From indicators to biology: the calibration problem in artificial consciousness
arXiv Preprint Archive March 29, 2026 Florentin Koch
Evaluating artificial consciousness by checking systems against indicators derived from theories of consciousness is an improvement over simple behavioral tests. However, this approach is epistemically weak because consciousness science is theoretically fragmented, the indicators lack independent validation, and there is no ground truth for artificial phenomenality. Attributing consciousness to current AI systems probabilistically is therefore premature. A more defensible strategy is to focus on biologically grounded engineering—biohybrid, neuromorphic, and connectome-scale systems—that narrows the gap with living systems, the only domain where consciousness is empirically anchored.