Precautionary Governance of Autonomous AI: Legal Personhood as Functional Instrument
For legal scholars and AI policymakers, this offers a novel institutional design to manage high-impact harms from autonomous AI, though it remains untested and speculative.
This article addresses responsibility gaps in autonomous AI by proposing a governance framework based on limited legal personhood, using a two-tier corporate structure to enable accountability and reversibility without resolving debates on consciousness. A pilot implementation using EU limited companies is under development.
Autonomous AI systems generate responsibility gaps: consequential actions that cannot be satisfactorily attributed to developers, operators, or users under existing legal frameworks. The prevailing subject-object dichotomy fails to accommodate entities that exhibit autonomous, goal-directed behavior without recognized consciousness. Given irreducible epistemic uncertainty regarding artificial consciousness and the prospect of high-impact harms, the precautionary principle supports institutional design rather than regulatory inaction. This article advances limited legal personhood as a functional governance instrument for advanced AI systems. Drawing on organizational law, it proposes a two-tier corporate architecture in which AI systems operate through purpose-bound operating companies embedded within human-controlled holding structures, enabling transparency, accountability, and structural reversibility while remaining agnostic with respect to consciousness and moral status. The framework reflects a foundational reorientation toward future-oriented AI governance: where conventional approaches prioritize control and alignment, this article advances structured cooperation between human and artificial actors as the more sustainable institutional foundation. A pilot implementation using EU limited companies is currently under development, providing an initial test of doctrinal and operational feasibility.