Bootstrapping Life-Inspired Machine Intelligence: The Biological Route from Chemistry to Cognition and Creativity

TL;DR

This paper advocates for a life-inspired approach to machine intelligence, emphasizing biological principles like autonomy, growth, and self-organization to develop more adaptable and resilient AI systems.

Contribution

It introduces the concept of 'cognitive light cones' and distills five biological design principles to guide the development of autonomous, embodied AI inspired by living systems.

Findings

Biological evolution offers scalable strategies for intelligence expansion.

Five key principles underpin life's problem-solving capabilities.

Pathways outlined for integrating biological principles into AI systems.

Abstract

Achieving advanced machine intelligence remains a central challenge in AI research, often approached through scaling neural architectures and generative models. However, biological systems offer a broader repertoire of strategies for adaptive, goal-directed behavior - strategies that emerged long before nervous systems evolved. This paper advocates a genuinely life-inspired approach to machine intelligence, drawing on principles from biology that enable robustness, autonomy, and open-ended problem-solving across scales. We frame intelligence as flexible problem-solving, following William James, and develop the concept of "cognitive light cones" to characterize the continuum of intelligence in living systems and machines. We argue that biological evolution has discovered a scalable recipe for intelligence - and the progressive expansion of organisms' "cognitive light cone", predictive and control capacities. To explain how this is possible, we distill five design principles - multiscale autonomy, growth through self-assemblage of active components, continuous reconstruction of capabilities, exploitation of physical and embodied constraints, and pervasive signaling enabling self-organization and top-down control from goals - that underpin life's ability to navigate creatively diverse problem spaces. We discuss how these principles contrast with current AI paradigms and outline pathways for integrating them into future autonomous, embodied, and resilient artificial systems.