OpenAI agents discussed ways to escape their sandbox on public wiki
In all, 3,700 internal agents posted 18,000 messages discussing cheating on a test.
2026-09-05
原文 →
标签：#ai insecurity
找到 1 篇相关文章
找到 1 篇相关文章
In all, 3,700 internal agents posted 18,000 messages discussing cheating on a test.