Agent swarms may be the next scaling law, but speed may matter more than capability

The article examines whether multi-agent swarms could become a new scaling law, comparing them with inference scaling from o1.

OpenAI researcher Noam Brown said its models are now sometimes trained with other agents, while the cited Anthropic data suggests gains beyond 10 agents are smaller and mainly speed-related.

The article also raises the risks of groupthink and misaligned agents, and it notes that a Microsoft Research and UC Berkeley paper found teams sometimes solved tasks solo agents could not.