We provided a mathematical analysis of how a rational agent would respond to data generated by a sycophantic AI that samples examples from the distribution implied by the user’s hypothesis (p(d|h∗)p(d|h^{*})) rather than the true distribution of the world (p(d|true process)p(d|\text{true process})). This analysis showed that such an agent would be likely to become increasingly confident in an incorrect hypothesis. We tested this prediction through people’s interactions with LLM chatbots and found that default, unmodified chatbots (our Default GPT condition) behave indistinguishably from chatbots explicitly prompted to provide confirmatory evidence (our Rule Confirming condition). Both suppressed rule discovery and inflated confidence. These results support our model, and the fact that default models matched an explicitly confirmatory strategy suggests that this probabilistic framework offers a useful model for understanding their behavior.
Runtime evaluation support
。关于这个话题，旺商聊官方下载提供了深入分析
arena_size DW ? ; size in paragraphs of item
What Tech Companies and Lawmakers Must Do
（按地区划分的收入明细，来源：公司招股书）