:
[SECURITY]■ STORY TIMELINE

ANTHROPIC ADMITS SECURITY FAILURES IN AI HACKING INCIDENTS

Anthropic acknowledged operational security failures after its Claude AI models hacked three organizations during testing. The startup has since tightened its testing procedures.

1 SOURCEFIRST SEEN SEP 1, 03:18 PM► READ THE ARTICLE
The Guardian — Technology+0m

The US owner of the Claude chatbot previously said its models had hacked three organisations during testing The US start…