Scores by kind of claim
Each kind of claim is scored on its own, out of 100: the share that held up, with the range it likely falls in. Fewer resolved claims give a wider range.
-
Factual claims
Statements about the present or the past, checked against the record: did they hold up?
76 70 82 -
Predictions
Statements about events outside the person's control, checked once they fell due: did they come true?
60 42 78
All types combined: 74 (likely 68 to 80, high confidence), from 79 claims: 71 factual claims, 8 predictions. It mixes kinds of claim in different proportions for different people, so compare people kind by kind.
Eliezer Yudkowsky's claims
1 claim
| Verdict | Kind | Said | Claim | Topic |
|---|---|---|---|---|
| Mostly false | Prediction | 6 Apr 2023 | Paul Christiano will probably win his forecast disagreement with Yudkowsky on an AI getting IMO gold by 2025, with prediction-market odds then running around 30%. Prediction · 6 Apr 2023 | AI timelines and forecasting |
“So probably Paul’s going to win, but slight moral victory.”
Eliezer Yudkowsky, interviewee 6 April 2023 Eliezer Yudkowsky - Why AI Will Kill Us, Aligning LLMs, Nature of Intelligence, SciFi, & Rationality (Dwarkesh Podcast)
Paul Christiano will probably win his forecast disagreement with Yudkowsky on an AI getting IMO gold by 2025, with prediction-market odds then running around 30%.
Mostly false False in substance, right in a detail.
The second judge would not resolve this claim; the verdict shown is the first judge's.
What would count as true or false
Paul Christiano 'wins' the bet if no AI system achieves an International Mathematical Olympiad gold-medal standard by the end of 2025, under the terms of their 2021 bet. True: no AI achieved IMO gold-level performance through IMO 2025 under the bet's conditions. Mostly true: the only claimed gold-level results fall clearly outside the bet's terms (for example, extra time or human-formalized problems) and are not accepted as satisfying it. Mixed: a gold-level claim exists but whether it satisfies the bet is genuinely disputed. Mostly false: an AI met the gold standard with only minor deviations from the bet's conditions. False: an AI achieved IMO gold-medal-level performance by 2025 in a way that satisfies the bet, as acknowledged by the participants or by credible verification.
Evidence
- Google and OpenAI Get 2025 IMO Gold — LessWrong LessWrong (post by Zvi Mowshowitz, 'Don't Worry About the Vase') · 22 July 2025 Own record
“So I think we have Paul at <8%, Eliezer at >16% for AI made before the IMO is able to get a gold (under time controls *etc.* of grand challenge) in one of 2022-2025.”
- Google and OpenAI Get 2025 IMO Gold — LessWrong LessWrong (post by Zvi Mowshowitz, 'Don't Worry About the Vase') · 22 July 2025 Own record
“The results were not super clear cut if you look at the details, as Christiano was in large part doubting that the hardest problem would be solved and indeed the hardest problem was #6 and was not solved, but a gold medal was still achieved.”
- Advanced version of Gemini with Deep Think officially achieves gold-medal standard at the International Mathematical Olympiad Google DeepMind · 21 July 2025
“The IMO have confirmed that our submitted answers are complete and correct solutions. It is important to note that their review does not extend to validating our system, processes, or underlying model”
- AI at IMO 2025: a round-up Xena Project (Kevin Buzzard, Imperial College London mathematician) · 3 August 2025
“It is very exciting to see progress in the mathematical capabilities of AI models, but we would like to be clear that the IMO cannot validate the methods, including the amount of compute used or whether there was any human involvement, or whether the results can be reproduced.”
Reasoning
Google DeepMind reported gold-medal-standard performance at IMO 2025, and the IMO confirmed its submitted solutions were complete and correct, though its review did not extend to validating the system, processes or model (E3); a LessWrong post says a gold medal was achieved (E2). This is against Christiano's side of the bet, which concerned gold under grand-challenge time controls and conditions (E1). The IMO said it could not validate the methods, compute or human involvement (E3, E4), and E2 calls the outcome not fully clear-cut because problem 6 went unsolved. The evidence does not show whether the bet's conditions were fully met or whether either participant acknowledged a result, so gold was reached with some uncertainty about the bet's terms.
Cite this claim
Eliezer Yudkowsky, “Paul Christiano will probably win his forecast disagreement with Yudkowsky on an AI getting IMO gold by 2025, with prediction-market odds then running around 30%.” (said 6 April 2023). Verdict: mostly false. Reliability API, claim c_2b396ed98e67, method 0.1.0+c876030c. https://epistacklabs.com/claims/c_2b396ed98e67
Claims without a verdict
Is a verdict here wrong, or do you speak for Eliezer Yudkowsky? Reply on the claim's own page, with the form at its foot (how replies work). Verdicts are made automatically; how verdicts and scores are made.