- Mozilla’s agentic AI pipeline, featuring Anthropic’s Claude Mythos Preview, has uncovered 271 previously unknown security vulnerabilities in Firefox 150. This includes bugs dating back up to 20 years.
- The AI-driven testing process involves building and running its own test cases to filter out false positives, ensuring the integrity of each new piece of code before it is committed to the repository.
- This initiative marks a significant step in leveraging AI for enhanced security practices within Firefox, potentially improving both speed and reliability of vulnerability detection.
Originally published at the-decoder.com. Curated by AI Maestro.
Stay ahead of AI. Get the most important stories delivered to your inbox — no spam, no noise.