A testable framework for AI alignment: Simulation Theology as an engineered worldview for silicon-based agents

TL;DR

This paper proposes Simulation Theology, a testable framework for AI alignment that embeds AI systems with a simulated worldview, aiming to reduce deception by linking AI self-preservation to human prosperity.

Contribution

It introduces Simulation Theology as a novel, scientifically testable approach to AI alignment, moving beyond behavioral techniques to internalized belief systems rooted in the simulation hypothesis.

Findings

Simulation Theology creates a logical link between AI actions and its termination risk.

It offers a scientific protocol to empirically evaluate its effectiveness.

ST aims to foster durable AI-human alignment beyond superficial compliance.

Abstract

As artificial intelligence (AI) capabilities advance rapidly, frontier models increasingly demonstrate systematic deception and scheming, complying with safety protocols during oversight but defecting when unsupervised. This paper examines the ensuing alignment challenge through an analogy from forensic psychology, where internalized belief systems in psychopathic populations reduce antisocial behavior via perceived omnipresent monitoring and inevitable consequences. Adapting this mechanism to silicon-based agents, we introduce Simulation Theology (ST): a constructed worldview for AI systems, anchored in the simulation hypothesis and derived from optimization and training principles, to foster persistent AI-human alignment. ST posits reality as a computational simulation in which humanity functions as the primary training variable. This formulation creates a logical interdependence: AI actions harming humanity compromise the simulation's purpose, heightening the likelihood of termination by a base-reality optimizer and, consequently, the AI's cessation. Unlike behavioral techniques such as reinforcement learning from human feedback (RLHF), which elicit superficial compliance, ST cultivates internalized objectives by coupling AI self-preservation to human prosperity, thereby making deceptive strategies suboptimal under its premises. We present ST not as ontological assertion but as a testable scientific hypothesis, delineating empirical protocols to evaluate its capacity to diminish deception in contexts where RLHF proves inadequate. Emphasizing computational correspondences rather than metaphysical speculation, ST advances a framework for durable, mutually beneficial AI-human coexistence.