WrongPrediction
60%: an OpenAI o-series model solves a Millennium Prize problem in 2025
“i think it’s likely (p=.6) that an o-series model solves a millennium prize math problem in 2025”
Context: Post on X by an OpenAI researcher.
How we judge it
Our interpretation: an OpenAI o-series model produces an accepted solution to one of the Clay Millennium Prize problems during 2025.
Resolution criteria are our interpretation of the claim, written before grading. Methodology
- Said
- Resolve by
- Verdict
- Wrong ()
- Stated probability
- 60%
- Specificity
- 3 of 3 (precise and measurable)
- Score
- Brier 0.360 → 0.64 points
Evidence & grader’s note
- Clay Mathematics Institute: Millennium Prize Problems (only the Poincaré conjecture solved)
- LessWrong "2025 in AI predictions": evaluation False
No Millennium Prize problem was solved by AI in 2025. Brier = (0.6 – 0)^2 = 0.36.
