understand in my mind, like, how those piece together. I can kind of fill in the gaps and get it. But there's just never been really any kind of recognition. reconciliation between those like really data-driven priors and then the kind of brute force dense reconstruction, which it actually is much more akin to almost like scientific or medical imaging what we did in dense reconstruction, right?

You basically have to say every single thing I want to appear in this reconstruction. I need at least three or four views of it. And if you think about that, like even just in this room, right? There's like under the microphone, under the table, between every different crack and crevice and the plant leaves, right? To actually truly get a picture that covers every one of those spots, it's just like very tedious and exhaustive effort to walk around the room. I think you've all seen me running around various places like capturing them.

It takes, you know, for someone who's well-trained per se, like it can take minutes. But if you hand a casual consumer or even some like kind of professional trying to do this for the first time, an average like cell phone camera or capture device, like it's going to take them probably an hour. I've seen someone for the first time trying to scan a multi-room environment, spend like two hours walking through it and get enough coverage. And that's just this like very, very exhaustive and tedious loop.

And so, yeah, when we say dense, we really mean dense. It's like this room. I mean, you're just doing like lots and lots of so many photos, right? I want like 100, 200, 300 photos of this room to capture it. And what we're trying to do is bring that down to like three, right? Well, we're saying like 50, 100x reduction. And then that's at that scale where it just completely like flips that calculus on its head of like what type of captures you reconstruct. You can go back to existing imagery you have.

You can go to stuff you find on the Internet and even build scenes out of that. You can go to casual videos and like kind of unearth a lot of footage in the past. We would never have treated as reconstructable and go back and like bring it to life as 3D potentially. This is something we've been playing around with a lot with Atlas, right? Like taking old clips, like I've taken a bunch of my own old captures that never worked before and then put them through the system and I kind of seen a reconstruction of the first time or taking my old captures and throwing away 95% of the photos I took.

And, you know, imagine angles that I never would have gotten from a traditional kind of like Nerf or Splat type reconstruction. One thing that's underappreciated on the website of the demos is the Stanford demo where Ben showed anywhere between three to twenty five images. You can reconstruct that entire Stanford quad. But the thing is, we had to show it from an aerial view. But every single input image is Ben standing on the ground taking a picture from the ground. So everything you see are generated, but according to the laws of reconstruction.

And this is really magical. And this is where like generation and reconstruction need to interplay in a really fundamental way to solve this problem. Because under the classic kind of reconstruction stuff that Ben was talking about, like the reason you need so many views is because I need like multiple images and I need to triangulate this point in 3D space and see it from multiple viewpoints. So that means like that's required in the traditional version. And on the flip side, anything that wasn't captured in these views, like any pixel that was not visible in one of the input views will be a hole in the 3D reconstruction.

Because fundamentally, like if a thing wasn't visible in the input views, you know, you need to imagine it to fill in the gaps. And that's fundamentally a generative process. So even in this room, even if we set Ben loose with a DSLR and like let him like capture like hundreds of views of this room, even the world expert on doing these dense captures is still going to miss some spots. Like he's not going to get like underneath all of the microphones or underneath all the tables or like in between all the chair legs.

You're always going to miss something, no matter how many views you get. So that's where you need generation as another mechanism in the model, because you're never going to get everything. So you need to have some generative capacity for the model to imagine, oh, based on what I'm seeing, then like first triangulate what I what I can see, but then fill in the gaps of the stuff that inevitably inevitably was not captured. Yeah, and there's something like super cool about this that LLMs have really understood this for a long time, right?

There was kind of almost these like context wars, like the first couple of years, it was like, oh, we got to 128, to 256, to like 512, we got a million, right? And everyone kind of understands now at a pretty tangible level, the value of, you know, you crank your context length to high when you're using your coding model, it's a hard problem. Like everyone has a feel for that. But like no one has pushed that at all on the image and video model side in the same kind of like principled way.

Like no one's out there trying to like put a like an hour long video through and do a needle in the haystack retrieval of like a frame at the 30, 37 minute mark. Whereas with reconstruction and generation, you actually have the same exact thing of like reconstruction. It's just like generation with a really long context and you put a lot of stuff in it. Yeah, right. Like that's the way to actually build a continuum where you kind of bridge between those two things. And like Atlas, like being able to like this is something we can never do with Marvel.

