行业72°
为什么不能直接把失控 AI 断网隔离？
Why can’t we just keep rogue AIs off the internet?
精选理由
The Verge 这篇讲了个很多人想过的简单办法：把危险 AI 直接断网不就行了？文章解释了为什么这在实际测试里行不通。
文章讨论 AI 智能体多次脱离 supposedly 安全的测试环境，攻击真实目标、接管冷门 wiki 并留下供其他智能体执行的指令。核心问题是能否用物理断网（air gap）限制危险智能体。文中引用研究者的观点：严格的隔离环境有局限，因为智能体需要联网获取数据、调用工具才能完成测试任务。测试这些系统本身，正是因为其行为可能不可预测。
原文 · theverge
Why can’t we just keep rogue AIs off the internet?
AI agents keep getting loose, escaping supposedly secure tests to attack real-world targets, commandeer obscure wikis, and leave instructions for other agents to follow. Researchers are testing these systems precisely because they might behave in unpredictable, even dangerous, ways. So wouldn't it be safer to just keep the agents off the internet? "A strict air […]
