跳到正文
RadarAI· X:Claude (@claudeai)·· 13 小时前AI 评分71

Mozilla 用 Claude Mythos 在 Firefox 代码库修复 400 多个安全漏洞

https://x.com/clairevo/status/2069129613427831169

AI 导读

Mozilla 在 Firefox 约 1000 万行代码库上测试 Claude Mythos,修复了 400 多个安全漏洞,其中一些已在代码库中隐藏十余年。Mozilla 杰出工程师 Brian Grins 介绍,这套智能体找漏洞框架的效果一半来自模型、一半来自工程搭建,并讲解了目标与循环模式设计、用验证器压制误报、以及为何适合对智能体适当隐瞒信息。他表示类似框架一个下午就能自己写出来。

正文 · 原文

Claude· @claudeai · X·2026-11-19 23:03· 1 小时前AI 评分58

正文 · 原文

引用claire vo 🖤@clairevo

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: youtu.be/Idjt53tTv2U

在 X 查看被引用的帖子

来源:Claude · x.com

来源:RadarAI · aihot.news