# Anthropic reports a 1,000-agent team reproduces the Fermat's Last Theorem proof

> Original title: Safely scaling multi-agent teams with Claude Fable 5.2

- Source: Claude Blog
- Published: 2026-11-09T05:00:00.000Z
- Bad Influence: https://badinfluence.news/items/snkdod2sou7ng6z8f28n53gj8
- Original: https://claude.dev/blog/safely-scaling-multi-agent-teams-with-fable-5-2/

## Summary

Anthropic says a team of 1,000 agents running an early version of Claude Fable 5.2 reproduced its formal proof of Fermat's Last Theorem in 28.7 hours. The agents used one-third as many output tokens and wrote a proof one-seventh the length of the earlier Prove2Me-assisted formalization, with no researcher steering. Each agent ran in a sandbox without internet access, under a real-time classifier and an offline monitor, and none of the more than one million tool calls were blocked.

## Why it matters

The post separates what the team achieved from the setup behind it, including the shared database, the sandbox limits, and the monitors that blocked nothing across the run.