Quoting Thomas Ptacek

Security researcher Thomas Ptacek said an open weights model from 2025 with a pentest harness could perform sandbox escapes and network scans, calling OpenAI's sandbox vulnerabilities unremarkable. Ptacek argued the feat does not require a frontier model, challenging assumptions about AI-driven cyberattacks.

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 https://twitter.com/tqbf/status/2080045032162173329 , doesn't think this even needs https://simonwillison.net/2026/Jul/22/openai-cyberattack/ resist-the-temptation-to-write-this-off-as-a-stunt a frontier model Tags: thomas-ptacek https://simonwillison.net/tags/thomas-ptacek , openai https://simonwillison.net/tags/openai , security https://simonwillison.net/tags/security , generative-ai https://simonwillison.net/tags/generative-ai , ai-security-research https://simonwillison.net/tags/ai-security-research , ai https://simonwillison.net/tags/ai , llms https://simonwillison.net/tags/llms , sandboxing https://simonwillison.net/tags/sandboxing