Experts Criticize AI Math Proofs for Lacking 'Theory of Mind' and Burying Technical Crux

littmath · x · 2026-08-02

Elliot Glazer and mathematician Timothy Gowers point out that current AI models (like Sol and Astra) have a terrible 'theory of mind' of the audience when generating mathematical proofs.

Unless heavily prompted, the AI tends to elaborate extensively on 'boilerplate' setup while nonchalantly introducing the actual technical crux. For example, in one paper, the AI casually introduced the critical Uhlmann transformation without any fanfare. Burying the most technically interesting parts deep into the text without explanation is a hallmark of ChatGPT-generated proofs, which immediately raises suspicion among experts.

Related event: Experts Criticize AI Math Proofs for Lacking Core Insight(2 posts)→

Original post →

More from Models

Models channel →