AI 精选动态
智能评分 60
Mozilla 测试 Claude Mythos 发现 400+ 安全漏洞
AI 推荐理由
展示了 AI 在大型代码库中发现长期隐藏漏洞的实际效果，附有可复现的 setup 方法。核心解读
Mozilla 在 Fable 发布前秘密测试 Claude Mythos 模型，针对 Firefox 的 1000 万行代码库，修复了超过 400 个安全漏洞，包括隐藏超过十年的漏洞。Mozilla 杰出工程师 Brian 介绍了 agentic bug-finding 的配置方法。
全文
Marc Andreessen 🇺🇸 (@pmarca) 转发了 claire vo 🖤 (@clairevo) 的帖子：
Before Fable got released (and pulled) @mozilla was quietly testing Claude Mythos against Firefox's 10M line codebase.
The result? Over 400 security bugs fixes, including ones that had been hiding in the codebase for over a decade.
@bgrins, distinguished engineer at Mozilla, walked me through the agentic bug-finding harness behind the model. His take? It was 50% mythos / 50% setup.
In this ep, Brian walks through:
- why you can't just point a model at 10M lines of code
- how to write a good goal/loop pattern
- killing false positives with a verifier
- why it's good to "lie to the agent"
And guess what? This isn't magic - you can write your own similar harness in less than an afternoon.
Watch now on YT: https://t.co/pBQJZHIM6D
https://video.twimg.com/amplify_video/2069128079151439872/vid/avc1/1920x1080/tPrexq3ACwDNvuqf.mp4?tag=28