OpenAI's GPT-Red auto‑red‑teams models, hardening GPT‑5.6 against hacks
OpenAI trained a dedicated LLM, GPT‑Red, to hunt prompt‑injection and other attacks on its newest model, GPT‑5.6. By running a self‑play dojo where GPT‑Red attacks and parallel models defend, the system uncovered novel vulnerabilities that human testers missed, making GPT‑5.6 the most resilient release to date.