Critics Question Lean Verification Details in OpenAI's Math Results

Gary Marcus pressed for details on how many solutions actually passed Lean verification in OpenAI's math results. Critics argued Lean serves only as an independent post-hoc check on agentic loop outputs, not as genuine proof search.

2026-10-07 ~ 2026-10-07 · 3 related posts

• altryne challenges Gary Marcus: Lean proofs only verify, they don't generate the results — altryne · 2026-10-07
• Gary Marcus probes math AI claims: how many solutions were tried and passed through Lean? — GaryMarcus · 2026-10-07
• Critic dissects OpenAI's IMO pipeline: one-shot generation plus auto-formalization, not proof search — GaryMarcus · 2026-10-07