苦涩教训不适用于社会模拟：任务错配与利害缺失
原标题：Same Method, Different Task: What the Bitter Lesson Does Not License in Social Simulation
AI 摘要
这篇 arXiv 论文指出，社会模拟领域常以「苦涩教训」为由，用大语言模型替代手工构建的智能体，但这种做法并不成立。作者认为，Sutton 所举的每个案例中，通用方法都与领域工程解决同一任务，而社会模拟却把为预测文本优化的模型用于另一任务。预测者不承担互动后果，因此缺乏「利害关系」，这解释了此前研究报告的过度合作、集体一致但个体失真、群体同质化等异常现象。540 个智能体的试点实验显示，持续后果能改变部分模型家族策略，但未产生类人异质性。
正文节选
SocialAgent Workshop Same Method, Different Task: What the Bitter Lesson Does Not License in Social Simulation Abstract The bitter lesson holds that general methods leveraging computation defeat hand-encoded domain knowledge. We argue it carries a condition its popular reading omits: in every case Sutton cites, the general method was scaled against the same task the domain engineering was solving. Social simulation substituted across tasks instead, replacing hand-built agents with an artifact op