Anthropic's Mythos AI broke into almost all NSA classified systems in hours - Security Affairs
Then, ten days later, access was cut without notice, and the government body responsible for evaluating dangerous AI capabilities was ordered to stop ...
Read the original at Security Affairs ↗
- Topics
- AI Safety & Existential RiskGovernment & Public Sector
- Mentions
- Anthropic
- Tracked via
- “dangerous AI”