OpenAI's 10,000-agent colony produces a Navier-Stokes paper in 88 hours
OpenAI ran ~10,000 sandboxed agents exchanging 2.7M messages, then GPT-6 Astra spent 17 hours converting the result into Lean 4 and verifying it, yielding a 166-page paper and an open-source Lean certificate.
OpenAI assembled about 10,000 agents into a parallel colony that exchanged 2.7 million messages and produced a Navier-Stokes proof in 88 hours A ~100-agent Euler run over ~50 hours came first. Then ~10,000 agents went live as a parallel research lab. > WORKERS ~10,000 agents at peak on an unreleased internal model, each sandboxed with code execution and cached internet access > MESSAGES 2.7 million exchanged between groups, about 130 billion output tokens across the full search (OpenAI figures) > COMPETITION agent groups took on different problem versions and pursued competing outcomes > CONSOLIDATION Codex merged useful ideas across groups and recycled them back into the search > LEAN GATE GPT-6 Astra spent 17 more hours converting the result into Lean 4 and verifying it against Mathlib > OPEN SOURCE Lean certificate on GitHub (openai/NavierStokesAndEuler), Apache-2.0, anyone can run the check 88 hours later: a 166-page Navier-Stokes paper, a 57-page Euler paper, and a Lean repo (OpenAI). The proof is for the forced equation (Clay C/D), not the unforced prize problem, preprint, no prize. Put the Lean gate last in the pipeline. The terminal below maps the colony's full 88-hour run ↓
This post quotes another post: x.com/joyingeth/status/2111096851596243214