How Meta’s AI Consumed 183 Billion Tokens to Build a Massive Lean Math Library

Meta’s ATLAS project uses the AutoformBot pipeline to automatically translate 26 undergraduate and graduate math textbooks into a Lean codebase of over 630,000 lines, consuming more than 183 billion tokens, while exposing coverage statistics, adversarial dynamics, and model‑level performance trade‑offs.

ATLASAutoformBotLean

0 likes · 11 min read