Lean proof may not map 1-to-1 to paper: GPT formalization takes shortcuts on hard lemmas
ctjlewis · x · 2026-10-08
Pushing back on claims that GPT-6 repaired Peter Bel's incorrect Navier-Stokes proof, Elliot Glazer says he's moderately persuaded the Lean proof isn't 1-to-1 with the English paper, weakening the 'deformalization' theory. He notes that when asked to formalize a paper, GPT often focuses on the headline result and takes shortcuts on hard-to-formalize lemmas.
Related event: Researchers Question Lean Verification of GPT's Navier-Stokes Proof(2 posts)→
More from Research
- Full Slides Released for ECCV'26 Tutorial on Diffusion Model Post-Training and Alignment — CSProfKGD · 2026-10-08
- Norvig's Classic Essay on Chomsky and the Two Cultures of Statistical Learning Still Reads Fresh in the LLM Era — 3scorciav · 2026-10-08
- DatologyAI open-sources Zephon, cutting data-order noise from 0.82 to 0.05 points when GPU count changes — lmoroney · 2026-10-08
- ProactiveCoach: Hierarchical Guidance Boosts Proactive AI Assistants by 57.1 Points — skku · 2026-10-08
- STEPQuant: 6-bit quantization of Delta-rule recurrent states cuts serving memory by up to 68.7% — zju-community · 2026-10-08
- RoboQuest Benchmark: Best Multimodal Agent Succeeds in Only 23% of Embodied Exploration Tasks — declare-lab · 2026-10-08