Physical Intelligence's Chelsea Finn on robot models that handle the unknown

Physical Intelligence cofounder Chelsea Finn (TIME100 AI 2026) joins Reid Hoffman and Aria Finger to explain how general-purpose robot models learn to act in messy, unfamiliar physical environments. Hear why adaptability matters for useful robots, the challenges posed by lower-quality training data, and what generalization looks like for real-world robot learning.

Congratulations to Chelsea, recently named one of TIME’s 100 most influential people in AI:

⁠https://time.com/collection/time100-ai/2026/chelsea-finn/

For more info on the podcast and transcripts of all the episodes, visit https://www.possible.fm/podcast/