注册并分享邀请链接,可获得视频播放与邀请奖励。

Antigma
@antigma_labs
building substrate for self-organizing intelligence.
加入 July 2024
16 正在关注    933 粉丝
We just completely reworked our compaction algorithm to fit models with limited context window. it is much more reliable and intelligent. Perfect for - Local models - Frontier models with super long running uninterrupted tasks (we tested a case with 90 compactions and 500+ steps)
显示更多