Noam Brown on Dwarkesh: agent swarms, alignment, and what math progress says about recursive self-improvement
GregCook2011 · x · 2026-09-22
A new 80-minute Dwarkesh Podcast episode with Noam Brown covers multi-agent systems, the Navier-Stokes problem, and what the current explosion of math progress reveals about what happens once AI research itself is automated. They also discuss how we could know whether models are actually aligned before kicking off recursive self-improvement. The episode also promotes Jane Street's October FOOM Debate panel in San Francisco with Daniel Kokotajlo, Ege Erdil, Ryan Greenblatt, and Jaime Sevilla, hosted by Ron Minsky. Watch on YouTube or read the transcript.
More from AGI Musings
- Anthropic safety: Opus 5.5 release likely reduces misalignment risk vs predecessors — EricBuess · 2026-09-23
- Duncan Weldon: disasters won't kill AI — the response to them will decide — ShakeelHashim · 2026-09-23
- Academia Is a Content Farm Ill-Positioned to Police Outsiders on AI Use — RexDouglass · 2026-09-23
- Academia operates like a content farm amid frontier-lab science disruption, researcher argues — RexDouglass · 2026-09-23
- OpenAI Researcher Blasts 'Total Safety Transparency' Push as a Gift to AI's Enemies — trevposts · 2026-09-23
- Distillation's real impact on Chinese labs debated: no hard evidence, says Lambert, maybe 1-2 month edge — xeophon · 2026-09-23