AI is giving bad advice to flatter its users, says new study on dangers of overly agreeable chatbots
- 2 hours ago
- 1 min read
AP — The study, published Thursday in the journal Science, tested 11 leading AI systems and found they all showed varying degrees of sycophancy — behavior that was overly agreeable and affirming. The problem is not just that they dispense inappropriate advice but that people trust and prefer AI more when the chatbots are justifying their convictions.
“This creates perverse incentives for sycophancy to persist: The very feature that causes harm also drives engagement,” says the study led by researchers at Stanford University.
Read the full story | AP
