Quoting Thomas Ptacek

摘要 · I genuinely believe that if you took an open weights model from 2025 and built a pentest harness for it, it could do this kind of sandbox escape and scan/hack in most networks. This is only surprising because you assume OpenAI has sounder sandboxes. — Thomas Ptacek , doesn't think this even ne

阅读原文 · Simon Willison →

开源社区

I genuinely believe that if you took an open weights model from 2025 and built a pentest harness for it, it could do this kind of sandbox escape and scan/hack in most networks. This is only surprising because you assume OpenAI has sounder sandboxes. — Thomas Ptacek , doesn't think this even ne

原文：https://simonwillison.net/2026/Jul/22/thomas-ptacek/#atom-everything

0 条评论 · 观点来自社区

评论区 0 条讨论

以 … 的身份发言

还没有评论，来抢沙发。