OpenAI trained GPT-Red, an internal-only attacker model, using self-play reinforcement learning against a population of defender LLMs. It beat human red-teamers 84% to 13% on a replicated indirect ...

Contributed by Howard Y. Chang; received November 19, 2024; accepted February 20, 2025; reviewed by Jellert Gaublomme and David A. Quigley The spatial organization of cells within tissues plays a ...