Dwarkesh interviews Noam Brown on multi-agent, math explosion, and verifying alignment before RSI

Miles_Brundage · x · 2026-09-18

Dwarkesh Patel's new podcast with Noam Brown covers multi-agent systems and Navier-Stokes, how AI firms will work, what the current explosion of automated math progress says about recursive self-improvement, the internal/external model gap, chain-of-thought degradation, and how we could know models are aligned before kicking off RSI.

Related event: Noam Brown on Dwarkesh: 10,000-Agent Swarm Solves Navier-Stokes(7 posts)→

Original post →

More from AGI Musings

AGI Musings channel →