Grok 4.5 Finds Counterexample to Math Conjecture
rohanpaul_ai · x · 2026-07-11
Grok 4.5 is described as providing a clear counterexample to a hard math problem, corresponding to a serious research-level conjecture.
The citation mentions it constructed an explicit counterexample to the Poisson semigroup hypercontractivity problem on the 4-sphere. The researcher also noted testing other frontier models—some of which also found counterexamples—but they preferred Grok 4.5's solution because it was explicit, simple, and elegant.
Related event: Grok 4.5 Reportedly Discovers Research-Level Math Counterexample(5 posts)→
More from Models
- MissionReport benchmark: only 3 of 540 AI-generated government reports pass all criteria — Exp_Mark · 2026-10-27
- Local beats cloud: Qwen 3.8 FN handles private student data as well as frontier models — dr_lm · 2026-10-27
- Aidan Gomez: model's CoT said no tool calls right before making them — aidangomez · 2026-10-27
- Nat Lambert: Cohere's model is narrow RL training on internal infra ill-suited for open weights — natolambert · 2026-10-27
- OpenAI teases DOTS is coming to Europe 'soon' — mark_k · 2026-10-27
- Clifford Pickover challenges AI to decipher a message he encoded in Norse runes — pickover · 2026-10-27