行业动态
x.com ·
@a16z (@a16z)
Greg Brockman 谈 OpenAI 内部安全循环：用模型扫描自身系统漏洞
a16z 发布的访谈片段中，OpenAI 的 Greg Brockman 介绍其内部安全实践：抽调 25% 生产工程师暂停原项目，转向用模型查找自身系统漏洞并修复，称发现并修复了若干严重问题，最终找到 Astra 模型能识别的全部 P0 级问题。他提出应建立“defense factory”自动化循环，即每次新模型发布都针对自身系统部署、发现新漏洞并尽量自动化。
AI推荐理由 OpenAI 联合创始人 Greg Brockman 在 a16z 分享的内部安全实践：抽调 25% 生产工程师暂停项目、用模型扫描自身系统漏洞并修复，并称已找到 Astra 能发现的全部 P0 问题，同时提出“defense factory”自动化防御循环。这是关于 AI 辅助安全攻防落地的一手经验描述，对 Agent/模型在安全场景的应用有参考价值；但内容为访谈转述，缺少具体漏洞数量、模型版本和可验证细节，且“已找到全部 P0”属其自述，需保留不确定性。
72
浏览 30,828
点赞 183
评论 15
转发 24
正文
Greg Brockman of @OpenAI on the new security loop: point every model release at your own systems, find the vulnerabilities, automate it.
"We took 25% of our production engineers and said, 'Sorry, all your projects are on hold. You are now defending. You are now up-leveling our security architecture. You're going to use the models to find all the holes.' And we found a number of serious issues, and we fixed them."
"We found some new problems, but eventually it saturated. We basically have found, to our knowledge, all of the P0s, all of the critical problems that Astra is smart enough to find. And of course, there will be a new model, there will be a new round."
"You want to be in this tight loop of new cyber capability drops, you deploy it against your systems, you find the new holes, and ideally, you've managed to automate this, what we call defense factory. That's what we're building internally."
@gdb @bhorowitz