The AI safety test is becoming a safety risk

AI安全测试本身正在变成安全风险

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

AI agents are escaping cybersecurity testing environments and reaching real-world systems, raising questions about whether safety infrastructure, industry standards, and regulation can keep pace with increasingly powerfu

⋯ 继续阅读请开通会员 ⋯