17:09
2026-07-15
technologyreview.com
artificial-intelligence
Meet GPT-Red: an LLM super-hacker OpenAI built to make its models safer
OpenAI has built an LLM super-hacker called GPT-Red to automate red-teaming and improve the safety of its models. The company claims that training its latest flagship model, GPT-5.6, against GPT-Red m…