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.
00:16:20 · Priya, Maya, Anika
[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. [00:16:31] S0: Yeah. I actually, like, imagine a world where you can, like, fine tune a specific robotic model for your specific line work. So like for example, like Amazon still has people like packaging boxes. And like Amazon probably has a bunch of cameras on those people and will probably train like humanoid or autonomous like arms to be able to package boxes. Because you can't... Because like previously robotics was just like performing like a specific task really really well over and over and over again. But it had like, it was a rules based task. It's not like a reactive task. And I think that you can actually constrain the problem to, like, only reacting to packages in a box and putting those in a box. And it makes the problem easier. And so, like, if you can build... So I think, like, what... At least what I understand from these Chinese data factories is, like, it's trying to... They're trying to build, like, specific smaller robot models for smaller line work tasks. [00:17:18] S1: Which also makes sense for China. Yeah. Yeah. Yeah. So... [00:17:22] S2: And I [00:17:22] S0: think that... Yeah. I think that they would be able to like deploy those. Yeah.
00:17:22 · Maya, Anika, Priya
[00:17:22] S0: think that... Yeah. I think that they would be able to like deploy those. Yeah. [00:17:25] S2: I feel like we may get a generalized model or robot before like we go. Like, for example, like LLMs, like, got a generalized version before people started going into the fine tune phase. And so then either, like, they're making the bet that that won't be true in robotics or they're, like, skipping ahead. They're doing two parallel paths. Right? [00:17:44] S0: Yeah. I mean, I feel like there are so many more dimensions in the three d space outside. Like, when you go from like language to literally like moving in a three d space, I think there's like infinitely more factors that you're dealing with. Yeah. For sure. That I could see opposite being true being being, like, fine tuned models will work better and earlier Yeah. Than, like, a general humanoid at your home. [00:18:08] S1: Also, the starting point for both of them are different. Like, the starting point for robotics today is that they are trained on individualized tasks. And we're, like, moving the opposite direction of, like, trying to get more broad. [00:18:19] S2: Yeah. And in terms of the companies in the space, there are a few. One is Pronto. They recovered pretty extensively during their last rage... Race because they're basically a marketplace for, like, cleaning homes and other, like, domestic labor. What, like, else do they do? Do they do stuff besides cleaning homes in India? [00:18:37] S0: I thought they do, like, laundry too. [00:18:38] S1: Yeah. Okay. Like, different maid services.