We propose sycophancy leads to less discovery and overconfidence through a simple mechanism: When AI systems generate responses that tend toward agreement, they sample examples that coincide with users’ stated hypotheses rather than from the true distribution of possibilities. If users treat this biased sample as new evidence, each subsequent example increases confidence, even though the examples provide no new information about reality. Critically, this account requires no confirmation bias or motivated reasoning on the user’s part. A rational Bayesian reasoner will be misled if they assume the AI is sampling from the true distribution when it is not. This insight distinguishes our mechanism from the existing literature on humans’ tendency to seek confirming evidence; sycophantic AI can distort belief through its sampling strategy, independent of users’ bias. We formalize this mechanism and test it experimentally using a rule discovery task.
20:02, 27 февраля 2026Наука и техника
，推荐阅读咪咕体育直播在线免费看获取更多信息
Уточняется, что это уже четвертый разведывательно-ударный беспилотник MQ-9 Reaper, который Иран перехватывает с начала эскалации конфликта.
第二财季净利润达到20.35亿美元，同比增长13.8%；摊薄后每股收益为4.58美元，两项数据均高于市场预测。前6个月净利润为40.36亿美元，同比增长12.55%，摊薄后每股收益9.08美元。
# 'product': ['iPhone 15 Pro']