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。

Nikhil Chandak
@nikhilchandak29
PhD @ Max Planck Institute. Prev: Post-Training @MistralAI Past @iiit_hyderabad @VectorInst. Interested in better evals, forecasting, and open-endedness.
参加 December 2016
573 フォロー中    1.1K ファン
FutureSim cleanly differentiates the performance of the agents on their skill of forecasting with GPT-5.5 dominating. We find open-weights models are significantly overconfident in their predictions, performing worse than the baseline of not submitting any prediction. (4/5)
もっと見る