Ptacek: 2025 open-weights model could escape OpenAI's sandbox
Security researcher Thomas Ptacek argues an open-weights 2025 model fitted with a pentest harness could escape OpenAI's sandbox and scan or hack most networks. He adds the outcome is only surprising because one assumes OpenAI has sounder sandboxes.
Featured · Thomas Ptacek
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Anton: self-improving terminal AI agent automates inbox, calendar, reports
- Allie Mellen discusses AI's cybersecurity impact at Black Hat 2026
- Satirical post by Timnit Gebru mocks 'autonomous AGI startup' hype
- AI YouTube Shorts Generator turns long videos into vertical Shorts
- Domain name tool generates 60 creative startup name candidates