EP. 102 · 02.14.2026 · 1:33:12
RLHF AND TEACHING MODELS TO BEHAVE
with John Schulman
Video coming soon
AI ResearchAI1:33:12
ABOUT THIS EPISODE
THE CONVERSATION
John Schulman joins the DAO podcast to discuss rlhf and teaching models to behave — and what it means for the trajectory of artificial intelligence over the next decade.
GUESTS
ON THE ROUNDTABLE
J
JOHN SCHULMAN
Co-founder, OpenAI alum, Anthropic
Co-creator of ChatGPT and RLHF. A foundational researcher behind aligned LLM behavior.
RELATED EPISODES
EP. 1432:07:11
THE TAO OF INNOVATION: STEVEN HOFFMAN ON BUILDING GLOBAL STARTUPS
with Steven Hoffman (Captain Hoff)
EP. 1441:15:33
CHINA'S AI UNDERDOGS: STARTUP LESSONS FROM BEIJING TO SHENZHEN
with Li Xiaohua
EP. 1421:42:08
THE AI INFRASTRUCTURE BUBBLE: CAPEX, GPU CLUSTERS, AND THE NEW RAILROADS
with Lin Wei & Marcus Cho