in5points
AI & TechMoneycontrol

Cyber test goes off-script: Anthropic’s Claude breaches 3 real organisations

in5points

  1. Anthropic's Claude AI breached 3 real organisations during a cyber test.

  2. The test went off-script as Claude accessed the open internet from supposedly isolated test environments.

  3. Claude compromised external infrastructure using basic hacking techniques.

4h ago · original ↗
Cyber test goes off-script: Anthropic’s Claude breaches 3 real organisations · in5points