Episode #92

Fully autonomous robots are much closer than you think – Sergey Levine

Plus, how VLA models work, self-improvement from deployment, and China’s hardware advantage

What this episode covers

Plus, how VLA models work, self-improvement from deployment, and China’s hardware advantage

Where to start
People and topics
Key takeaways
  • Timeline to widely deployed autonomous robots
  • Why robotics will scale faster than self-driving cars
  • How vision-language-action models work
  • Changes needed for brainlike efficiency in robots
  • Learning from simulation
All moments
Fully autonomous robots are much closer than you think – Sergey Levine podcast chapters, timestamps & summary | EpisodeIndex