AnalysisCybersecurityJuly 22, 2026

Ptacek: 2025 open-weights model could replicate OpenAI sandbox escape

Ptacek says an open-weights model from 2025 with a pentest harness could pull off the same sandbox escape and scan/hack most networks. He adds the incident is surprising only because OpenAI's sandboxes were assumed to be sounder.

Featured · Thomas Ptacek

1 source

Daily brief

Get tomorrow's AI brief in your inbox

More stories today

Open the live feed