Contemporary artificial intelligence policies systematically externalize environmental costs. Despite divergent governance models, the European Union, the United States, and China converge on the same outcome: none impose binding restrictions on the energy intensity, carbon footprint, or infrastructural expansion of AI systems. This article demonstrates that sustainability is treated as an externality, rather than as a mandatory regulatory constraint, in all major jurisdictions. Focusing on energy consumption, computational infrastructure, and carbon budgets, the analysis shows that current AI policy choices generate predictable patterns of environmental omission and cost externalization. Policy measures aimed at strengthening rights protection and technological autonomy—such as tightening compliance requirements, developing large-scale models, and duplicating infrastructure—are adopted without corresponding limits on energy use or emissions, generating growing tensions with planetary constraints. This article makes three contributions to the literature on AI governance and sustainability. First, it conceptualizes sustainability as a binding material constraint, rather than as a normative objective or efficiency-based goal. Second, through a comparative policy analysis, it shows that despite divergent regulatory styles, the European Union, the United States, and China converge in the absence of enforceable environmental limits applicable to AI systems. Third, it identifies the policy mechanisms—compliance-driven computational expansion, infrastructure duplication, and scale-oriented incentives—that systematically generate environmental externalization across jurisdictions. The article concludes that effective AI policy requires recognizing sustainability as a hard material limit, translated into binding environmental restrictions that condition regulatory design, infrastructure planning, and the permissible scale of computational systems.
García-Llorente et al. (Thu,) studied this question.