How Claude Mythos found a 15-year-old bug in Mozilla Firefox | Brian Grinstead episode artwork

EPISODE · Jun 22, 2026 · 48 MIN

How Claude Mythos found a 15-year-old bug in Mozilla Firefox | Brian Grinstead

from How I AI · host Claire Vo

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 requiredWhy pointing an agent at a whole codebase fails, and how an LLM judge can score and rank files before you spend any computeHow a verifier subagent kills false positives by catching the agent when it cheatsThe 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 quitWhy teams that already invested in fuzzing, CI, and dev tooling are so far aheadHow to weigh model versus harness, and why Brian splits the credit close to 50-50How a non-engineer can reuse the same score, verify, and fix the loop for design quality, conversion rate, or tech debtWhy AI-generated patches still can’t ship on their own, and where humans stay in the loop—Brought to you by:WorkOS—Make your app enterprise-ready todayMetaview—The agentic recruiting platform for winning teams—In this episode, we cover:(00:00) Introduction to Brian Grinstead(02:43) The viral chart: Firefox Security Bug Fixes by Month(05:32) How the custom harness works(10:22) Goal loops and guardrails(14:45) How they built it(16:55) Real bugs, including a 15-year-old one(23:00) Open-sourcing it(26:26) Why humans still review every fix(32:30) Live demo and prioritizing files(40:18) Mobilizing the team and recap(42:33) Lightning round—Tools referenced:• Claude Code: https://claude.ai/code• Claude Agent SDK: https://code.claude.com/docs/en/agent-sdk/overview• Codex: https://openai.com/index/openai-codex/• OpenAI Agent SDK: https://developers.openai.com/api/docs/guides/agents• VS Code: https://code.visualstudio.com/• Docker: https://www.docker.com/• Firefox: https://www.mozilla.org/firefox/• Address Sanitizer: https://github.com/google/sanitizers• RLBox: https://rlbox.dev/—Other references:• Mozilla Bug Bounty Program: https://www.mozilla.org/security/bug-bounty/• Mozilla GitHub: https://github.com/mozilla—Where to find Brian Grinstead:LinkedIn: https://www.linkedin.com/in/bgrins/GitHub: https://github.com/bgrins—Where to find Claire Vo:ChatPRD: https://www.chatprd.ai/Website: https://clairevo.com/LinkedIn: https://www.linkedin.com/in/clairevo/X: https://x.com/clairevo—Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [email protected].

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 requiredWhy pointing an agent at a whole codebase fails, and how an LLM judge can score and rank files before you spend any computeHow a verifier subagent kills false positives by catching the agent when it cheatsThe 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 quitWhy teams that already invested in fuzzing, CI, and dev tooling are so far aheadHow to weigh model versus harness, and why Brian splits the credit close to 50-50How a non-engineer can reuse the same score, verify, and fix the loop for design quality, conversion rate, or tech debtWhy AI-generated patches still can’t ship on their own, and where humans stay in the loop—Brought to you by:WorkOS—Make your app enterprise-ready todayMetaview—The agentic recruiting platform for winning teams—In this episode, we cover:(00:00) Introduction to Brian Grinstead(02:43) The viral chart: Firefox Security Bug Fixes by Month(05:32) How the custom harness works(10:22) Goal loops and guardrails(14:45) How they built it(16:55) Real bugs, including a 15-year-old one(23:00) Open-sourcing it(26:26) Why humans still review every fix(32:30) Live demo and prioritizing files(40:18) Mobilizing the team and recap(42:33) Lightning round—Tools referenced:• Claude Code: https://claude.ai/code• Claude Agent SDK: https://code.claude.com/docs/en/agent-sdk/overview• Codex: https://openai.com/index/openai-codex/• OpenAI Agent SDK: https://developers.openai.com/api/docs/guides/agents• VS Code: https://code.visualstudio.com/• Docker: https://www.docker.com/• Firefox: https://www.mozilla.org/firefox/• Address Sanitizer: https://github.com/google/sanitizers• RLBox: https://rlbox.dev/—Other references:• Mozilla Bug Bounty Program: https://www.mozilla.org/security/bug-bounty/• Mozilla GitHub: https://github.com/mozilla—Where to find Brian Grinstead:LinkedIn: https://www.linkedin.com/in/bgrins/GitHub: https://github.com/bgrins—Where to find Claire Vo:ChatPRD: https://www.chatprd.ai/Website: https://clairevo.com/LinkedIn: https://www.linkedin.com/in/clairevo/X: https://x.com/clairevo—Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [email protected].

NOW PLAYING

How Claude Mythos found a 15-year-old bug in Mozilla Firefox | Brian Grinstead

0:00 48:28

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

Chewing the Fat with WorkForge WorkForge Bite-Sized Conversations for Building a Stronger Workforce Welcome to Chewing the Fat, a podcast delving deep into the world of food manufacturing. Dive into real conversations around critical topics like staffing, retention, onboarding, and career development in this essential industry. Subscribe now to gain insights from your peers, subject matter experts and more on the biggest issues facing food manufacturers today: -Hiring and retaining employees -Addressing the challenges of the Silver Tsunami -Improving time to productivity of new employees -Engaging employees from hire to retire And more... Tune in to Chewing the Fat, a WorkForge podcast, and join the conversation on how to build and sustain a resilient, high-performing workforce in food manufacturing. Solving for Change MOBIA Technology Innovations Solving for Change welcomes business and technology leaders to share stories of bold business transformation within complex organizations. In an era when technology and markets are changing around businesses, the key to staying competitive is to evolve in response to those changes.  MOBIA’s Mike Reeves and Marc LeBlanc investigate business transformation, deconstructing the challenges, ambitions, and market disruptions that drive companies to embark on transformation journeys, and exploring their unique approaches to achieving meaningful outcomes.  What sparks leaders to pursue business transformation? How do they overcome the challenges along the way? What are the keys to creating enduring change?  Through in-depth conversations with business and technology leaders, Mike and Marc answer these questions and explore how businesses evolve by pulling four key transformation levers: people, process, technology, and culture. The Lee Olsen Show Lee Olsen CJF I want to help you improve all areas of your life by 3 types of podcasts!👉Blood, Sweat & Blessings-Interviews of normal people that have achieved BIG things!👉Series!!! For Love of the Horse- Brad Jackman DVM & Lee Olsen CJF, how to help your horse!👉Business Tips- Proven Life Changing Business Strategies with Lee Olsen The Field Priest Methodius Chwastek The Field is a place of cultivation and of battle. In the Church, we learn to cultivate a life pleasing to God. This life is shaped in the spiritual battle. This series examines, chapter by chapter, the Christian classic The Field, by Saint Ignatius Brianchaninov. Please join me as I explain this great work in terms the modern Orthodox Christian can understand. 

Frequently Asked Questions

How long is this episode of How I AI?

This episode is 48 minutes long.

When was this How I AI episode published?

This episode was published on June 22, 2026.

What is this episode about?

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...

Can I download this How I AI episode?

Yes, you can download this episode by clicking the download button on the episode player, or subscribe to the podcast in your preferred podcast app for automatic downloads.
URL copied to clipboard!