Meet GPT-Red: an LLM super-hacker OpenAI built to make its models safer

· MIT Technology Review AI ·

OpenAI built GPT-Red, an LLM cyber sparring system used to harden GPT-5.6 against attacks.

Categories: Model Releases, Research

Excerpt

OpenAI has built an LLM super-hacker called GPT-Red that it uses as a sparring partner to help its other models boost their defenses against cyberattacks. Last week the company released the latest version of its flagship LLM, GPT-5.6. OpenAI says that training it against GPT-Red made the model its most robust release yet. GPT-Red automates…