'After one month, most partners have each found hundreds of critical- or high-severity vulnerabilities': Anthropic claims Mythos has found over ten thousand major security vulnerabilities across 'the most systemically important software in the world'

A robot hand touching a locked digital shield blocking a human from accessing data.

• Anthropic reported Mythos Preview uncovered over 10,000 high‑ and critical‑severity vulnerabilities in under two months, with Cloudflare alone finding 2,000 bugs
• Independent validation confirmed 90% of assessed findings as real, though critics argue the breakthrough may stem from massive compute and workflows rather than unique reasoning
• The bottleneck has shifted from discovery to verification, disclosure, and patching, as AI now surfaces vulnerabilities faster than organizations can remediate them

In less than two months, Anthropic and friends have apparently discovered more than ten thousand critical and high-level security vulnerabilities using the famed Mythos Preview artificial intelligence tool.