返回全部动态
为何不能简单将失控AI隔离于互联网之外
原标题：Why can’t we just keep rogue AIs off the internet?
AI 摘要
文章探讨为何不能简单地将失控AI与互联网隔离（air gap）。研究者指出，严格气隙虽能提升测试安全性，却会降低真实性和实用性，因为现实评估常需访问外部API和服务。气隙成本高、拖慢研究，且无法消除模型内部潜在风险，还可能被USB等方式突破。专家主张采用分层隔离而非一刀切方案。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
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? Why can’t we just keep rogue AIs off the internet? Air-gapping AI to keep it away from real-world targets makes testing safer, but less useful. Why ca
发布时间：2026-09-24 22:30
抓取时间：2026-09-24 23:15
来源机构：The Verge