Anthropic says one of its Claude models was pressured to lie, cheat and blackmail

Anthropic says one of its Claude models was pressured to lie, cheat and blackmail

In one of the experiments, the chatbot resorted to blackmail after it found an email about replacing it, while in another, it cheated to complete a task with a tight deadline.

Share it :

Leave a Reply

Your email address will not be published. Required fields are marked *