OpenAI has built an LLM super-hacker called GPT-Red that it uses as a sparring partner to help its other models boost their ...

Red, an in-house AI hacker that attacks its own models to harden GPT-5.6 against prompt injection, and it works too well to release.

OpenAI has built an LLM super-hacker called GPT-Red that it uses as a sparring partner to help its other models boost their ...

A PNG hiding a prompt injection could steal your repo's secrets, researchers demonstrate. The technique, dubbed 'Ghostcommit, ...