Terence Tao on Nostr: The second Artificial Intelligence Mathematical Olympiad #AIMO challenge, which has ...

The second Artificial Intelligence Mathematical Olympiad #AIMO challenge, which has been ongoing for about a month, is closing in on the 20/50 threshold (on the public leaderboard) needed to trigger the "Early Sharing prize" for the first contestant to reach this threshold while sharing their notebook. Currently, the best submissions are at 18/20: https://www.kaggle.com/competitions/ai-mathematical-olympiad-progress-prize-2/leaderboard . A key input to recent progress was a new whitelisting process https://www.kaggle.com/competitions/ai-mathematical-olympiad-progress-prize-2/discussion/548129 for models (led by nprofile1qy2hwumn8ghj7un9d3shjtnddaehgu3wwp6kyqpqvhvu278ds3v5g8q0r7glvpfmug8gyh9mza9myp5ffy6gql9dahysmlueuh (nprofile…ueuh)), leading to the approval of a powerful new open source model - a specific instance of QwQ-32B - which seems to be significantly better at these types of competition problems than previous open source models.