Dwarkesh interviews Noam Brown on multi-agent AI, math progress and alignment
soumitrashukla9 · x · 2026-09-20
Dwarkesh Patel released a new episode with Noam Brown covering multi-agent systems, Navier-Stokes, how the current explosion of math progress informs recursive self-improvement, the internal/external model gap, degrading chain-of-thought, and how we'd know models are aligned before kicking off RSI. The reblogger praises Brown for taking uncertainty seriously despite criticism over an isolation-related example.
Related event: Noam Brown Clarifies Out-of-Context Podcast Clip(2 posts)→
More from AGI Musings
- AI Agent Switches Auto Insurance in 5 Minutes, Saving $3,500 a Year — rohanpaul_ai · 2026-09-20
- If continual learning is nearly solved, why do we still pick reasoning effort tiers? — akbirthko · 2026-09-20
- Nucleus's Vitruvian claims 14-point embryo IQ boost; researcher calls it misleading marketing — anshulkundaje · 2026-09-20
- XGEN Labs unveils generative world simulation JING+DAO, tops WBench leaderboard — hey_abusiddik · 2026-09-20
- Schmidhuber: LLMs aren't truly creative because they lack compression progress — SchmidhuberAI · 2026-09-20
- Guardian podcast traces chatbot 'rabbit hole' from ELIZA to ChatGPT — nordicinst · 2026-09-20