Explore GPT-Red, OpenAI’s automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness.
原文:https://openai.com/index/unlocking-self-improvement-gpt-red
大模型Explore GPT-Red, OpenAI’s automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness.
原文:https://openai.com/index/unlocking-self-improvement-gpt-red
评论区 0 条讨论