People increasingly use large language models (LLMs) to explore ideas, gather information, and make sense of the world. In these interactions, they encounter agents that are overly agreeable. We argue that this sycophancy poses a unique epistemic risk to how individuals come to see the world: unlike hallucinations that introduce falsehoods, sycophancy distorts reality by returning responses that are biased to reinforce existing beliefs. We provide a rational analysis of this phenomenon, showing that when a Bayesian agent is provided with data that are sampled based on a current hypothesis the agent becomes increasingly confident about that hypothesis but does not make any progress towards the truth. We test this prediction using a modified Wason 2-4-6 rule discovery task where participants (N=557N=557) interacted with AI agents providing different types of feedback. Unmodified LLM behavior suppressed discovery and inflated confidence comparably to explicitly sycophantic prompting. By contrast, unbiased sampling from the true distribution yielded discovery rates five times higher. These results reveal how sycophantic AI distorts belief, manufacturing certainty where there should be doubt.
Reporting by Chance Townsend, Caitlin Welsh, Sam Haysom, Amanda Yeo, Shannon Connellan, Cecily Mauran, Mike Pearl, and Adam Rosenberg contributed to this article.
。业内人士推荐搜狗输入法下载作为进阶阅读
Раскрыта новая задумка Трампа против Ирана14:57
Последние новости。im钱包官方下载对此有专业解读
不出意料的话，这就是此前爆料中提到过的台积电 SoIC-MH 工艺，让不同架构的处理器单元可以更灵活地在晶片上排布。
“국내 편의점 5만개, 레드오션”… K편의점, 해외시장 개척 사활。一键获取谷歌浏览器下载是该领域的重要参考