00:11:16 · Priya, Maya
[00:11:16] S1: after? Yeah. Like what is actually the best architecture for like the end result that we're trying to get to? Yeah. So who's doing the second approach where it's like one combined model right now? [00:11:24] S0: Physical intelligence. Okay. Yeah. So their first version that they released is the combined approach. Is it [00:11:29] S1: like pie zero? Yeah. That's what it's called? [00:11:31] S0: Yeah. Pie zero. Nice. It's not... These things are not easy. Yeah. And the reason why it's not easy is because like LLMs are really good at generalizing. They're really good at taking the average. But when you think about an action, like if you wanna move a cup from left to right, there's like literally twenty hundred, maybe thousands of different ways to move... [00:11:49] S1: Think about like the average of how it would get there. It's like so funny. [00:11:53] S0: There's no there is no average. Right? There's it's actually there's like one... There's actually like an action and either works or it doesn't. And there's like a 100 actions at work and there's like a thousand actions that don't. Right? And so you need to actually produce like your output instead of being one general answer or one average answer, it should be like a 100 answers. And then you pick the one that works. And so like at the actual architecture layer, what this new model is doing is literally pushing out like a 100 options and then they're testing which option is the best one and then going and doing that option.
00:11:53 · Maya, Priya
[00:11:53] S0: There's no there is no average. Right? There's it's actually there's like one... There's actually like an action and either works or it doesn't. And there's like a 100 actions at work and there's like a thousand actions that don't. Right? And so you need to actually produce like your output instead of being one general answer or one average answer, it should be like a 100 answers. And then you pick the one that works. And so like at the actual architecture layer, what this new model is doing is literally pushing out like a 100 options and then they're testing which option is the best one and then going and doing that option. [00:12:24] S1: Yeah. Do you think like Figure... Because in my opinion, it seems like Figure is optimizing the model they're building for their hardware specifically versus a physical intelligence where it can be applied anywhere. Maybe they'll go after it themselves and have their own hardware, but it's kind of like choosing to do a hardware first approach in my opinion or like a software first approach. Do you think they'll all ultimately converge or do you guys think there's one that's like a better approach than the other to take right now? [00:12:48] S0: I think that... So I'm actually not really sure what is the better approach to take. What I do know is that the industry is not aligned on this approach. [00:12:57] S1: On what we should [00:12:57] S0: I be don't think anyone will be aligned until one player like does the thing. [00:13:02] S1: Like it actually works. And they're
00:13:02 · Priya, Maya
[00:13:02] S1: Like it actually works. And they're [00:13:03] S0: like, okay, is the right thing. It's... It was real... It to me, it's like almost kind of similar to like the Waymo Tesla debate. I was just thinking I'm like, LiDAR, [00:13:10] S1: do you need... [00:13:11] S0: Do you really need LiDAR? Do you really not need LiDAR? And I feel like this is similar in the robotics space of, like, do you need a diffusion policy model, which is this end to end learning model? Or do you do a dual system architecture? Because it's faster and it's just, like, better practically. [00:13:24] S1: So... Yeah. Because Tesla has one model. Right? And then Waymo has... Well, I guess, actually, Waymo, they just combine their model to also have one model. Yeah. So that's interesting because maybe it is. So if there's anything I [00:13:36] S0: had to guess, I would assume it's one model. Yeah. Obviously, because of, like, industry standards and, like, what we see in other industries. But it's just it's it's an easier thing like when you when you just have less moving parts in any engineering system, it is easier to reason about. So people always prefer one or like less. Yeah.
00:13:36 · Maya, Anika
[00:13:36] S0: had to guess, I would assume it's one model. Yeah. Obviously, because of, like, industry standards and, like, what we see in other industries. But it's just it's it's an easier thing like when you when you just have less moving parts in any engineering system, it is easier to reason about. So people always prefer one or like less. Yeah. [00:13:55] S2: And I feel like generally companies have good long term success with owning more of the stack rather than less. Right? Like Elon's approach also. Like, which is like different than what you guys are saying, but like another thing where like figure has that. And I think the reason why it might matter more for robotics than other things... Like, in my view, physical intelligence is making a bet that there's gonna be an open AI for robotics. Right? Mhmm. But then the thing about robotics is like the... Like we already said, the best quality data is from the robot. And so they obviously are getting that data all the time as well, but not... I don't think it can be, like, as tight of a chain if, like, you're having to integrate with a million different types of robots versus figure, like, they can actually change their hardware or their architecture based on the data that they find. [00:14:40] S0: I I... Well, I guess what I was gonna say is like, I actually do really think that physical intelligence is going to release a robot. They just haven't yet. Because if you look at their careers page, there's literally an entire set of careers just for the robots. [00:14:52] S2: Yeah. That might be the case.
00:14:52 · Anika, Maya, Priya
[00:14:52] S2: Yeah. That might be the case. [00:14:54] S0: The whole thing is like like you're either a bit or an atom. And like bits are like the model researchers and then the atoms are like the hardware researchers. That's so nerdy. No. It is so nerdy [00:15:06] S1: because like I tried [00:15:06] S0: to apply to them like six months ago. And then I was like, I can't. I'm like... [00:15:11] S2: I also tried to apply to them. [00:15:12] S0: Where's the other? [00:15:15] S1: You're like, hi. I'm a product engineer. [00:15:18] S0: I can make your website really pretty. But... Yeah. So anyways. But yeah, we should move on. So the... So yeah. We were talking earlier about like other data startups that are going after this. The other thing I wanted to mention was that there is a bit of a Chinese market that's happening right now. Like currently, the Chinese government is building centralized like robotic training centers. They literally have data factories of, like, robots performing tasks, and they're taking all sorts of, like, measurements and video and all that kind of stuff on this. But...
00:15:18 · Maya, Priya, Anika
[00:15:18] S0: I can make your website really pretty. But... Yeah. So anyways. But yeah, we should move on. So the... So yeah. We were talking earlier about like other data startups that are going after this. The other thing I wanted to mention was that there is a bit of a Chinese market that's happening right now. Like currently, the Chinese government is building centralized like robotic training centers. They literally have data factories of, like, robots performing tasks, and they're taking all sorts of, like, measurements and video and all that kind of stuff on this. But... [00:15:47] S1: I do question that approach generally. Because I've heard of people even in The US, like, building factories or whatever it is, warehouses where they simulate home environments and stuff like that. But I feel like homes are the most unstructured place that exists. And so how much can you actually simulate in an an environment versus is it worth it to take... And with this can, like, lead us into our conversation about the different companies, but, like, a shift approach where it's, like, let's just go into thousands of New York City homes and get the data from each of those individual environments because they'll be more randomized, more unique, and give us better data [00:16:19] S2: Yeah. [00:16:20] S1: Than, like, a Chinese factory. Like, I feel like in my head, I'm imagining it as this, like, pristine place, and then they're, like, messing things up to have the robot come and fix it. But I just don't know how realistic that actually is.