Benchmark researcher Ofir Press jokes as AI solves Millennium Problems
Princeton benchmark researcher Ofir Press self-deprecatingly admitted he was too conservative after saying Millennium Prize Problems could serve as benchmarks that would take 100 years to saturate, as OpenAI reportedly solves them; responders note frontier models already excel at counterexample search and disproof.
2026-09-09 ~ 2026-09-11 · 4 related posts
- Ofir Press jokes his "millennium prizes would take 100 years to saturate" benchmark line aged badly — OfirPress · 2026-09-09
- Benchmark researcher Ofir Press jokes he'll stop saying millennium problems are too hard to saturate — OfirPress · 2026-09-09
- Frontier models ace counterexamples but lag on closed-form math, benchmark designer notes — evijit · 2026-09-09
- As OpenAI Chews Through Millennium Problems, Benchmark Researcher Jokes About His Next Eval — OfirPress · 2026-09-11