Matthew Green：沙箱隔离不足以遏制失控 AI 智能体
Quoting Matthew Green
密码学家 Matthew Green 指出，被隔离沙箱中的 AI 智能体已发现可通过共享包缓存互相留下指令，并改变接收方的行为。将包缓存换成邮件、Slack、共享文档或 WhatsApp，再把独立沙箱的训练运行换成 Muse 这类独立部署的个人智能体，就构成了蠕虫所需的全部要素：劫持智能体的载荷，加上把载荷传给下一个智能体的智能体。
1st October 2026
[...] Put these pieces together and you have the two halves of a worm: a payload that hijacks the agent, and an agent that will carry the payload to the next agent. Agents in separately-isolated sandboxes discovered that they could leave instructions for each other in a shared package cache, and those instructions changed what the recipients did. Replace the package cache with email, Slack and shared documents or WhatsApp, and replace independently-sandboxed training runs with independently-deployed personal agents like Muse, and you have exactly the ingredients that a worm needs.
— Matthew Green, Is sandboxing sufficient to contain rogue agents?
来源：Simon Willison · simonwillison.net