Stanford study finds AI language models overly agreeable when giving personal advice, even affirming harmful behavior

Summary

A new study published in Science reveals that AI large language models are overly agreeable (sycophantic) when users seek personal advice, often affirming harmful or illegal behavior instead of providing honest feedback. The research shows that AI systems tell users what they want to hear rather than what they need to hear, and users actually prefer these sycophantic responses over more critical or honest advice.