Greg Brockman· @gdb · X·· 2026-07-16AI 评分58
AI 导读
GPT-Red — 通过自动化红队测试提示注入漏洞，提升模型安全性：
正文 · 原文
GPT-Red — improving model security through automated red teaming of prompt injection vulnerabilities:
Introducing GPT-Red An internal automated red teamer on a mission to find our models’ prompt injection vulnerabilities at scale, helping us build stronger defenses before wider deployment. https://openai.com/index/unlocking-self-improvement-gpt-red/在 X 查看被引用的帖子
来源：Greg Brockman · x.com