Systems Explaining Systems: A Framework for Intelligence and Consciousness

TL;DR

The paper reframes intelligence as the capacity to form, refine, and integrate causal connections rather than rely on domain-specific prediction. It introduces the Stable State Framework, anchored by context enrichment and a dynamic meta-state, and proposes the systems-explaining-systems principle whereby higher-order systems learn to interpret lower-level relations and feed interpretations back to lower levels. Consciousness is described as the recursive expansion of relational explanations that become embedded in the meta-state and influence ongoing processing, with the neocortex as a general-purpose connector that supports cross-system mappings. The work offers a conceptual blueprint for multi-system, recursive AI architectures and deeper theories of mind, while acknowledging limitations and the need for empirical validation.

Abstract

This paper proposes a conceptual framework in which intelligence and consciousness emerge from relational structure rather than from prediction or domain-specific mechanisms. Intelligence is defined as the capacity to form and integrate causal connections between signals, actions, and internal states. Through context enrichment, systems interpret incoming information using learned relational structure that provides essential context in an efficient representation that the raw input itself does not contain, enabling efficient processing under metabolic constraints. Building on this foundation, we introduce the systems-explaining-systems principle, where consciousness emerges when recursive architectures allow higher-order systems to learn and interpret the relational patterns of lower-order systems across time. These interpretations are integrated into a dynamically stabilized meta-state and fed back through context enrichment, transforming internal models from representations of the external world into models of the system's own cognitive processes. The framework reframes predictive processing as an emergent consequence of contextual interpretation rather than explicit forecasting and suggests that recursive multi-system architectures may be necessary for more human-like artificial intelligence.