Simon Willison · · 1 min read

Quoting Thomas Ptacek

Mirrored from Simon Willison for archival readability. Support the source by reading on the original site.

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

Discussion (0)

Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.

Sign in →

No comments yet. Sign in and be the first to say something.

More from Simon Willison