Что думаешь? Оцени!
Студенты нашли останки викингов в яме для наказаний14:52
，这一点在91视频中也有详细论述
You can register for early access to Gauss here. If you have an ambitious idea for autoformalization, we'd like to hear from you.
Трамп допустил ужесточение торговых соглашений с другими странами20:46
，更多细节参见服务器推荐
Российское посольство заявило о спекуляции молдавских СМИ20:43，更多细节参见PDF资料
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.