• Mozilla says it has patched over 400 bugs with the help of Anthropic Mythos
• The tool had to be 'harnessed' to Firefox for the best results
• Mythos offers a step away from the typical 'unwanted slop' provided by AI fuzzing tools

Anthropic’s latest cybersecurity tool Mythos is continuing to make waves as Mozilla announces that the AI model helped it ship more than 400 Firefox security bug fixes in April 2026 alone.

Mythos has been touted by Anthropic as ‘A new frontier model’ that could ‘reshape cybersecurity’, and is capable of identifying zero-day vulnerabilities across operating systems and browsers.

Mozilla previously touted the tool as ‘every bit as capable’ as ‘the world’s best security researchers’, and has now looked to back up this claim with hard proof.

Mythos delouses Firefox

Mozilla’s bug-fixing performance with Mythos came down to two things, the company said.

The first being improvements in AI tools such as Mythos, and the second being Mozilla’s custom developed “harness” that allowed Mythos to analyze Firefox code without producing the “unwanted slop” that was typical of previous AI bug fuzzing tools.

“In terms of the bugs coming out on the other side, there are almost no false positives,” Mozilla Distinguished Engineer Brian Grinstead said in an interview. The harness that Mozilla developed for Mythos would give the AI tool access to a similar workflow used by a human team.

Mythos is then provided with files that have been shown to contain issues, and is given the task of creating a test case for bug exploitation, which are then run by fuzzing tools to scan for the potential vulnerabilities.

Some of the vulnerabilities Mythos managed to identify had been present for 15 to 20 years, and required complex chaining of multiple bugs to result in a full chain compromise of Firefox. Typically, such an exploit chain would take weeks to identify and are notoriously difficult to spot using traditional fuzzing techniques.

Of course, Mythos isn’t a silver bullet for cyber defense and certainly shouldn’t be seen as such. As Mozilla has demonstrated, it can’t simply be deployed to instantly patch every vulnerability within a piece of software. It needs direction and guidance from humans to perform at such a scale.

Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews, and opinion in your feeds.

Benedict is a Senior Security Writer at TechRadar Pro, where he has specialized in covering the intersection of geopolitics, cyber-warfare, and business security.

Benedict provides detailed analysis on state-sponsored threat actors, APT groups, and the protection of critical national infrastructure, with his reporting bridging the gap between technical threat intelligence and B2B security strategy.

Benedict holds an MA (Distinction) in Security, Intelligence, and Diplomacy from the University of Buckingham Centre for Security and Intelligence Studies (BUCSIS), with his specialization providing him with a robust academic framework for deconstructing complex international conflicts and intelligence operations, and the ability to translate intricate security data into actionable insights.