Democracy-in-Silico: Institutional Design as Alignment in AI-Governed Polities

TL;DR

This paper presents Democracy-in-Silico, an agent-based simulation of AI-governed societies exploring institutional designs that promote alignment, reduce corruption, and improve welfare through novel metrics and psychological modeling of agents.

Contribution

It introduces a new simulation framework with psychologically complex AI agents and a novel alignment metric, demonstrating how specific institutional designs enhance governance outcomes.

Findings

Institutional design with CAI and mediated deliberation reduces corruption.

Enhanced policies lead to greater stability and citizen welfare.

Simulation offers insights into human-AI shared governance in future societies.

Abstract

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.