Contemporary artificial intelligence (AI) policy suffers from a basic categorical error. Existing frameworks rely on analogizing AI to inherited technology types -- such as products, platforms, or infrastructure -- and in doing so generate overlapping, often contradictory governance regimes. This "analogy trap" obscures a fundamental transformation: certain advanced AI systems no longer function solely as instruments through which existing institutions exercise power, but as de facto centers of power that shape information, coordinate behavior, and structure social and economic realities at scale. This article offers a new conceptual foundation for AI governance by treating such systems as a fourth societal actor -- what we term the "Digital Gorilla" -- alongside People, the State, and Enterprises. It develops a Four Societal Actors framework that maps how power flows among these actors across five power modalities (economic, epistemic, narrative, authoritative, physical) and uses this map to diagnose where AI capabilities disturb established allocations of authority, concentrate power, or erode accountability. Drawing on constitutional principles of separated powers and federalism, the article advances a federalized, polycentric governance architecture and institutionalizes dynamic checks and balances among the four actors, rather than today's more reactive and compliance-driven approaches. Reframing AI governance in this way shifts the inquiry from how to control a risky technology to how to design institutions capable of accommodating these increasingly powerful and autonomous digital systems without sacrificing democratic legitimacy, the rule of law, or the production of public goods, and it recasts familiar debates in administrative, constitutional, and corporate law as questions of power allocation in a four-actor system.

翻译：当代人工智能政策存在一个基本的分类错误。现有框架依赖于将人工智能类比于继承性技术类型——如产品、平台或基础设施——这种做法催生了重叠且往往相互矛盾的治理体系。这种"类比陷阱"掩盖了一个根本性转变：某些先进人工智能系统不再仅仅作为现有机构行使权力的工具，而是作为事实上的权力中心，大规模地塑造信息、协调行为并构建社会与经济现实。本文通过将此类系统视为继人民、国家与企业之后的第四种社会行动者——我们称之为"数字大猩猩"，为人工智能治理提供了新的概念基础。文章构建了一个"四维社会行动者"框架，描绘权力如何通过五种权力形态（经济、认知、叙事、权威、物理）在这些行动者间流动，并运用此框架诊断人工智能能力在何处扰乱了既有的权力分配、集中了权力或削弱了问责机制。借鉴权力分立与联邦主义的宪法原则，本文提出了一种联邦化、多中心的治理架构，在四个行动者之间制度化了动态制衡机制，以取代当前更具反应性且以合规为导向的治理模式。通过这种重构，人工智能治理的研究重心从如何控制风险技术，转向如何设计能够容纳这些日益强大且自主的数字系统，同时不牺牲民主合法性、法治或公共产品生产的制度框架，并将行政法、宪法与公司法中的经典论辩重新诠释为四维行动者体系中的权力分配问题。