Noam Brown – Agent swarms, alignment, & recursive self-improvement
Summary
Noam Brown of OpenAI discusses the recent use of 10,000 AI agents to solve a Millennium Prize problem, explaining how multi-agent systems scale test-time compute in parallel. He details the emergent coordination behaviors of these agents, noting that while they mimic human collaboration, they operate at vastly higher speeds and with seamless context sharing. The conversation explores the "jaggedness" of current AI capabilities, which excel at well-scoped tasks but lag in posing new mathematical questions. Finally, Brown and the host debate the timeline for recursive self-improvement, acknow…
Listen ad-free on Castria