Meta 首席 AI 官 Alexandr Wang 解释 Muse 智能体的安全沙箱机制
Meta 的 Muse 智能体每个都跑在独立沙箱里，还有个 sentinel 专门拦截信用卡号，做智能体安全的可以看看这套设计
Alexandr Wang 介绍 Muse 智能体的安全设计：每个 Muse 实例运行在独立的 secure VM 沙箱中，用户共享的数据只存储在该沙箱内。当智能体尝试对外发送信息（如填表单或打电话）时，由一个单独的 sentinel 智能体检查并拦截信用卡号、社会安全号等敏感数据。Muse 还要求用户逐一批准其要访问或发送数据的新网站。后续将推出加密等级更高的 confidential VM，目标是达到 WhatsApp 级别的隐私保障，代价是速度可能变慢。
Alexandr Wang (Chief AI Officer at Meta) explains how each Muse runs inside its own "secure VM", a sandboxed, isolated mini computer, and the data you share with it is stored only there.
> Whenever the agent tries to send anything out, like filling a form or making a call, a separate "sentinel" agent checks it and blocks sensitive data such as credit card or Social Security numbers.
> Muse also asks the user to approve every new website it wants to contact or send data to.
> A more encrypted "confidential VM", is coming later with the goal of WhatsApp-level guarantees, though it may be slower.
---- Full video on "Cleo Abram" YouTube channel, (link in comment)
