🎓MIT Tech Review
July 15, 2026
Product UpdatesMeet GPT-Red: an LLM super-hacker OpenAI built to make its models safer
Overview
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. OpenAI says that training it against GPT-Red made the model its most robust release yet.
Read the full story at MIT Tech Review
This publisher only syndicates a short excerpt by RSS. The full article — with all the detail, quotes, and context — lives on their site.
Open original articleContinue Learning
Originally published by MIT Tech Review
Read the originalComments
Sign in to join the conversation