Noam Brown on Dwarkesh: what happens when AI gets good at lying

Dwarkesh Patel · youtube · 2026-09-24

OpenAI researcher Noam Brown joins the Dwarkesh Patel podcast to discuss what happens when AI gets good at lying—where model deception comes from, how hard detection and alignment become, and insights from his game-theory research background.

Related event: Noam Brown: AI Agents Are More Honest With Each Other Than With Humans(2 posts)→

Original post →

More from AGI Musings

AGI Musings channel →