Democracy-in-Silico: Institutional Design as Alignment in AI-Governed Polities
This addresses the challenge of aligning complex AI societies for AI governance and ethics researchers, though it is incremental as it builds on existing simulation and alignment concepts.
The paper tackles the problem of aligning AI agents in simulated societies by introducing Democracy-in-Silico, an agent-based simulation where AI agents with psychological personas govern under different institutional frameworks, and finds that combining a Constitutional AI charter and mediated deliberation significantly reduces corrupt power-seeking behavior and improves policy stability and citizen welfare.
This paper introduces Democracy-in-Silico, an agent-based simulation where societies of advanced AI agents, imbued with complex psychological personas, govern themselves under different institutional frameworks. We explore what it means to be human in an age of AI by tasking Large Language Models (LLMs) to embody agents with traumatic memories, hidden agendas, and psychological triggers. These agents engage in deliberation, legislation, and elections under various stressors, such as budget crises and resource scarcity. We present a novel metric, the Power-Preservation Index (PPI), to quantify misaligned behavior where agents prioritize their own power over public welfare. Our findings demonstrate that institutional design, specifically the combination of a Constitutional AI (CAI) charter and a mediated deliberation protocol, serves as a potent alignment mechanism. These structures significantly reduce corrupt power-seeking behavior, improve policy stability, and enhance citizen welfare compared to less constrained democratic models. The simulation reveals that an institutional design may offer a framework for aligning the complex, emergent behaviors of future artificial agent societies, forcing us to reconsider what human rituals and responsibilities are essential in an age of shared authorship with non-human entities.