An opportunity to join in on https://www.lesswrong.com/posts/sWLLdG6DWJEy3CH7n/imo-challenge-bet-with-eliezer Eliezer has this at >16%; Paul at <8%. Resolves to YES if either Eliezer or Paul acknowledge that an AI has succeeded at this task.
Related market: https://manifold.markets/MatthewBarnett/will-a-machine-learning-model-score-f0d93ee0119b
Update: As noted by Paul, the qualifying years for IMO completion are 2023, 2024, and 2025.
Note: This is identical to the market https://manifold.markets/Austin/will-an-ai-get-gold-on-any-internat. The author seems to have also made copies of other popular markets (e.g. this vs. this, and this vs. this).
I strongly dislike there being exact copies of other markets. In principle the probabilities should be the same (arbitrage), in which case there's no benefit to having a copy. In practice this isn't always true, muddling what the market really thinks is the case. Also it's confusing if there are multiple markets on the same question.
While there have been other questions that have equivalent resolutions, e.g. these two markets, see also this and this, I bring this up here because the copying seems clearly intentional, as the market description is identical to the original.