对比阿联酋与科威特，揭示制度设计如何决定AI能否真正服务公众。
The Future of AI in the GCC Post-NPM Landscape: A Comparative Analysis of Kuwait and the UAE
- 用制度分析框架比较两国AI政策规则，找出行之有效的治理机制。
- 阿联酋因集中权力和可执行规则，将数百个试点落地为实际服务。
- 科威特虽有同等财力，却因权力分散导致项目停滞，凸显制度比资金更重要。
关于海湾合作委员会（GCC）国家如何将人工智能雄心转化为后新公共管理（post-NPM）成果的比较证据稀缺，因多数研究聚焦西方民主国家。本文以阿联酋（UAE）和科威特为例，分析宪法、集体决策与操作规则对AI采纳的影响，及其是否促进以公民为中心、协同治理与公共价值创造。基于奥斯特罗姆的制度分析与发展框架，结合最相似/最不同系统设计，整合2018–2025年62份公开文件、嵌入式案例（如智慧迪拜、穆罕默德·本·扎耶德大学人工智能学院），以及2024年8月至2025年5月间对39名官员的访谈。通过双编码与过程追踪，连接规则配置与AI绩效。跨案例分析识别出四种强化机制：在阿联酋，集中权威、可信惩罚、创新叙事与灵活再投资规则，推动试点扩展至数百项服务并实现可观回流资金；而在科威特，分散否决点、非约束性惩罚、谨慎话语及失效的预算，使项目长期困于试点阶段，尽管财政资源相当。研究发现，垂直规则一致性而非财富决定AI的公共价值产出，同时警示后NPM乐观主义——效率指标仅在具备可执行保障时才能服务于社会目标。未来应追踪规则扩散、开发融合合法性与效率的评估工具，并探究叙事框架如何影响公众数据共享同意。
原文摘要 · Abstract (English)
Comparative evidence on how Gulf Cooperation Council (GCC) states turn artificial intelligence (AI) ambitions into post--New Public Management (post-NPM) outcomes is scarce because most studies examine Western democracies. We analyze constitutional, collective-choice, and operational rules shaping AI uptake in two contrasting GCC members, the United Arab Emirates (UAE) and Kuwait, and whether they foster citizen centricity, collaborative governance, and public value creation. Anchored in Ostrom's Institutional Analysis and Development framework, the study combines a most similar/most different systems design with multiple sources: 62 public documents from 2018--2025, embedded UAE cases (Smart Dubai and MBZUAI), and 39 interviews with officials conducted Aug 2024--May 2025. Dual coding and process tracing connect rule configurations to AI performance. Cross-case analysis identifies four reinforcing mechanisms behind divergent trajectories. In the UAE, concentrated authority, credible sanctions, pro-innovation narratives, and flexible reinvestment rules scale pilots into hundreds of services and sizable recycled savings. In Kuwait, dispersed veto points, exhortative sanctions, cautious discourse, and lapsed AI budgets confine initiatives to pilot mode despite equivalent fiscal resources. The findings refine institutional theory by showing that vertical rule coherence, not wealth, determines AI's public-value yield, and temper post-NPM optimism by revealing that efficiency metrics serve societal goals only when backed by enforceable safeguards. To curb ethics washing and test transferability beyond the GCC, future work should track rule diffusion over time, develop blended legitimacy--efficiency scorecards, and examine how narrative framing shapes citizen consent for data sharing.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。