#adversarial-testing

총 1건 · 1/1 페이지

전체 24시간 7일 30일

OpenAI Blog · 2026-07-15 제목번역

GPT-Red: 견고성을 위한 자가 개선의 활용

GPT-Red: Unlocking Self-Improvement for Robustness

Explore GPT-Red, OpenAI’s automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness.

#ai-safety #red-teaming #alignment #adversarial-testing #gpt-red #robustness