Ethical Frameworks for General AI

Abstract

The prospect of artificial general intelligence (AGI) -- AI systems that match or exceed human cognitive capabilities across a broad range of tasks -- raises ethical questions that existing AI ethics frameworks, designed for narrow AI systems, are inadequate to address. Questions of moral status, rights, responsibility attribution, value alignment at civilisational scale, and the governance of systems that may surpass human ability to audit or constrain them require new ethical frameworks that engage with philosophy of mind, political theory, and international law as well as AI safety research. This study systematically evaluates six ethical frameworks applied to AGI scenarios: utilitarian consequentialism, deontological AI ethics, virtue ethics for AI, contractualist AI governance, capability approaches, and a proposed Relational AI Ethics Framework (RAEF). Evaluation applies each framework to twelve ethically complex AGI scenarios drawn from near-term forecasting, safety research, and speculative but plausible long-term AGI deployment. Scenarios include: AGI as medical decision authority, AGI-managed resource allocation during climate emergency, AGI moral status and legal personhood, AGI oversight of democratic processes, and AGI self-modification rights. Assessment instruments include structured expert analysis by 42 philosophers, legal scholars, and AI researchers, and a stakeholder impact analysis tool. No single framework adequately addresses all AGI ethical challenges. RAEF achieves the highest expert consensus score (3.84/5) by grounding AGI ethics in ongoing human-AI relationships rather than abstract principles. Key finding: current AI ethics frameworks systematically underweigh the interests of future generations and non-human stakeholders in AGI governance decisions. A multi-framework governance architecture is proposed.