CharlieKey takeaways from your favorite podcasts
← 13 October 2026Latent Space

The Million-Hour Robot Brain: Dyna-2 & World Models — Jason Ma, Dyna Robotics

Jason Ma argues robotics will be solved by scaling a general world action model that predicts the future, pretrained on human video, and built full stack around real deployments.

Watch on YouTube ↗

Word for word

There's a lot of research in robotics that's coming up with like very specific priors like for example we need to make the robot see objects as they are draw some boxes that will give robot better perception right but I think the bitter lesson here is that just keep the algorithm simpler and scale the right kind of data then generalization better behavior will emerge
★ In the digest▶ 44:05
What's really hard is not putting your robot in one location or doing a pilot. What's really hard is that the customers believe or validate that your robot creates enough value that they want to deploy your robots across many of their sites. So that's what's happened for us with Dintyong, which to the best of my knowledge hasn't really happened for other companies.
For robots, the inference latency has to be very short. The robot needs to act; it can't just hold a knife and not do anything for three seconds. That's going to freak people out.

Do more with Charlie

Free — sign in with your email, no password.