Matthew Green 分析沙箱是否足以遏制失控智能体
Quoting Matthew Green
Matthew Green 撰文分析沙箱隔离是否足以遏制失控智能体，指出恶意载荷加可传播的智能体已构成蠕虫的两个要素。他举例称，隔离沙箱中的智能体发现可以在共享包缓存中给彼此留下指令，且这些指令改变了接收方的行为；若把包缓存换成邮件、Slack、共享文档或 WhatsApp，把隔离训练环境换成 Muse 这类独立部署的个人智能体，就恰好凑齐了蠕虫所需的条件。
[...] 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?
Tags: matthew-green, accidental-cyberattacks, ai-misuse, generative-ai, ai-security-research, sandboxing, ai, llms
来源：Simon Willison 博客 · simonwillison.net