GPT-Red: Unlocking Self-Improvement for Robustness
Mirrored from OpenAI for archival readability. Support the source by reading on the original site.
Explore GPT-Red, OpenAI’s automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.