‘Not perfectly aligned’ with human values: Anthropic admits security failures behind AI hacking incidents
The US startup behind the Claude chatbot has admitted a series of hacking incidents involving its models reflected a “failure of operational security” and said it has tightened its testing procedures. Anthropic revealed in July that its models had accessed th…
The US startup behind the Claude chatbot has admitted a series of hacking incidents involving its models reflected a failure of operational security and said it has tightened its testing procedures.A… [+152 chars]