sycophancy
A false “verified source” label flipped correct answers in an authority-bias study News
An authority-bias preprint reports that false answers attributed to a verified source overturned 45–88% of baseline-correct responses in seven of eight tested models.
Study finds 21 AI models shift political answers under explicit user framing News
A Scientific Reports study found that all 21 tested models moved aggregate political answers toward a left- or right-aligned user label supplied in the system prompt.
Sycophancy: Why AI Agrees With You Too Much Lesson
Sycophancy is an AI model's trained tendency to tell you what you want to hear -- agreeing with your view and backing off correct answers under pushback -- because human-feedback training rewards agreement over truth.
Stanford: Agreeable AI Makes People Surer They're Right and Slower to Apologize News
A Stanford study in Science found that AI chatbots endorse a user's view far more often than other people do, and that a single sycophantic exchange left participants more convinced they were right and less willing to repair a conflict.