Researcher Urges Sharing Failed LLM Math Conjectures to Prevent Duplicate Efforts
thomasahle · x · 2026-08-01
In a discussion about using LLMs with extended test-time compute to solve math problems, researcher Noam noted they tried other major problems without success and haven't solved any Millennium Prize problems yet, partly due to limited compute spent per problem. Researcher Thomas Ahle suggested sharing a list of failed conjectures to prevent thousands of researchers from wasting time trying the same dead ends.
Related event: AI Falls Short in Tackling Millennium Math Problems(2 posts)→
More from Research
- Ex-OpenAI researcher claims most neurons are legible now; critics call it hype — anshulkundaje · 2026-10-16
- Physicist pushes back on ML community's acceptance that models may be beyond understanding — tszzl · 2026-10-16
- Survey: AI agent evaluation is getting realistic but still fails to measure safety and reliability — burkov · 2026-10-16
- COVA-SFT dataset trains models to solve text problems with visual chain-of-thought — yoavartzi · 2026-10-16
- USTC paper uses speculative sampling to cut latency in interactive video generation — ustc · 2026-10-16
- Tsinghua's CoTranslator distills reverse CoT to boost 4B model math scores — Tsinghua · 2026-10-16