Alexandr Wang · @alexandr_wang · X·2026-09-11 10:01·44分钟前
AI 导读

Muse 安全架构让用户能大量控制 AI 智能体何时需要请求 human-in-the-loop 审批。

Alexandr Wang@alexandr_wang
40AI 编辑部评分,满分 100
2026-09-11 10:01· 44分钟前
AI 导读

Muse 安全架构让用户能大量控制 AI 智能体何时需要请求 human-in-the-loop 审批。

our muse security architecture enables a ton of control over when the agent needs to ask for human-in-the-loop approval

see more from the goat @bigT_sheesh:

Tarek SheashaIn the blog post and video (https://research.meta.ai/blog/security-and-safety-for-ai-agents-our-approach-with-muse) I posted earlier this week on the @Muse secu...

来源:Alexandr Wang· x.com