CharlieKey takeaways from your favorite podcasts
← 3 October 2026The Cognitive Revolution

One Brain, Any Body: Google DeepMind's Keerthana on Gemini Robotics 2, Cross-Embodiment & Humanoids

Keerthana argues robotics is still in its GPT-2 era: locomotion is easy in simulation, while general manipulation, cross-embodiment transfer and reliable orchestration remain open, so she favors empirical mixtures over firm predictions.

Watch on YouTube ↗

Word for word

The jury is still out there. Ultimately, the thing about working as a roboticist is that you are not emotionally attached to one method or the other method. You're emotionally attached to the problem itself, and whatever way you solve the problem, you will pick that. And there are many schools of thought. Definitely world modeling is a very interesting area for robotics, and not just as policies but also simulation and other things. I say the jury is out there still because there are obviously the VLAs, the VAMs, but also look at how the agent robotics are going. And this is maybe one of the most exciting parts of working in robotics: it is still very early, the recipes haven't stabilized. Different people can have very different schools of thought about how I'm going to go about and solve robotics.
Generalization and mastery are somewhat orthogonal axes. And working on generalization is lifting the wave for all the boats. So if you imagine the tasks are sitting along this manifold, doing very general common sense, very general understanding is making it much easier to get to mastery on all the tasks.
Certain applications, like if you're on an assembly line, you can't loiter and you need to do things really fast. But let's say I'm at home and I'm like, "Hey robot, can you go fold my laundry?" I don't really care about how fast it is folding laundry. I care about how well it is doing the task. I can wait. And then maybe also, scaling is a very important factor in LLMs and in robotics. And I would imagine that a lot of the very frontier capabilities are going to appear in the very large models. And those models are going to be naturally slower than the smaller models. So I think there is definitely a trade-off and a spectrum to be made.

Give your email to unlock the rest of the quotes — for every episode.

Do more with Charlie

Free — sign in with your email, no password.