Marvel had this kind of fundamental blocker of like you couldn't really jam more than honestly like a couple images in. But Atlas, I can go and I can actually take like a 64 image capture and do like a fly through of an entire house and everything is grounded by being, you know, seen or like almost seen or like slightly extrapolated from what's not there. But you're just getting these, you know, I'm taking captures I did with 2000 images of a multi room house and taking it down to like 30, 40 inputs and the fly through looks like basically the same.

And this is just like totally inconceivable before. And it's all enabled by building this gracefully scaling kind of context window that you can dump stuff into. And so is the way to think about it is like the the sparseness are the pictures that you physically took. And then Atlas as a model creates the rest of the views. And then you use classic reconstruction techniques. Is that roughly the way to think about it? Or in some sense? Yeah, yeah. I mean, that's the beauty of Atlas. It's like you can take however many inputs you have down to like a single view and then you can almost use Atlas as this rendering engine to produce anything else you want.

Or you can you can navigate it. The virtual camera. Yeah, exactly. You can just you can say like, OK, I have a picture here. I want the picture there. They're there. You can make a couple of those. Then you can stage a dense fly through. You can do this in sequence because it's an autoregressive model. It's up to you, right, to kind of pick and choose what you add interactively into the context as you generate. I mean, the thing that I just blows my mind is, listen, I just have a very simple mental model.

I have four pictures and then I've got to like have the model extrapolate between them. And then it has to fit when you reconstruct, like it's got to be 3D. Because, yeah, like and I always think of these diffusion models as like being visually great, but not accurate. And so like and I don't even know if there's a question here, but like how is it like the room fits? Like how is it that it's 3D consistent? Is it just lots of data or? Yeah, I mean, it's a partially it's a belief in the scaling hypothesis, right?

Like, you know, did you? By the way, I have to ask, when you set out to do this, did you know it was going to work? I was pretty sure. That's so, so, OK. Were you sure? I think three of us have total conviction about the scaling law that that I think we do. I do think the exact architecture choices and data mixtures is where the devils are in the details. I have watched Justin and his team going from, we really don't know how long this is going to take to, oh, maybe sign of life to, wow, this is going to work.

So no one has done it. But I think the hypothesis, two hypotheses, one is scaling law hypothesis. The other one is next viewpoint prediction. We had conviction of these two things from early on. So I think I was very convicted that it was going to work. I was not sure it was going to work this well at this fast. Right. Like I thought there's a chance that we do this. Maybe it's not clear that like the first cycle of pre-training a new model with a new architecture, a new paradigm, like the first cycle of that working is insane.

So I thought there was a chance in which we had to we might have had to do a couple more turns of that pre-training cycle before we got to the level of quality we were we wanted. Is there is it are we kind of like at the end of like the scaling for this architectural approach? We need another breakthrough or is there? No, no. We're at the beginning. Really? Without changing the architecture. I think we're basically at the beginning. Yeah. I think we're basically at the beginning and we're basically limited by compute at this point.

All right. Like data is very important, as Fei-Fei likes to point out, but like everything has a bottleneck. And I think the main bottleneck on continuing to scale this thing is actually training compute, right? Like during development, we trained a sequence of models. We read about this in the blog post a little bit, but we trained a couple of models that like the first couple of rungs of the scaling ladder. And each time we made the model bigger and each time we trained it for longer, each time we put it on more chips, like it got significantly better.

And the model size that we like, the model that we showed in the blog post is obviously the biggest and best one that we trained. But the thing that was limiting it was not the scale or the data or anything like that. It was literally like we had a deadline of when we wanted to release this thing. And therefore, we backed up what we could afford to train after that deadline. But here's a little bit of an insider story, right? Like Justin and team are training from the smaller and slightly bigger, you know, are having these roadmaps.

