Biospheric AI

2024-01-31

arXiv.org

AI Summary

Current AI ethics and value alignment research remains anthropocentric; although recent efforts have extended consideration to sentient beings, they inadequately capture biospheric complexity and fail to mitigate systemic ecological risks. Method: This paper introduces the “Biosphere AI” paradigm—grounded in ecocentrism—to transcend anthropocentric and sentience-centric limitations. It formally defines “biosphere intelligence,” establishing ecosystem integrity, resilience, and evolutionary potential as core normative criteria. A technical framework is developed, integrating ecological modeling, multi-scale simulation, value-interpretable learning, and constrained reinforcement learning to enable formal specification and optimization of non-anthropocentric objectives. Contribution/Results: The work delivers a biosphere-compatible AI R&D roadmap, governance interfaces, and cross-disciplinary collaboration mechanisms—providing both theoretical foundations and actionable pathways for ecologically sustainable AI development.

Technology Category

• Philosophy and Ethics of AI: Morality & Value-based AI
• Humans and AI: Learning Human Values and Preferences
• Intelligent Robots: Embodied AI

Application Category

• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems
• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

The dominant paradigm in AI ethics and value alignment is highly anthropocentric. The focus of these disciplines is strictly on human values which limits the depth and breadth of their insights. Recently, attempts to expand to a sentientist perspective have been initiated. We argue that neither of these outlooks is sufficient to capture the actual complexity of the biosphere and ensure that AI does not damage it. Thus, we propose a new paradigm -- Biospheric AI that assumes an ecocentric perspective. We discuss hypothetical ways in which such an AI might be designed. Moreover, we give directions for research and application of the modern AI models that would be consistent with the biospheric interests. All in all, this work attempts to take first steps towards a comprehensive program of research that focuses on the interactions between AI and the biosphere.

Problem

• AI ethics needs ecocentric perspective beyond human values
• Proposing Biospheric AI to address biosphere complexity
• Developing AI designs aligned with biospheric interests

Innovation

• Proposes Biospheric AI with an ecocentric perspective
• Discusses hypothetical designs for biosphere-aligned AI
• Provides research directions for biosphere-friendly AI models