1X wants one model to generalize across tasks

Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

1. 5:48

   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, kind of there's this safety bar that you want to hit before you ship it to, you know, your kit 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? 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 kind of 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 um gives you kind of like the kind of customer impression how is it to live with this how um how well capable is the

2. 6:37

   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 and 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 kind of like would think it is so it's kind of 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

3. 7:24

   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 kind of like the first new big training run ...now, later this month, and I'm very excited to see how the new model is going to turn out.

4. 8:06

   It's a bit early yet, but there's some very, very promising results there, and I think we have a pretty good shot at solving the general problem. On this training run? No. Okay. But getting to... It's kind of 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 kind of fold this into the training and now you get more data so now the model is even more capable and then you kind of hill climb like this but the really important thing here is to have models that are so capable that you don't need the human in the loop to generate the data you just need a large fleet of deployed robots and then you will get very capable

5. 8:53

   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 for the environment when 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 on the kind of scaling the manufacturing side what has the