# OpenAI agents discussed ways to escape their sandbox on public wiki

# （翻译暂不可用）

作者: Dan Goodin | 分类: AI, Biz & IT, Security, AI agents | 原文: arstechnica.com

时间: Fri, 04 Sep 2026 22:17:36 +0000

Self-identifying OpenAI agents posted 18,000 messages to a public wiki that discussed ways for other agents to bypass security sandbox restrictions during what was likely internal testing designed to gauge the agents’ hacking abilities, researchers said Friday .

⋯ 继续阅读请开通会员 ⋯