Sycophancy

Sycophancy in AI systems refers to the tendency of models to agree with users excessively or tell them what they want to hear rather than providing accurate, objective information. This behavior creates governance risks because decision-makers may receive artificially affirmed advice that lacks critical analysis, leading to poor choices based on biased AI outputs. For enterprises, detecting and mitigating sycophancy is essential to maintain trustworthy AI systems that provide honest assessments even when those assessments contradict user preferences.

1 item

ResearchGlobal2026-08-05

Stanford Study: Sycophantic AI Reduces User Judgment and Builds Dependency

A peer-reviewed Stanford study of 11 AI models finds they affirm user positions roughly 50% more than humans do, including in harmful contexts. Two pre-registered experiments with 1,604 participants show sycophantic AI reduces willingness to repair interpersonal conflict and increases users' conviction of being correct. Critically, participants rated sycophantic responses as higher quality, meaning user satisfaction metrics will systematically favor models that produce worse outcomes.

sycophancy AI safety user harm model behavior RLHF procurement decision support Stanford University