註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Daniel Lenton
@DanielLenton1
Founder @letsunifyai | YC
加入 December 2019
279 正在關注    2K 粉絲
OpenClaw, Hermes Agent and Prime Agent don't meaningfully learn from experience. On Continual-ARC, our new benchmark at @letsunifyai, none of them were able to memorize anything of value and none were able to generalize to new tasks. Training a small 9B model's weights did both.
顯示更多
0
595
1.5K
527
轉發到社區