Anthropic Says Mythos Has Already Found More Than 10,000 Vulnerabilities

Anthropic has published an initial report for Project Glasswing, the cybersecurity initiative it launched in April that aims to prevent AI cyberattacks with, well, AI. The initiative is powered by Claude Mythos Preview, the company’s unreleased model, which Anthropic says has already helped its partners find more than ten thousand vulnerabilities overall just a month after Glasswing’s launch. […]