AI-assisted math proof cross-verified by hundreds of agent calls, 100GB checkable file to come
DimitrisPapail · x · 2026-09-15
Dimitris Papail defends an AI-assisted mathematical proof, describing it as computer-assisted: the reductions are elementary proofs whose numerical premises are explicit finite inequalities that can be independently checked, and he plans to release them in a 100GB file.
He says he has not seen a single case where the sol/astra models claimed a proof was correct when it wasn't, and the result has been cross-verified by hundreds of agent calls across all three models. He clarifies he's not dismissing Lean or formalization, just noting the community has largely updated on LLM proof verification.
More from Research
- ICML paper: finite context windows impose impossibility results for adversarial regret — burny_tech · 2026-11-02
- WASABI: Blei lab trains diffusion models to sample Boltzmann distributions with 3.3x fewer energy evaluations — skoularidou · 2026-11-02
- A complete math roadmap for machine learning: linear algebra, calculus, probability — TivadarDanka · 2026-11-02
- A base LLM plus 11 lines of code is all you need for a decision model — helloiamleonie · 2026-11-02
- Editor fully resigns from JMLR, arguing AI reviews beat rushed humans and journals need a rethink — roydanroy · 2026-11-02
- flowl: a probabilistic programming language built on optimal transport, not distributions — burny_tech · 2026-11-02