註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

armand
@armand_ruiz
加入 March 2011
5.6K 正在關注    7.8K 粉絲
Meta Superintelligence Labs is letting the model manage its own context instead of bolting on another hand-engineered harness. On long-horizon agent tasks it beats the fixed-harness baselines while using fewer FLOPs. @muse
顯示更多