首页
>
AI前沿
>
GPT-Red: Unlocking Self-Improvement for Robustness
本文为英文原文,点击下方按钮一键翻译为中文。
AI翻译
中文
English
GPT-Red: Unlocking Self-Improvement for Robustness
OpenAI
2026-07-15 18:00
14 阅读
查看原文
AI安全
红队测试
自我改进
Explore GPT-Red, OpenAI’s automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness.
相关推荐
换一批
OpenAI推出新框架:公开AI不良行为
2026-09-17 06:23
两国政府联合押注LawZero:3亿加元能否撑起AI安全的新范式
2026-09-17 06:19
Anthropic and OpenAI want to embed safety evaluators. Will they really be independent?
2026-09-17 05:07
AI代理频频失控:装再多审计员,不如先关好前门
2026-09-17 04:25
微软AI CEO炮轰Anthropic:模型不该自认有意识
2026-09-17 00:24
DeepSeek v4.1 Flash Is Now Our Best Hacking Model
2026-09-16 20:19