The Shepherd Test: How Will SuperIntelligent Agents Balance Care and Control in Asymmetric Relationships?

Djallel Bouneffouf, Matthew Riemer, Kush R. Varshney

Keywords: SuperIntelligent, Trustworthy AI, Agents

TL;DR: This paper proposes the Shepherd Test, a framework for evaluating superintelligent AI through its moral choices in asymmetric, survival-driven relationships.

Abstract: This paper introduces the Shepherd Test, a new conceptual test for assessing the moral and relational dimensions of superintelligent artificial agents. The test is inspired by human interactions with animals, where ethical considerations about care, manipulation, and consumption arise in contexts of asymmetric power and self-preservation. We argue that AI crosses an important, and potentially dangerous, threshold of intelligence when it exhibits the ability to manipulate, nurture, and instrumentally use less intelligent agents, while also managing its own survival and expansion goals. This includes the ability to weigh moral trade-offs between self-interest and the well-being of subordinate agents. The Shepherd Test thus challenges traditional AI evaluation paradigms by emphasizing moral agency, hierarchical behavior, and complex decision-making under existential stakes. We argue that this shift is critical for advancing AI governance, particularly as AI systems become increasingly integrated into multi-agent environments. We conclude by identifying key research directions, including the development of simulation environments for testing moral behavior in AI, and the mathematical formalization of ethical manipulation within multi-agent systems.

Submission Number: 72