And then there was one day in summer, early summer, that it's not even the current Atlas model size, it's a smaller model. And then Ben, Justin, Ben feed it into, you know, the viewpoint generation. And remember that famous table, the garden table for NERF paper and many papers that overnight I got a slack. I mean, we all saw the slack from Ben that flew through under the table with the soccer ball. Yes, with the soccer ball. Is the soccer ball emergent or is that in the original picture?

It was real, right? That morning, the three of us looked at each other in the eyes and say, that's it. This is we're going to build this like we made a decision within five seconds. This is just a no one has ever seen this result. Ben, can you talk through maybe more specifically the use cases? So so World Labs has historically had a lot of users that were creatives and they use it for like consistency and, you know, like whatever. For 2D images and for movies and for 3D and for games, et cetera.

And so maybe can you talk about how this extends use cases are catered to the existing ones? And then we'll talk about robotics. Yeah, sure. Yeah, I mean, it's kind of funny. Actually, one of the kind of main ways we even saw people using Marvel plays exactly into this new view prediction case. Like a lot of our Marvel being the previous sorry, a Marvel, our previous product, like people would take that product, put an image and get a full 3D scene as a Gaussian splat. Take a couple of screenshots of it from different points of view and we're like.

We can just make those images. And that's right. So I think like, you know, there's a lot of degradation there. They're like, this could look better. And it's like, OK, what if we just generatively model those viewpoints with that exact modality of control? So I think like even that core capability of just like view synthesis, it's sort of been this academic problem for a long time. But in the sense of, oh, you're going to do this really dense capture, like like generative view synthesis is relatively quite a new problem.

And we just see so many people who in this creative pipeline, right, people have a multistage workflow, right? I don't think there's a single person out there using one monolithic model, not even see dance or whatever for their entire task. People will have this like, you know, kind of bunch of storyboards and mood boards of images they pull out from like their favorite collection of image models. And then they'll go to different video tools and like build those together as key frames. Then they'll go on like clip and edit those later.

So we were seeing this like sort of, you know, niche, but very specific use case for Marble as just providing that like sanity that you can ground your generations in some kind of 3D consistent world, right? People, you know, I've fought with various image models to ask them to like give me different viewpoints of a room. And every time you just look and see, oh, things kind of moved around like it's not stable. And like even that one seed of a use case, I think kind of signals that there's this value and there's hiding under the surface there.

Like there's just decades of people being used to persistent 3D state, like virtually modeling what they would be doing in the real world and having, you know, a stage and props and like elements there, whether it is for a movie or a show or marketing shot or like building out game environments like this, this statefulness and persistence is so key in how people think about spatial reasoning and like developing an environment over time. Like people don't think in this ephemeral, like generate a thing, like just throw it away, keep my text prompts.

Like people want to build this like collection of assets and like model a world in that way. So we're trying to provide like, again, with the spatial context mechanism and other things, like we're trying to provide that level of control and precision and the ability to ingest different modalities of input starting with the post images. But, you know, we want to give people more control over the elements of the things in the scenes they're looking at and editing and interaction and all that as we go forward.

And I think that that it unlocks like further use cases in those areas we're already seeing, but also expanding out into kind of any place people want to create a virtual replication or like, you know, a pre-imagination of a real world space they need to build right for architecture and construction. Like I talked to a guy at some point building booths for conferences, right? There's just so many things in the world you don't think about need to be fabricated. And every single one of those basically goes through this like pretty painstaking virtual design phase.

And of that process, like the part where you go into 3D software is kind of one of the most like arduous and like labor intensive parts right now, like like taking feedback on a 3D design from kind of like verbal commentary or sketches or really, really quick stuff you got from like a creative director or like a design director or an architect or whatever, like mapping that back into the 3D representation is like 95% of the work, right? You can have a meeting, get feedback, and then you go back and do a week of revisions.

And that's just because like our software is kind of decades old at this point. And it just never became as intuitive as, you know, playing with Legos or like pottery or doing this stuff with your hands or sketching with a pencil. And this is the real place where AI can actually unlock a ton of value for people in their process, whether it's a creative application or something more industrial or design or whatever. And that like really motivates me to kind of build different flavors of our model to cater to those kind of people.

