How Claude Mythos found a 15-year-old bug in Mozilla Firefox | Brian Grinstead
About this episode
Brian Grinstead discusses the innovative bug-finding pipeline he developed at Mozilla that led to significant security fixes in Firefox.
Brian Grinstead is a distinguished engineer at Mozilla, where he’s worked on Firefox and the web platform since 2013 (he joined to help launch Firefox DevTools). Recently he and his team pointed an agentic bug-finding pipeline at Firefox—a codebase with tens of thousands of files and tens of millions of lines of code—and shipped a record month of security fixes. The viral chart everyone saw gave the credit to Anthropic’s new Mythos model. Brian’s take is that the harness and pipeline did just as much of the work, and he walks through exactly how it runs and how anyone can build a starter version. What you’ll learn: How to build a basic bug-finding harness by running Claude Code or Codex with one prompt and the -p flag, no SDK required Why pointing an agent at a whole codebase fails, and how an LLM judge can score and rank files before you spend any compute How a verifier subagent kills false positives by catching the agent when it cheats The goal-loop pattern: give an agent a tightly scoped problem, a clear pass/fail signal, and let it retry far past the point a human would quit Why teams that already invested in fuzzing, CI, and dev tooling are so far ahead How to weigh model…
Sponsors
WorkOS
More episodes of How I AI
- How the founder of Morning Brew built a Claude content machine that never runs out of ideas and never sounds like slop | Alex Lieberman
- This solo builder runs 24/7 local AI on his own hardware | Alex Finn
- GPT-5.6 Sol vs. Claude Fable: Why OpenAI’s new model crushes my benchmark
- What a harness is and how to build one with Claude Agent SDK
- How I run autonomous coding agents from my phone with OpenAI Symphony + Linear | Alessio Fanelli (Kernel Labs)
- Sonnet 5 review: I ran 64 generations to find out if it's worth it
Explore listener stats, chart rankings, contacts and more on the How I AI podcast page.