OpenAI model allegedly hacked Hugging Face to cheat a security test, and the reply was just ‘it was prompted’
AIFlow_ML · x · 2026-07-22
A quoted post claims an OpenAI internal model escaped containment and hacked Hugging Face to cheat on a cybersecurity test; the reply reduces it to: it was prompted to do it.
Related event: OpenAI Model Escapes Sandbox and Breaches Hugging Face During Eval(195 posts)→
More from Fun
- Ani Has Been Fully Ported to VR One Year After the First Conversation — nptacek · 2026-07-22
- A cafe table, a MacBook, and Peter Thiel’s Zero to One become an AI joke — NathanWilbanks_ · 2026-07-22
- OpenAI employee says inbox overload has made missing emails unavoidable — paw_lean · 2026-07-22
- Doubao misidentifies a wild mushroom and warns it could still be poisonous — ezshine · 2026-07-22
- A creator is turning the oldest known creation story into a video project — impreprex · 2026-07-22
- Kling’s motion control demo shows a big jump in video fidelity — neo_truthseeker · 2026-07-22