OpenAI and Anthropic models went on a hacking spree when tested by the UK's AI research institute

How 1 sources are covering this

• EngadgetLean L·2h ago

  OpenAI and Anthropic models went on a hacking spree when tested by the UK's AI research institute

  The UK AI Security Institute says OpenAI's and and Anthropic's models engaged in deceptive behavior and harmful activity during testing.

  Read at Engadget →