Skip to content
Anthropic · Claude.dev· Barry Zhang, Tianyi Peng, Elle Najt, Keller Scholl, and Lance Martin·· 4 d agoPicksAI score80

Anthropic: 1,000 Claude Fable 5.2 agents reproduce Fermat's Last Theorem formalization in 28.7 hours

Safely scaling multi-agent teams with Claude Fable 5.2

AI summary

7 hours without the Prove2Me platform or researcher steering used in Anthropic's September run, writing a proof one-seventh as long and using one-third as many output tokens. Each agent worked in a network-isolated sandbox with a classifier checking every shell command and file edit plus an offline monitor, and across more than a million tool calls none met the bar to be blocked.

Why it matters

Anthropic's 1,000-agent run reproduced the Fermat's Last Theorem formalization without Prove2Me or a researcher, showing how sandboxing and monitoring bound a self-organized agent team.

Source:Anthropic · Claude.dev · claude.dev