Chelsea Finn on June 17th, 2025 at AI Startup School in San Francisco.
From MIT through her PhD at Berkeley, where she pioneered meta‑learning methods, and Google Brain, Chelsea Finn has built her career around teaching machines how to learn. Now an Assistant Professor at Stanford and co‑founder of Physical Intelligence, she’s using that foundation to bring learning-driven robotics into messy, real-world environments rather than confined lab setups.
In this talk, Chelsea traces the evolution of her team’s work—from early experiments on robotic grasping and vision to today’s ambitious efforts at folding laundry, tidying kitchens, and generalizing across tasks—all without hand-crafted code. Instead, they used scalable foundation models and massive datasets, teaching robots physical common sense as they learn by doing.
She shares stories of the rocky setbacks, the surprises hidden in data, and the moment it all clicked: robots equipped with generalizable physical intelligence can indeed adapt and assist in the unpredictable world around us.
Apply to Y Combinator: https://ycombinator.com/apply
Work at a startup: https://workatastartup.com
Chapters:
00:00 – General Purpose Robots
00:11 – Challenges in Robotics Applications
00:57 – Physical Intelligence: A New Approach
01:47 – Learning from Language Models
02:08 – Data Sources for Training Robots
03:32 – Training with Real-World Data
04:39 – Initial Successes and Challenges
09:10 – Breakthrough in Robot Training
11:03 – Improving Performance
15:43 – Expanding Capabilities
17:34 – Robots in Unseen Environments
25:54 – Handling Open-Ended Prompts
29:36 – Evaluating Robot Performance
30:03 – Future Directions and Challenges
31:27 – Audience Q&A
