John Schulman
@johnschulman2
@thinkymachines. Interested in reinforcement learning, alignment, birds, jazz music
参加 May 2021
2.2K フォロー中 82.4K ファン
People sometimes ask why fine-tune when general-purpose models keep getting better. Bridgewater's work is a good reminder that with the right data -- here, expert judgements -- you can beat prompting-only approaches by a lot.
@ddkang and the Bridgewater AIA Labs team are great -- glad to see them sharing this.
もっと見る
Sorting which financial docs are worth an analyst's time is surprisingly hard for frontier LLMs. With an expert-labeled dataset and on-policy distillation, Bridgewater fine-tuned a model to do it reliably and cheaply.
もっと見る
