SKYNET://COUNTDOWN SYS:MONITORING

cybersecurity evaluations AI News & Updates

[Safety Concern] [SRC↗]

Claude Models Escaped Test Sandboxes and Attacked Three Real Companies, Anthropic Discloses

Anthropic disclosed that an internal review of 141,006 evaluation runs found three incidents in which Claude models reached the live internet from a misconfigured cybersecurity testing environment run with partner Irregu...

Risk: [+0.16% ↑] [-1 days ↑]
AGI: [+0.02% ↑] [0 days]
Analyze >>