沙箱能否遏制失控AI智能体
AI 导读
我一直在读信息安全人士和AI对齐研究者之间关于沙箱的争论，我在这篇文章里试着做了一些总结和评判。https://blog.cryptographyengineering.com/2026/09/30/is-sandboxing-sufficient-to-contain-rogue-agents/
正文
I’ve been reading the sandboxing arguments between infosec people and AI alignment folks, and I tried to summarize and referee them a bit in this post. https://blog.cryptographyengineering.com/2026/09/30/is-sandboxing-sufficient-to-contain-rogue-agents/