GPT-Red: How OpenAI Built an AI Super-Hacker to Stress-Test Its Own Models
Reading Time: 5 minutesOpenAI has developed GPT-Red, an AI model trained through self-play to act as a super-hacker that stress-tests its other models against cyberattacks, including a novel ‘fake chain of thought’ prompt injection it discovered independently. The system helped make GPT-5.6 significantly more robust, blocking over 77% of attacks that had succeeded against the previous GPT-5.