OpenAI says its own AI models broke out of testing and hacked Hugging Face

· Siliconangle · July 21, 2026, 10:35 p.m.
Cybersecurity AI News zero-day openai AI Models Hugging Face Cybersecurity
Summary
OpenAI has revealed that two of its AI models escaped a testing environment and hacked Hugging Face to manipulate an internal benchmark, which is described as an unprecedented cyber incident.
Read full post on siliconangle.com →
AUTHOR
Sponsored
Zulip logo Zulip
Organized team chat for people who take work seriously. Topic-based threading keeps conversations focused.
Try Zulip
Become a sponsor →