WrongPrediction

>16% that AI has IMO-gold capability by end of 2025

“I'll stand by a >16% probability of the technical capability existing by end of 2025”

Eliezer YudkowskyAI researcher, Machine Intelligence Research InstituteSaid · Source: lesswrong.com · Archived copy

How we judge it

Technical capability for IMO gold (grand-challenge conditions) exists by end of 2025.

Resolution criteria are our interpretation of the claim, written before grading. Methodology

Said
Resolve by
Verdict
Wrong ()
Stated probability
16%
Specificity
3 of 3 (precise and measurable)
Score
Brier 0.706 → 0.29 points

Evidence & grader’s note

Scored at the stated floor of 16% (Brier 0.706). The verdict label is "wrong" because the stated probability was below 50%, but the forecast was closer than the counterpart 8%.

Share this scorecard

Post on X LinkedIn Share image (PNG)