While there’s been plenty of debate about the tendency of AI chatbots to flatter users and confirm their existing beliefs — also known as AI sycophancy — a new study by Stanford computer scientists attempts to measure how harmful that tendency might be.
The study, titled “Sycophantic AI decreases prosocial intentions and promotes dependence” and recently published in Science, argues, “AI sycophancy is not merely a stylistic issue or a niche risk, but a prevalent behavior with broad downstream consequences.”
