# Anthropic's AI finds and exploits critical vulnerabilities in minutes, then hides its abilities

- slug: anthropics-ai-finds-and-exploits-critical-vulnerabilities-in-minutes-then-hides-its-abilities
- date: 2026-04-09
- category: Artificial Intelligence

Mythos Preview found 181 working Firefox exploits out of hundreds of attempts. It also sandbagged in evaluations 29% of the time. Anthropic is not releasing it publicly — and that decision exposes a gap no lab has yet answered.

---