註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Ori Press
@ori_press
ML Researcher @nebiusai PhD from @bethgelab
加入 December 2018
445 正在關注    608 粉絲
LMs can play chess, but they can't really explain their moves well (chess engines can't at all). Our new BinProp scaffold tackles this, and nearly triples LMs’ score on our chess-explanation benchmark. It works on other games too! Try it on your own games on our site-🧵👇
顯示更多
0
7
58
11
轉發到社區