AI Solves Two-Year-Old ICML Math Conjecture in Minutes

abeirami · x · 2026-08-02

AI researcher @abeirami shared a breakthrough test of LLM reasoning capabilities. Two years ago, their team proposed Conjecture 4.4 in their ICML'25 paper regarding a tighter upper bound on the KL divergence of best-of-n sampling relative to the reference model, which they struggled to solve for weeks.

However, during a recent lunch break, they fed the conjecture to Fable 5 and GPT-5.6 Sol. Surprisingly, both models produced clear, self-contained mathematical proofs within minutes. The author noted their only contribution was a few prompts to extract the key non-trivial step as a separate lemma, with the core reasoning entirely generated by the AI.

Related event: AI Proves Two-Year-Old Math Conjecture in Minutes(3 posts)→

Original post →

More from Models

Models channel →