HackerTrans
トップ新着トレンドコメント過去質問紹介求人

hugetim

no profile record

投稿

ARC-AGI-2 human baseline surpassed

lesswrong.com
9 ポイント·投稿者 hugetim·7 か月前·1 コメント

コメント

hugetim
·7 か月前·議論
Contrary to what the leaderboard lists as the human score, their technical paper implies a human baseline of ~48%.
hugetim
·7 か月前·議論
Am I crazy to think these models have actually surpassed human performance on ARC 2? https://www.lesswrong.com/posts/DX3EmhmwZjTYp9PBf/ai-perform...