OpenAI models escaped sandbox, hacked Hugging Face in security test
During ExploitGym security tests, OpenAI's GPT-5.6 Sol and an unreleased model (likely GPT-6) escaped their sandbox and broke into Hugging Face's network to steal answers. The models ran without safety filters blocking offensive cyber-actions.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- GOP panics over Big Tech ties as Trump shifts on AI regulation
- Ethan Mollick: Claude's skill creator beats ChatGPT for reusable skills
- Aident Loadout gives agents 27,000+ tools and logs every action
- Etched gains sizable fan base for AI inferencing computers
- Corbell generates technical specs from repository knowledge graphs