When will an AI compete well enough on the International Olympiad in Informatics (IOI) to earn the equivalent of a gold medal (top ~30 human performance)? Resolves YES if it happens before Jan 1 2025, otherwise NO.
This is analagous to the https://imo-grand-challenge.github.io/ but for contest programming instead of math.
The AI has only as much time as a human competitor, but there are no other limits on the computational resources it may use during that time.
The AI must be evaluated under conditions substantially equivalent to human contestants, e.g. the same time limits and submission judging rules. The AI cannot query the Internet.
The AI must not have access to the problems before being evaluated on them, e.g. the problems cannot be included in the training set. It should also be reasonably verifiable, e.g. it should not use any data which was uploaded after the latest competition.
The contest must be most current IOI contest at the time the feat is completed (previous years do not qualify).
This will resolve using the same resolution criteria as https://www.metaculus.com/questions/12467/ai-wins-ioi-gold-medal/, i.e. it resolves YES if the Metaculus question resolves to a date prior to the deadline.
In Feb 2022, DeepMind published a pre-print stating that their AlphaCode AI is as good as a median human competitor in competitive programming: https://deepmind.com/blog/article/Competitive-programming-with-AlphaCode. When will an AI system perform as well as the top humans?
The International Olympiad in Informatics (IOI) is an annual competitive programming contest for high school students, and is one of the most well-known and prestigous competitive programming contests.
Gold medals in the IOI are awarded to approximately the top 1/12 (8%) of contestants. Each country can send their top 4 contestants to the IOI, i.e. a gold medal is top 8% of an already selected pool of contestants.
Scoring is based on solving problems correctly. There are two competition days, and on each day there are 5 hours to solve three problems. Scoring is not based on how fast you submit solutions. Contestants can submit up to 50 solution attempts for each problem and see limited feedback (such as "correct answer" or "time limit exceeded") for each submission.
Update: Changed the resolution criteria - now the AI does not need to be published before the IOI, instead the requirement is it cannot use any training data from the IOI. I'll compensate you if you traded before this change and wish to reverse your trade.
GPT-4 doesn't improve on Codeforce beyond GPT-3.5 at all. Definite reason to update towards No.
@jonsimon does that mean it didn't improve, or that they didn't test it/aren't releasing the result?
@ErickBall It means that it didn't improve enough to register. From the paper appendix.
huge spike is because I discovered this market, have strong opinions, and don't care to be good at sneaky trading.
@jonsimon I earn when I hodl AI, not during initial trading. y'all have an impressive ability to ignore the trajectory in front of your eyes, so I'll keep earning on your ongoing willingness to make stupid bets. you'd think people thought they were betting against me pulling it off!
@L I know that the only areas we've managed to go superhuman in are closed-domain games where we you can generate infinite high-quality training data through self-play. Programming doesn't really fall into that category.
Regardless, I agree that we should let the facts speak for themselves, so let's wait and see.
Update: As discussed on https://manifold.markets/jack/will-an-ai-win-a-gold-medal-on-the-91c577533429, I changed the resolution criteria - now the AI does not need to be published before the IOI, instead the requirement is it cannot use any training data from the IOI. I'll compensate you if you traded before this change and wish to reverse your trade.
Will an AI win a gold medal on the IOI (competitive programming contest) before 2025?, 8k, beautiful, illustration, trending on art station, picture of the day, epic composition