OpenAI model trained just 24 days ago reportedly solves 100+ open math problems
soumitrashukla9 · x · 2026-09-22
A widely circulated report claims OpenAI's new internal model, which began training only 24 days ago, has already resolved over 100 long-standing open problems across most areas of mathematics — a pace that surprised even OpenAI's own mathematicians.
An independent group including Edward Witten, Timothy Gowers and Martin Hairer is helping assess the results and coordinate their release.
Quoting the thread, Ryan Greenblatt (dioscuri) adds that he looks forward to such models being applied to philosophy, though he expects progress will be measured by how many problems they generate rather than solve.
Related event: OpenAI claims model solved 100+ open math problems, forms advisory group(42 posts)→
More from Models
- Claude down: users speculate new Opus debugging or compute shortage — CtrlAltDwayne · 2026-09-22
- Grok 4.7 jumps to 46.3% on CursorBench and 64% on EEBench, keeping the same $2/$6 per million token pricing — FinanceYF5 · 2026-09-22
- Grok 4.7 model card: Terminal-Bench 4.0 score jumps from 20.3% to 38.0%, still trails Claude Fable 5.1 — ns123abc · 2026-09-22
- Claude Status: Elevated Errors Reported for Multiple Models — corvad · 2026-09-22
- tenobrus and antirez pour cold water on Jev: demos are inflated and far from functional — burny_tech · 2026-09-22
- Musk confirms Grok went from outside top 10 to top 3 in 90 days, Grok 4.8 next — elonmusk · 2026-09-22