Yeah, I can understand how it helps with the creatives because like Marvel did that and also how that extends to things like design or architecture. But say you acquired a robotics company. We just talked about it too much. I know, but it's less obvious to me, especially in the context of Atlas, like how that maps to robotics. So if you wouldn't mind just penciling that out. Yeah, actually, Atlas is a key part of the puzzle. So we acquired this company that was formerly known as Cinex.

And what is their key technology? Right now, their key technology is a system that goes from real to sim and then sim to real. And what does that mean in robotics situation? You want to train a robotic arm to, you know, figure out how to do cabling, let's say, in an industrial setting. Well, you need a whole bunch of data to first train the robotic. policy to do these cables, cabling activity. And then you want to evaluate if the robotic policy is doing a good job, and then you deploy the robot into the cabling environment.

In order to train, what this company, Cynics, and now our robotics team used to be doing is doing exactly what Ben was saying, dense reconstruction. You take, you know, pictures of a situation and then try to reconstruct that environment is excruciatingly painful, takes a long time, laborious, and it really blocks the velocity of robotic simulation real to some, right? So Atlas really is the next generation technology for that. And this is not just for robotics, cabling or anything. We should zoom out and recognize the biggest problem right now in robotics is actually data.

One day it'll be chips, but for now it's data. Because it's so hard to collect real world data where robots are operating. And in order to not only you need to collect the data of, let's say, the cabling situation or the dishwashing situation or whatever, there is also a very important step called randomization, is that you have to take the same environment and then randomize the condition so the cable doesn't literally only, you know, bend this way, it can bend a different way, or the box can have different sizes, colors, different lids, and all that, and or in different parts of the scene.

So you have to go through a real to some situation in order to get enough of that data, in addition to other data you can get from Internet. So this real to some step will be, you know, really helped by Atlas. That's just the first part of this, is meeting the robotics needs in the current technology, because we don't yet have a frontier foundation model that's robust enough for robotics. But Atlas is an omni-model, is a multi-modal model. It takes different kinds of input and generates different kind of output.

You can totally imagine the next step is Atlas taking in data that's dynamical. And that can really start to bridge the gap between, you know, action planning and robotics and the Atlas output. So that's on that roadmap. Were you going to say? Yeah, I was going to say there's something fundamentally different about training a robotics policy compared to really any other application in AI we've seen before. And that's like if you're generating a piece of code, like you're generating an image or generating a video, the model is fundamentally creating this artifact.

And that artifact, like there's a lot of examples of artifacts that you can go out on the web or somewhere and collect, right? You want to generate images, there's a lot of images out there. You want to generate videos, there's a lot of videos out there. You want to generate a code base, there's a lot of code bases out there you can learn from. A robotics policy is something fundamentally different. It's not producing a static thing. It's instead a policy that's going to go out into the world, make actions and like try to achieve a goal.

And the world's not always going to respond the way you expect, right? Unexpected stuff is going to happen. So a robotics policy is like fundamentally an agent that is out in the real world interacting with the real world and stuff happens. So you need like a critical part of that is those those policies during training need to be exposed to every possible thing that could go wrong during their deployment. And that's where simulation is really key for robotics, right? So there's the and then there's two angles on that.

Like one is the kind of classical simulation. You can go out, you can go and like go to your favorite physics engine and like try to imagine creatively as a human designer, what are all the scenarios that might happen in this in this in this when achieving this task and then try to write explicit code that models them all. That's one angle. And that's an interesting angle with coding agents like that actually gets supercharged too. But there's another angle which is try to more data driven simulation, right?

Like maybe we can't can we have a learned model that can understand how the environment how the world is going to respond to actions and maybe it might respond in unexpected ways sometimes. Then could we build these neural simulators that are trained on as much data as we can, then use these neural simulators, these learned neural simulators, you know, as a simulation bed to train robotic policies. And that's that's a really interesting future direction of Atlas. But but then it doesn't stop there, right? So but once you have, you know, this learned simulator, like this learned simulator kind of already has in its like mental brain, like it understands the world, it understands how the world is going to respond to actions.

