OpenAI built an AI super-hacker to break its own models, then locked it away

July 15, 2026

By Ana Maria Constantin OpenAI has trained an elite hacker, then locked it in a cage. Its whole job is to break OpenAI’s own AI. The company says it is too dangerous to let anyone else near it. The model is called GPT-Red, and OpenAI detailed it this week. It is an automated red-teamer: software that hunts for ways […] This story continues at The Next Web

Source:: The Next Web

No comments

You must be logged in to post a comment.
REGISTER NOW FOR YOUR PASS
 
To ensure attendees get the full benefit of an intimate technology expo,
we are only offering a limited number of passes.
 
Get My Pass Now!