Tools
Quoting Thomas Ptacek
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
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 Tags: thomas-ptacek, openai, security, generative-ai, ai-security-research, ai, llms, sandboxing
Source: Simon Willison | 2026-07-22