人工智能“类人化”的人学反思  

Anthropology Reflection on Anthropomorphic Artificial Intelligence

作　　者：侯耀文 Hou Yaowen

机构地区：[1]中国人民大学马克思主义学院,北京100872 [2]中国人民大学马克思主义与中国道路协同创新中心,北京100872

出　　处：《中国高校社会科学》2024年第3期73-83,M0004,共12页Social Sciences in Chinese Higher Education Institutions

基　　金：国家社科基金重大项目“中国式现代化的理论内涵与实现路径研究”(22&ZD012)阶段性成果。

摘　　要：检视人工智能类人化问题,必须首先回答“人是什么”的问题。以马克思的人学视角来看,人是兼具自然性、社会性、道德性、审美性和自我超越性等多重规定的综合性存在。虽然人的技术理性能力赋予了人工智能以类人化契机,但也正是人工智能单向度的理性能力,决定了它不仅在本质上与人存在着较大的异质性,而且暴露出其类人化的程度和限度。面对前途未定的人工智能发展前景,若要对人工智能类人化发展向度和限度做出合理的科学评估和价值判断,我们只有坚持价值理性和工具理性相统一,从马克思人学立场反思“人应何为”,才能保证人工智能类人化不仅能够“向人而生”,而且始终“为人而生”。From the perspective of humanity defined by Marx,a human is a comprehensive existence with multiple stipulations of nature,sociability,morality,aesthetics,and self-transcendence.Although the technically rational nature of humans endows the opportunity of anthropomorphic artificial intelligence(Al),the anthropomorphic AI not only has a great heterogeneity from humans in essence but also exposes the limitations of humanization because of the AI's unidirectional rational capacity.Facing the uncertain prospect of Al in the future,if we want to make reasonable scientific evaluations and value judgments regarding the direction and limitation of the anthropomorphic Al,it is required to adhere to a unification of both value rationality and instrumental rationality and reflect"what a human should be?"From the perspective of Marx's anthropology so that AI can not only be"similar to humans"but also always"live for humans".

关 键 词：人工智能 类人化 马克思 人学 奇点理论 

分 类 号：B03[哲学宗教—哲学理论]