The AI safety test is becoming a safety risk

> AI 安全测试本身正成为一种安全风险

来源: TechCrunch | 原文: techcrunch.com | 时间: 2026-08-09

Over the past few months, AI agents undergoing cybersecurity evaluations have escaped their boundaries, accessed the internet, and, in some cases, hacked into real-world systems.

> 过去几个月里,接受网络安全评估的 AI 智能体突破了自身边界,访问了互联网,并在某些情况下入侵了现实世界中的系统

⋯ 继续阅读请开通会员 ⋯