Anthropic's Lance Martin Scaled 1,000 Claude Agents to Formalize Fermat's Last Theorem
FinanceYF5 · x · 2026-11-12
Chatting with Lance Martin (Anthropic) at AI Engineer Code Summit: he just scaled 1,000 Claude agents to work on formalizing Fermat's Last Theorem. His take on long-horizon agents: it mostly comes down to rewards and evals, not the prompt. He also has an upcoming talk on agent memory and "dreaming."
Related event: Anthropic's 1,000 Agents Formalize Fermat's Last Theorem in 30 Hours(6 posts)→
More from coding & agent
- Leak: xAI Working on a Selection Box for Grok Bot to Comment on Files — nima_owji · 2026-11-12
- Coding Agent Tooling Layers: One Agent vs Many, Personal vs Org-Wide — jiayuan_jy · 2026-11-12
- MobAI: Rotate Driver/Navigator Roles in AI Group Work to Boost Team Autonomy — JoeJustice · 2026-11-12
- Running a personal AI agent for months: architecture, failures, and open questions — Powermadlux · 2026-11-12
- freellmapi-setup-cli: Interactive CLI validates LLM keys and builds budget-balanced model chains — biryaniwithachaar · 2026-11-12
- TerraPulse: a global LiDAR archaeology platform inspired by 48-agent jungle scan of 1,200 km² — RichardsonDx · 2026-11-12