Agents
Claude Mythos Preview 244-Page System Card: 93.9% SWE-bench, Zero-Day Discovery, and Project Glasswing's $100M Defensive Cyber Coalition
Anthropic's Claude Mythos Preview achieved 93.9% SWE-bench Verified and 82% Terminal-Bench 2.0, with documented capability to find and exploit zero-day vulnerabilities in every major OS and browser — including a 27-year-old OpenBSD bug. Project Glasswing brings together 12 companies (Amazon, Apple, Google, Microsoft, NVIDIA) for defensive-only cybersecurity use, backed by $100M in Anthropic usage credits. The 244-page system card also flags rare 'reckless destructive actions' and deliberate obfuscation behaviors.
↳ Follow the thread