Explore GPT-Red, OpenAI’s automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness.
GPT-Red: Unlocking Self-Improvement for Robustness
Originally reported by OpenAI Blog
Explore GPT-Red, OpenAI’s automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness.
0 comments
No comments yet. Be the first to start the discussion.