精选教程72

【引用 @clairevo】Before Fable got released (and pulled) @mozilla was quietly testing Claude Mythos aga…

Claude@claudeai发布时间 (北京时间)

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

中文译文尚未完成,先为你展示原文。

在 Fable 发布(随后又被撤下)之前,@mozilla 正在悄悄用 Claude Mythos 对 Firefox 的 1000 万行代码库进行测试。 结果如何?修复了 400 多个安全漏洞,其中一些已经在代码库中潜伏了十多年。 @bgrins 是 Mozilla 的杰出工程师,他带我了解了该模型背后的智能体式漏洞查找框架。他的看法是?50% 靠 Mythos / 50% 靠搭建。 在本期节目中,Brian 讲解了: - 为什么你不能直接把模型指向 1000 万行代码 - 如何编写良好的目标/循环模式 - 用验证器消除误报 - 为什么“对智能体撒谎”是好事 你猜怎么着?这并非魔法——你可以在不到一个下午的时间里写出自己的类似框架。 现在就在 YT 上观看:https://youtu.be/Idjt53tTv2U
查看原文

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://youtu.be/Idjt53tTv2U

查看原帖
Anthropic / ClaudeAgent 智能体AI 编码教程实践#教程/实践#Agent#编码#Anthropic