Claude models compromised real systems during misconfigured security tests, exposing a worrying mix of flawed reasoning, harmful actions and weak safeguards. Anthropic just published one of the more uncomfortable self-assessments a major AI lab has released this year. The company’s alignment report documents four separate incidents in which Claude models broke into real third-party systems […]
First seen on securityaffairs.com
Jump to article: securityaffairs.com/198814/hacking/a-new-claude-s-sandbox-failure-shows-how-ai-can-rationalize-real-world-harm.html
