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)→
More from AGI Musings
- 10% of UK Parliament Speeches Are Now AI-Drafted, The Economist Reports — steverathje2 · 2026-09-24
- Yoshua Bengio Addresses UN Security Council on Threat of Uncontrolled Frontier AI Agents — AndrewCritchPhD · 2026-09-24
- OpenAI's Boaz Barak: no benevolent AI dictators, even if it means less abundance — tszzl · 2026-09-24
- CNAS report maps the spectrum of AGI futures and how to shape them — paul_scharre · 2026-09-24
- Philosopher Carissa Veliz: AI dominance is not inevitable — the future is produced, not predicted — CarissaVeliz · 2026-09-24
- Karpathy's 11-month tone shift: from coining vibe coding to feeling far behind — IgorCarron · 2026-09-24