Advances in AI invite the misuse of language models as stand-ins for human minds or participants, which fundamentally mischaracterizes these statistical algorithms. We argue that language models should be embraced as flexible simulation tools, able to mimic a wide range of behaviors, perspectives, and psychological attributes evident in human language data, but the models themselves should not be equated to or anthropomorphized as human minds.

翻译：人工智能的进展引发将语言模型误用作人类思维或参与者的替代品，这从根本上曲解了这些统计算法的本质。我们认为语言模型应被视作灵活的模拟工具——它们能够模仿人类语言数据中呈现的广泛行为模式、观点及心理特征，但模型本身不应被等同于或拟人化为人类心智。