数字利维坦:生成式人工智能的意识形态风险与治理路径——以ChatGPT为例  

Digital Leviathan:The Ideological Risk and Governance Path of Generative Artificial Intelligence——Taking ChatGPT as an Example

作　　者：刘锐 Rui Liu

机构地区：[1]上海交通大学人文艺术研究院

出　　处：《新媒体与社会》2024年第1期342-352,403,共12页New Media and Society

基　　金：国家社科基金重大项目“中国特色国际传播战略体系构建研究”(项目编号:22ZDA087);上海社科规划项目“计算政治对舆论安全的挑战及治理”(项目编号:2022BXW004);上海交通大学文科青年人才培育计划项目“百年大变局下西方对华舆论战新态势、新策略研究”(项目编号:2023QN020)。

摘　　要：ChatGPT的诞生,标志着人类信息传播迎来了一次全新的革命性变革,但其引发的意识形态风险及对社会治理的挑战亦不容忽视。本文聚焦这种由技术引发的数字利维坦效应,以ChatGPT为例,分析生成式人工智能的意识形态风险生成机制,将其划分为技术生成机制造成的意识形态风险、制度权力介入引发的意识形态风险以及媒介使用因素引发的意识形态风险共三大类,并就如何走出生成式人工智能的“科林格里奇困境”,提出破解数字利维坦困局的建议:以审慎包容为治理原则,未雨绸缪,兼顾治理与发展;增加主流媒体信息供给,提升主场驾驭能力;健全智能治理机制,为全球治理贡献中国方案;建立技术控制标准,规范数据和算法模型使用。The birth of Chapter marks a revolutionary change in human information dissemination,but the ideological risks and challenges it brings to social governance cannot be ignored.This article focuses on the digital Leviathan effect caused by technology,using Chatgpt as an example to analyze the ideological risk generation mechanism of generative artificial intelligence.It is divided into three categories:ideological risk caused by technology generation mechanism,ideological risk caused by institutional power intervention,and ideological risk caused by media use factors.Suggestions for breaking through the“Corinthian Dilemma”of generative artificial intelligence are proposed:taking prudence and inclusiveness as the governance principle,taking precautions,and balancing governance and development;Increase the supply of mainstream media information and enhance the ability to control the home field;Establish sound intelligent governance mechanism and contribute China’s solutions to global governance;Establish technical control standards and standardize the use of data and algorithm models.

关 键 词：数字利维坦 生成式人工智能 意识形态风险 治理 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] G206[自动化与计算机技术—控制科学与工程]