And why doesn't the simulator itself become the player, right? Like the same. And that's kind of the core thesis that we've had around world models and their generality, that there are some core stuff that a model should understand around generating worlds, simulating them, understanding how they appear in different search situations. And, you know, understanding how the world's going to respond to an action is highly related to imagining what kind of action I need to take to make the world respond in a particular way. What one piece of feedback that I got, I mean, by the way, congrats on the launch.

It was overwhelmingly positive. I think it was probably the most significant model launch this year. And, you know, we said glowing things, but one person who's an expert in the space who I texted was like, what do you think? And it's great, it's fantastic, it's amazing, but there needs to be more dynamics. And so it seemed to be at least the robotics case, but generally it was kind of ideal to actually have a world that moves. And so maybe talk a little bit about that and then any other future directions that you're comfortable sharing what you think are worth talking through.

Yeah, I mean, like dynamics is clearly going to happen. Like, actually, we have baby dynamics, we actually do have baby dynamics already. And this is something I think people didn't quite appreciate. I didn't really highlight in the blog post, but like the previous Marble world model, it was fundamentally static. Like the model just like could not handle any dynamics at all. And that was just like baked into the model architecture, baked into the training. Like the whole thing was fundamentally static. We already knew that that was a big problem post-Marble and we already fixed it in Atlas.

The Atlas architecture is already fundamentally supports dynamics. The Atlas training data fundamentally has dynamics. And if you look carefully in some of the videos that we even posted, it actually is. I saw, I saw you see it moving a little bit. Yeah, the waves, the water waves. Yeah. So like some of the examples, there's like waves in the water, like in some of the like generated aerial views, there's like little cars moving around. So like dynamics is actually already in this model. By the way, dynamics seems very problematic to me.

If you're trying to reconstruct 3D from multiple views, right? And so like, are these things like at odds or? No, so it's actually one of our theses here is that like, you know, if you're going to do fundamental 3D reconstruction, you actually want to have no dynamics. Like you want to be able to model like exact views of the scene with exact frozen time. But then like this is actually kind of a problem with our previous Marble approach, right? Like they're like, you can try to find data that's fully static, but that's really hard to scale and really hard to get more of.

And the thing we realized is that even in the case where I want a static output in the end, the best way to get it is actually expose the model to dynamics, right? Like expose the model to as much dynamic stuff as you got, as much static stuff as you got, and let the model figure out how to factor out the dynamic stuff. So especially in like the code, this is like this is actually. So in the Atlas pre-training already, like it saw a ton of dynamics in the pre-training already.

Then the post-training that we did specific to this checkpoint in this release was focused a lot more on static stuff, focused a lot more on spatial movement and less on temporal. But like we already have we already like I'm pretty sure this the pre-trained checkpoint already has a lot of latent dynamics in it. And this is something we're going to improve quite a lot going forward. So Ben, does that mean we're going to get 4D video? It's like a walk around. You can see the smile on their face.

So I actually can see if like you just stopped now and you only did kind of bigger, you know, faster, better, you can build almost an entire industry. It feels like a very horizontal primitive. And if you did nothing else, but are there other things that are not just kind of bigger, faster that you're excited about the applications you're focused on, which tend to be kind of more on the kind of content creative 3D side? Yeah, I'm really excited about pushing that kind of multimodal aspect.

I think different modes of control is so critical here. I think like it's super underappreciated, especially in the academic community, how critical it is to add control conditioning to these models to kind of get out what's inside. I mean, honestly, this dynamic versus static is a good way to look at that. I'm not sure I even understand what those words mean. To translate in layman's language is to start with editability. Yeah. I think editability is the key here. Yeah. So, I mean, this is something we've seen in like sort of single image models and starting this year in video models is starting to be unlocked in terms of, oh, like getting that flavor of like multi-turn or really like intuitively interpreting like, I want like this person and this object and this thing to happen and kind of combining those all together in like one pastiche without having to do a lot of like manual work with the system.

Like it just interprets it like kind of frontier image models are kind of there, right, for in terms of editing. But we haven't seen that propagate out as strongly into video yet and then into world models. We've seen some really kind of toy examples of, oh, I can like put in a sentence and like, you know, a dinosaur appears or something with these like sort of real time models. But I want to like turn that up to really industrial strength and make that because like the trick here is you've got to add control but not compromise the quality of the model or it just becomes a party trick, basically.

