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)→

Original post →

More from AGI Musings

AGI Musings channel →