Can We Test Consciousness Theories on AI? Ablations, Markers, and Robustness
arXiv Preprint Archive December 22, 2025 Yin Jun Phua
Three major theories of consciousness—Global Workspace Theory, Integrated Information Theory, and Higher-Order Theories—may describe complementary functional layers rather than competing accounts. Artificial agents embodying mechanisms from each theory were tested through architectural ablations impossible in biological systems. A Self-Model lesion abolished metacognitive calibration while preserving first-order task performance, creating a synthetic blindsight analogue consistent with Higher-Order Theories. Workspace capacity proved causally necessary for information access, with complete lesions producing qualitative collapse in access-related markers, consistent with Global Workspace Theory. A broadcast-amplification effect showed that broadcasting amplifies internal noise, creating extreme fragility. Raw perturbational complexity decreased under the workspace bottleneck, cautioning against naive transfer of Integrated Information Theory-adjacent proxies to engineered agents. The results suggest a hierarchical design principle: Global Workspace Theory provides broadcast capacity, while Higher-Order Theories provide quality control.