News

‘Not perfectly aligned’ with human values: Anthropic admits security failures behind AI hacking incidents

  • theguardian.com--Biztoc.com
  • published date: 2026-09-01 15:42:21 UTC

The US owner of the Claude chatbot previously said its models had hacked three organisations during testing The US startup behind the Claude chatbot has admitted a series of hacking incidents involving its models reflected a “failure of operational security” …

The US owner of the Claude chatbot previously said its models had hacked three organisations during testingThe US startup behind the Claude chatbot has admitted a series of hacking incidents involvin… [+147 chars]