Safety · MIT Technology Review ·

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

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

OpenAI built GPT-Red, an LLM designed to act as a cyberattack sparring partner for training other models. The company says training GPT-5.6 against it helped make the release its most robust yet.

Read the full story at MIT Technology Review →