[jcims]

I don't know if I caught your comment in my peripheral vision or what but GPT-2 is exactly where I conceptually placed this.

Neural networks for motion control is very clearly resulting in some incredible capability in a relatively short amount of time vs. the more traditional control hierarchies used in something like Boston Dynamics. Look at Unitree's G1

https://www.youtube.com/shorts/mP3Exb1YC8o

https://www.youtube.com/watch?v=bPSLMX_V38E

It's like an agile idiot, very physically capable but no purpose.

The next domain is going to be incorporating goals and intent and short/long term chains of causality into the model, and for that it seems we're presently missing quite a bit usable training data. That will clearly evolve over time, as will the fidelity of simulations that can be used to train the model and the learned experience of deployed robots.

[robots0only]

Locomotion and manipulation are pretty different. The former we know how to do well -- this is what you see in unitree videos. Manipulation still not so much. This is not at all like GPT-2 because we still don't know what to scale (and even the data to scale is not there).