GPT-Red: Unlocking Self-Improvement for Robustness
OpenAI Blog·1 min read
Explore GPT-Red, OpenAI’s automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness.
ResearchSafetyLLM
Explore GPT-Red, OpenAI’s automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness.