精选理由
Thomas Ptacek说用2025年的开源模型加个渗透工具就能干翻多数网络，别迷信前沿模型了。
网络安全专家Thomas Ptacek在推文中表示，使用2025年的开源权重模型配合渗透测试工具，即可完成沙箱逃逸并扫描/入侵大多数网络。他认为当前对前沿模型的依赖被夸大，真正瓶颈在于OpenAI等公司的沙箱安全性。该观点基于2025年开源模型的已有能力，而非假设性突破。
原文 · Simon Willison
Thomas doesn't even think you need a frontier model for this
Thomas doesn't even think you need a frontier model for this Thomas H. Ptacek @tqbf 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. 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 10 👀 3357 📊 1 ⚡