EP. 170 · 28.07.2026 · 42:21
SOLVING THE HARDEST PROBLEM IN ROBOTICS
with Fei-Fei Li
Auto-generated brief
EPISODE BRIEF — EP. 170 · SOLVING THE HARDEST PROBLEM IN ROBOTICS Guest: Fei-Fei Li · Published: 28.07.2026 · Duration: 42:21 【OVERVIEW】 Why robots still struggle with the physical world, and what World Labs is building to close the gap: large world models that give machines a usable, three-dimensional understanding of space, objects and action. 【KEY TAKEAWAYS】 1. Why robotics is harder than language 2. What a world model actually is 3. Data, simulation and generalisation 4. Building World Labs 【CHAPTERS】 00:00 — Why robotics is harder than language 11:00 — What a world model actually is 24:00 — Data, simulation and generalisation 35:00 — Building World Labs 【TOPICS】Robotics · World Labs · Spatial Intelligence · Embodied AI · Startups 【WATCH】https://thedaopod.com/episodes/ep-170-fei-fei-li-world-labs-robotics
SUBSCRIBE
Subscribe to The DAO
Get every dialogue, roundtable and observatory briefing in your podcast app — or copy the RSS feed and add it manually.
Subscription status unknown
We can't read your YouTube subscription directly — confirm it manually, and redo it anytime.
Follow us
https://thedaopod.com/rss.xmlABOUT THIS EPISODE
THE CONVERSATION
Why robots still struggle with the physical world, and what World Labs is building to close the gap: large world models that give machines a usable, three-dimensional understanding of space, objects and action.
SHARE
Copy link & social preview
thedaopod.com
EP. 170 · SOLVING THE HARDEST PROBLEM IN ROBOTICS
Why robots still struggle with the physical world, and what World Labs is building to close the gap: large world models that give machines a usable, three-dimensional understanding of space, objects and action.
Pasting this link on X, WeChat or LinkedIn renders the preview card above.
CHAPTERS
TIMELINE
Chapters derived from show notes
GUESTS
ON THE ROUNDTABLE
Co-founder & CEO, World Labs
Stanford professor and pioneer of computer vision, now focused on spatial intelligence and world models for robotics and embodied AI.
No subtitle track for this video — the timeline below is generated from chapters and follows playback
FULL TRANSCRIPT
Searchable Transcript
Chapter-derived timeline
0:00 · Why robotics is harder than language
Key Moments
4 lines
Related videos
Matched by host & keywords
EpisodeEP. 167 · SPATIAL INTELLIGENCE IS THE NEXT FRONTIER IN AI
with Fei-Fei Li
EpisodeEP. 168 · JOBS, ROBOTS AND WHY WORLD MODELS ARE NEXT
with Fei-Fei Li
EpisodeEP. 171 · USING AI TO INCREASE INTELLIGENCE AND ENRICH HUMANITY
with Fei-Fei Li
EpisodeEP. 186 · SIMULATING REALITY, PHYSICS AND VIDEO GAMES
with Demis Hassabis
EpisodeEP. 129 · SPATIAL INTELLIGENCE AND THE NEXT VISUAL FRONTIER
with Fei-Fei Li
EpisodeEP. 152 · BUILDING WITH LLMS: CRAFT, TOOLING AND THE NEW STACK
with Andrej Karpathy