Papers & Research

Anthropic uses 1000 Claude Fable 5.2 agents to reproduce formal proof of Fermat's Last Theorem in sandbox

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

AI summary

In an Anthropic toy experiment, 1000 agents running an early version of Claude Fable 5.2 reproduced the formal proof of Fermat's Last Theorem without the Prove2Me platform or researcher guidance, taking 28.7 hours, with output tokens only one-third of the original September formalization and a proof length of one-seventh.

Key Takeaways

  • In an Anthropic toy experiment,1000 agents running an early version of Claude Fable 5.
  • 2 reproduced the formal proof of Fermat's Last Theorem without the Prove2Me platform or researcher…
  • 7 hours,with output tokens only one-third of the original September formalization and a proof…

Quick Facts

Published
Updated
Source
Anthropic:Claude.dev 开发者博客(RSS)
Category
Papers & Research
Topic
AgentAnthropic / ClaudeSafety & Alignment
AI score
83
Read the original Read the full article at the original source
Why it matters

Anthropic 详细复盘了 1000 个智能体在沙箱内自组织证明费马大定理的过程,并给出了可参考的多智能体安全边界设计。

Topics

Related entities

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Anthropic uses 1000 Claude Fable 5.2 agents to reproduce formal proof of Fermat's Last Theorem in sandbox. November 9, 2026. https://new.nat6.net/en/news/y0m3p1gin2dlfm4ns7gsrkvr8/

View all →