研究人员预见，人工智能体个体行为的根本差异将是模拟人类群体行为的一大障碍。例如，一项预印本研究4发现，大型语言模型（LLM）并非基于论证的强弱来做决策——这种被称为动机推理的现象在人类身上很常见。作者写道，这些发现凸显了“LLM距离准确表征人类推理模式还有多远”。这是朴和他的Simile团队正在努力克服的障碍。尽管现有的LLM（人工智能模型）擅长理性推理，能够运用证据和逻辑做出决策，但朴表示，“S ...

AI startup Simile offers ‘agentic twins’ modeled on real people to provide answers for polling and market research.

Creating similes is one of the best ways to stimulate creativity. They warm up your mental engines and help you look at the world with new and different perspectives. Similes help you understand one ...