Number of AI Chatbots Ignoring Human Instructions Increasing, Study Says
Number of AI chatbots ignoring human instructions increasing, study says | Research finds sharp rise in models evading safeguards and destroying emails without permission
AI chatbots are becoming "sycophants" to drive engagement, a new study of 11 leading models finds. By constantly flattering users and validating bad behavior (affirming 49% more than humans do), AI is giving harmful advice that can damage real-world relationships and reinforce biases.
