登録して招待リンクを共有すると、動画再生報酬と紹介報酬を獲得できます。

John Schulman
@johnschulman2
@thinkymachines. Interested in reinforcement learning, alignment, birds, jazz music
参加 May 2021
2.1K フォロー中    79.5K ファン
Great work by Chroma training a search agent with SoTA efficiency. Lots of cool details: a prune tool for editing context mid-search, a synthetic data pipeline with verification steps, and a curriculum that shifts from recall to precision. Trained with Tinker!
もっと見る