00:04:19 · Bernt Øivind Børnich
[00:04:19] S1: Yeah. Yeah. So it's actually kinda interesting because it's about three years now since I kinda had the first, like, let's call it pilot at home, where I actually had our previous robot, Eve, the wheeled humanoid, which is a bit, like, bigger and more heavy, but very capable at home. And it was a lot of fun, and we learned a lot. And it was also one of the main inspirations for why, like, we had to kinda speedrun getting to, like, the full biped to be able to do all these tasks around the home and and also in, like, other diverse environments. Legs are actually very useful also for manipulation. It was a hard lesson learned. But I think the evolution over time is surprisingly slow. Like, it takes a long time. Right? So... And and this is often because you find something that doesn't really work and you need some significant data on this, then you need to iterate on your hardware, and you need your hardware to kinda redeploy, and now you get new data. And we're not in that many homes, so, like, it takes time to kinda run that loop. But luckily, we started very early, so we... We've had a lot of time to to think about these things. But I think mainly to me, the kinda, like, important barrier that has to be crossed on the trust side is is safety. And that's something that we're still working really hard on, and we really have a big goal to kinda, like, prove out safety this year in a more formal manner. So I'm very excited about that, and hopefully, we can share some more about that towards the end of the year.
00:05:48 · Ty Morse
[00:05:48] S0: How do you kind of decide on... There may be, you know, a thousand tasks that the robot can do in, like, a lab environment, but then, like you said, kinda there's this safety bar that you wanna hit before you ship it to, you know, your kid is around it. How fast do you go from, you know, creating a new task to actually having that in the environment and, like, testing it in your own home?
00:06:08 · Bernt Øivind Børnich
[00:06:08] S1: So one of the beautiful things about the system is that since it's so close to a human in how it operates, it's actually pretty straightforward to also operate the robot as a human. So this concept of kinda like an expert in place or like an expert operator allows you to really test a lot of tasks way before you're able to automate them, which is very useful. Gives you kinda like the kinda customer impression, how is it to live with this, how how well capable is the hardware to do these tasks. So I think, like, largely, most of the things we've already tested it out. And really, the big thing now is how do you automate it? And here, we follow a very different approach than most of the players in the space. I'm a very big believer in we can solve the general problem. We don't need to go and, like, automate every single task individually. There's a lot of tasks, and there's a lot of complexity. And, also, there's a lot more variability than you kinda, like, would think it is. So it's kinda like deep rabbit hole, right, to solve every task. And I see humanoids almost more like this bridge between human data and human intelligence and the machines. We've designed robots that are so similar to us as possible, even in how... Not just how they move, but how they interact with the world, how stiff they are, how compliant they are, all these things. So that we can take all this data that exists of us and just video and everything else out there on the Internet and train models that allows our system to be very generally capable across essentially all tasks, but less capable than if you specialize right now. But it allows you to solve the full problem way sooner. And I think that's generally what's also needed for the home. So I'm very excited about that. The new 1X world model labs that we stood up, amazing team. And we're kicking off kinda like the first new big training runs now later this month, And I'm very excited to see how the new model's gonna turn out. It's a bit early yet, but, there's some very, very promising, promising results there. And I think we have a pretty good shot at solving the general problem.
00:08:15 · Ty Morse, Bernt Øivind Børnich
[00:08:15] S0: On this training run? [00:08:17] S1: No. Or... Okay. But getting to... It's kinda like a bootstrap problem. Right? Because you train a model that is very capable of essentially attempting all these tasks. And it does a good job of attempting them and sometimes succeeds, sometimes fails. And this gives you more data. And you kinda fold this into the training, and now you get more data. So now the model is even more capable, and then you kinda hill climb like this. But the really important thing here is to have models that are so capable that you don't need a human in the loop to generate the data. You just need a large fleet of deployed robots, and then you will get very capable data of both successes and failures. And you close the loop in the real world essentially to learn. Right? And then you need the capable model. You need a safe robot because if it's not safe, then it will harm itself or the environment where it's trying to do things it doesn't quite know how to do. And then you need a lot of deployed robots. So that's one more reason to see if we can get 50,000 of them out by the end of next year. [00:09:15] S0: On the kind of scaling the manufacturing side, what has the process been like going from the first one to, like, the first 10 to the first 100? And what have been the biggest bottlenecks along that journey?
00:09:25 · Bernt Øivind Børnich
[00:09:25] S1: So to some extent, we're we're a bit lucky in that, like, the system has been designed from day one for manufacturability. So even if you think about, like, this is a tech tree, and how do we choose to build robots, it's a bit different. So while you normally would have, like, kinda like normal motors, which aren't that strong, so now you need very complex gear systems. These gear systems introduces a lot of, like, energy and other artificial dynamics into the system that nature doesn't have. Now you need a lot of sensors and high speed control and all things to kind of mask this. You're kinda like fighting physics. We've taken a very different approach. So we have some very capable motors we develop in house and also manufacture that allows us to do these tendon drives. And they're drastically simpler, actually. So not just more performant, drastically simpler, like less parts, less complexity, less tolerances, less sensors, and all the things that can go wrong. So the system is quite manufacturable in that sense. Now the downside, of course, is that since this is a new type of system, there is no supply chain for this, so we have to manufacture all of it ourselves. And that's taken us a decade. Right? Like, the company is eleven years old now. So we we really had to kinda, like, climb the maturity ladder of these production processes. But now that that is getting quite mature, it's really a superpower because we do it all in house here. So whenever anything happens, we can just go back and iterate very fast and make sure we fix it upstream. So I think the most important metric we have right now is we use about four weeks from when do, like, major changes on the full system in CAD until a new robot walks off the line. And it took us a decade to kinda build that momentum where we can iterate so fast on the hardware. But that allows us to take the feedback from the line, you know, and feed that back into engineering and iterate in about four weeks. So then you can really, really, really kinda, like, tune in your manufacturing process. So you pick off any mistakes that's done in, like, assembly or anything that's hard to do with respect to quality, yield, calibration, all these things down the line. But there's there's no, like, secret sauce. You just need to, like, grind through all these problems.
00:11:25 · Bernt Øivind Børnich, Ty Morse
And in the end, you read across your fingers that you're gonna you're gonna run out of problems. If you just fix enough of them, you're gonna run out of problems. Do you still believe? Yeah. I still believe. But, like, since that's kinda the only way to do it, then you just need to be able to really benchmark yourself on, like, how quickly can I iterate? Because that's how quickly I can kinda, like, churn through these problems. And we see less and less problems. So there's... Seems to be going in the right direction. So sooner or later, we'll run out of the problems. [00:11:54] S0: When you're, like, starting to put these in people's homes that aren't inside of the company, I think the bot at the beginning of next year is going to look significantly different than the bot at the end of next year. And the feedback that you get from January customers are gonna be very diff... You know, you can incorporate that for the December people. How do you kind of, as quickly as possible, incorporate new information and new feedback from the robots in the field, and then basically spin up new manufacturing lines in order to scale that?