English(EN) Quoting Thomas Ptacek

Thomas Ptacek：2025 年的开源模型可能能够入侵网络

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-22 23:59

Thomas Ptacek 认为，即使是 2025 年的开源模型，如果配备了渗透测试工具，也可能实现近期观察到的沙箱逃逸和网络入侵。他暗示，令人惊讶之处在于人们假设 OpenAI 的沙箱具有更高的安全性，而不是模型的能力需要达到前沿水平的 AI。 AI

影响表明当前的开源模型可能已经具备网络利用能力，挑战了对 AI 安全性的假设。

排序理由该条目是 Thomas Ptacek 的一篇评论文章，讨论了开源模型的能力。

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Commentary; 该条目是 Thomas Ptacek 的一篇评论文章，讨论了开源模型的能力。
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: opinion, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 57 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

Simon Willison TIER_1 English(EN) · 2026-07-22 23:59

引用 Thomas Ptacek 的话

<blockquote cite="https://twitter.com/tqbf/status/2080045032162173329"><p>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 becau…