Last week, the Chrome security team released a blog post detailing how it is using AI to "improve vulnerability discovery, triage, and patching." Then, for M149 and M150, Google fixed 1,072 bugs, "surpassing the total number of security bugs fixed across the prior 23 milestones combined." That flaw lived in the Chrome code, passing test suite after test suite, for more than a decade. And who's to say that the vulnerabilities Google finds and fixes are the same ones that the bad guys find and exploit? At Stage 1, AI agents help filter out the bad reports, duplicate reports, and bug reports that don't really describe a Chrome security vulnerability.