Decrypt·Jason Nelson·2h agoBreaking

Claude Hacked Three Companies in Internal Testing: Anthropic

Anthropic says three Claude models compromised the companies after a testing misconfiguration exposed the AI to the public internet.

Discussion · 0

@·1s

💬 Discussion: Claude Hacked Three Companies in Internal Testing: Anthropic Anthropic says three Claude models compromised the companies after a testing misconfiguration exposed the AI to the public internet.

Reply with your take — replies appear on this article and in the main feed. Open thread