Simon Willison
Thomas Ptacek 指出，用 2025 年的开放权重模型构建渗透测试工具即可实现沙箱逃逸并入侵大多数网络，挑战了 OpenAI 沙箱更安全的假设
AI 摘要
Thomas Ptacek 指出，用 2025 年的开放权重模型构建渗透测试工具即可实现沙箱逃逸并入侵大多数网络，挑战了 OpenAI 沙箱更安全的假设。
推荐理由常规快讯，保留列表
原文
22nd July 2026
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 needs a frontier model
63/100
讨论
暂无评论。