Real Alpha
Watch modeSubscribed

Minus One · 3 min · Oct 22, 2026

Robotics teams need expertise and shared stack context

Sergey Levine

Co-founder, Physical Intelligence

  • Aditya AgarwalHost · Partner, South Park Commons

    One of Facebook's first engineers, he helped build its first search engine; later CTO of Dropbox.

About this segment

Levine says robotics teams need specialists who respect others' expertise but still learn the full stack. At Physical Intelligence, ML researchers showed up for a hardware talk, reflecting that curiosity.

From “How Close Are We to Robots That Can Do Anything? | Sergey Levine, Physical Intelligence”, Oct 22, 2026. Watch the full episode

“you kind of have to have a culture that both embraces heterogeneous skill sets and at the same time sort of encourages people to gain complete context.”
Sergey Levineat 37:41 · Minus One37:41

Takeaways

  1. Keep deep expertise while encouraging context across the stack.
  2. Robotics teams need respect for specialties and cross-team learning.
  3. At PI, ML staff showed up for a hardware talk in large numbers.
Watch 2:42 from 37:21

In this episode

Full episode
  1. 9:32Reasoning and better annotations help robots generalize7:16
  2. 21:08General-purpose robots can bootstrap their own data7:02
  3. 33:21Data strategy matters more than the world-model label2:58
  4. 28:02Robotics may advance faster by solving the whole field5:27
  5. 1:50Robot-only data taught grasping, not broader physical skills2:38
  6. 16:39Robotics researchers must trace failures across the whole stack4:36
  7. 7:17Robot models need prior knowledge beyond demonstrations2:24

  8. 37:21Robotics teams need expertise and shared stack context2:42

Up next · The Cognitive RevolutionAn intent model lets AI generate enterprise code deterministically4:47

Transcript

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

  1. 37:27

    But one thing that I think is really important and uniquely important in robotics that is not, I think, as critical for Google or for OpenAI or for Meta is that because robotics is so interdisciplinary and because it's so important to have that attention to detail and see all parts of the stack, you kind of have to have a culture that both embraces heterogeneous skill sets and at the same time sort of encourages people to gain complete context. And that's a slightly paradoxical thing because specialization might imply that like, oh, you're the hardware expert. I'm the model expert.

  2. 38:05

    You do your thing. I'll do mine. And let's just try to like not meet too much in the hallway because we're all doing separate things. And the right thing is like a very healthy respect for the expertise that other people have that you don't have, but at the same time, like a burning desire to really get at least some kind of understanding of everything that's going on. And you got to strike that balance somehow.

  3. 38:25

    And if you do that, then you get this magical place where everyone has their superpower. Everyone is like very respecting of the different skill sets people have, but at the same time, really has at least like some rough conception of what the whole stack is doing. Yeah, it is always surprising to me how that meta observation ends up being just a key part of like great uh great companies early on which is that it's not that everyone is a generalist is that everyone actually shows up with like something that they're world-class at but then they don't constrain themselves to just the thing that they are world-class at is it both a curiosity but then also just like willingness to kind of go out and learn about like the whole stack and it's a weird mixture and you have to strike a balance because you know um but i think great great founding teams often are able to find

  4. 39:15

    a great equilibrium on that yeah one thing that like really stands out to me in my memory which kind of made me think like oh man i'm really happy about how this company functions is that uh we have um uh a person on our hardware team who um uh works on you know very low level hardware stuff like you know actuator sensors that sort of thing and he was giving a talk uh kind of like a lunch tech talk type of thing.

  5. 39:37

    And I could see that a disproportionate number of the people that showed up to the talk are the ones that are furthest away from the hardware, like the ML infrastructure, like folks that are doing the really esoteric reinforcement learning algorithms. Those are the people that most wanted to learn about this thing because they have this burning desire to understand the entire stack. That's cool. I'm going to give you some rapid fire questions.

  6. 39:55

    What are the tasks that surprised you most when a robot did it? Using a plastic bag.