AI Weekly Malaysia

Back to items Summaries

Quoting Thomas Ptacek

ID
7052
Status
new
Published
23 Jul 2026, 7:59 AM
Fetched
29 Jul 2026, 6:50 AM
Provider
Simon Willison
Category
developer-ai
Original URL
https://simonwillison.net/2026/Jul/22/thomas-ptacek/
Source URL
https://simonwillison.net/atom/everything/

Excerpt

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, openai-hugging-face-incident

Summary

No summary yet. It will appear after the daemon summarizes this item.

Top