uk-aisi

The UK's AI Safety Institute published an independent evaluation confirming Anthropic's Claude Mythos is highly effective at finding security vulnerabilities. The evaluation revealed a linear relationship: more tokens spent equals more exploits discovered, transforming security into an economic arms race.

The UK's AI Safety Institute reports Claude Mythos Preview achieved a 73% success rate on expert-level capture-the-flag cybersecurity challenges and became the first AI model to complete a full 32-step simulated corporate network takeover, succeeding in 3 out of 10 attempts. The testing occurred in environments without active security monitoring or defenders.