תומאס פטצ'ק על OpenAI

תקציר מקורי באנגלית<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 because you assume OpenAI has sounder sandboxes.</p></blockquote> <p class="cite">&mdash; <a href="https://twitter.com/tqbf/status/2080045032162173329">Thomas Ptacek</a>, doesn't think <a href="https://simonwillison.net/2026/Jul/22/openai-cyberattack/#resist-the-temptation-to-write-this-off-as-a-stunt">this even needs</a> a frontier model</p> <p>Tags: <a href="https://simonwillison.net/tags/thomas-ptacek">thomas-ptacek</a>, <a href="https://simonwillison.net/tags/openai">openai</a>, <a href="https://simonwillison.net/ta