Get our breaking news email, free app or daily news podcast
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.
。业内人士推荐币安_币安注册_币安下载作为进阶阅读
В двух аэропортах на юге России ввели ограничения на полеты14:55。同城约会是该领域的重要参考
«Рассмотреть вопросы: о закреплении необходимости обязательной отработки по специальности для выпускников строительных ВУЗов, получивших образование за счет средств бюджета», — говорится в проекте.
Pikachu and Poké Ball