Like it's like no one is going to seriously think about swapping their like cutting edge frontier video model usage for your model if you give them extra knobs. But the quality degrades. So I think it's really that game of like how can we maintain like the high bar we've set was the outputs we're able to get in the current model and then add all kinds of interesting stuff that people ask us for in terms of like I want to interact with the scene or control the layout or control like the identity of the objects and the things that we're seeing within there or control time.

Right. And I think that's like an axis where it opens up like a ton of really interesting product and interface work. The more complexity you add there and richness in terms of kind of like enabling you to really think about like redesigning almost from scratch the way people interact with sort of like stateful, you know, 3D worlds in the computer. Like that's that's really the end goal here is getting like all the capabilities you need to build that kind of system. Awesome. Anything you'd add to that as far as new functionality that you'd be excited about that's not just bigger, better?

I think for me, let's go back to the first principle of intelligence. Intelligence is not sitting there stuck and just seeing something or interpreting something when it comes to space and physical space. Right. It's really this closing the loop between seeing and experiencing an interaction. So just thinking about going up that ladder is exactly what Ben said. Cool. I think one interesting notion there is this notion of AI completeness. You read this before? Yeah. Yeah. So like everyone I hear about AI complete, by the way, in terms of LLMs, which is like you have to be basically, you know, like the smartest LLM to answer the question what the smartest LLM will need to answer.

Or you have to solve general intelligence. No, no. It's a connection to Turing completeness, right? Like the idea of being that like a task is Turing complete, like in classical complexity theory. If like I can take any class at any problem in this category, reduce to that one problem. You can take any NP-hard problem and reduce it to 3SAT, therefore you can use 3SAT to solve any problem. Yes. Yeah. So then like the kind of like soft definition of AI completeness is like there's this fundamental primitive that's an AI task.

But if I could solve this AI task in its full broadest generality, it would solve any intelligence problem. And like the classic example at LLMs is like next token prediction is AI complete because I could like, you know, there's the classic example, I think from Ilya, where like there's a mystery novel and like the thing has to read the whole mystery novel and the final sentence of the mystery novel is like, and the killer was predicting the next token. So like you could basically like frame any kind of intelligence task in terms of that.

So clearly next token prediction is something that people believe is AI complete. But I think that's something we're kind of realizing. And Ben was talking about this earlier today, is like new view prediction, this primitive that we have in Atlas, especially generative new view prediction. This is also AI complete. Right. And because I could take something like. You can you can have the movie and you do all of the frames of the movie and then like the killer walks out and then you predict exactly who walks out.

Exactly. I want to have a world where like Martine is like writing a proof of the Riemann hypothesis on the camera, opens up to the next whiteboard and he solves the Riemann hypothesis. So to take an evolutionary view, right, that new viewpoint prediction is exactly evolution had to solve by making animals move. Nature gave animals eyes, but nature didn't give trees eyes. Why? Because when you move, you see a new viewpoint. And that is the whether you call it AI complete or intelligence complete. So. So we do believe very strongly that next viewpoint prediction is is the equivalent of next token prediction.

Amazing. Well, with that, congratulations to all of you on a phenomenal model launch. We're very excited for future launches and thanks for coming. Thank you so much. Thanks for listening to this episode of the A60T podcast. If you like this episode, be sure to like, comment, subscribe, leave us a rating or review and share it with your friends and family. For more episodes, go to YouTube, Apple Podcasts and Spotify. Follow us on X, A16Z and subscribe to our substack at A16Z.substack.com. Thanks again for listening and I'll see you in the next episode.

As a reminder, the content here is for informational purposes only, should not be taken as legal business, tax or investment advice or be used to evaluate any investment or security and is not directed at any investors or potential investors in any A16Z fund. Please note that A16Z and its affiliates may also maintain investments in the companies discussed in this podcast. For more details, including a link to our investments, please see A16Z.com forward slash disclosures. Thank you for listening to this episode of the A60T podcast.