注册并分享邀请链接,可获得视频播放与邀请奖励。

Bryan Bischof fka Dr. Donut
@BEBischof
Leading AI @theoryvc; Teach ML @rutgersu. Prev: Led AI @_hex_tech; Led Data @weights_biases, ML @stitchfix, Led Data @bluebottleroast
加入 December 2010
2.8K 正在关注    5.4K 粉丝
I know this is about thinking traces but before thinking traces this was a really effective tool for improving cot in tool calling cases. After thinking models this trick became useful for explaining caveats or uncertainties.
显示更多
guys you do know you can just disable thinking, and instead give it a "deep_think" tool, and it will call it with internal CoT reasoning format right? gl fixing that