From indicators to biology: the calibration problem in artificial consciousness

TL;DR

This paper critiques current indicator-based approaches to artificial consciousness, emphasizing the need for biologically grounded engineering due to the lack of definitive ground truth and theoretical fragmentation.

Contribution

It highlights the epistemic limitations of indicator-based methods and advocates for focusing on biologically inspired systems to better understand consciousness.

Findings

Indicator-based evaluation remains epistemically under-calibrated.

Current AI systems lack a ground truth for consciousness.

Biologically grounded engineering offers a more promising near-term approach.

Abstract

Recent work on artificial consciousness shifts evaluation from behaviour to internal architecture, deriving indicators from theories of consciousness and updating credences accordingly. This is progress beyond naive Turing-style tests. But the indicator-based programme remains epistemically under-calibrated: consciousness science is theoretically fragmented, indicators lack independent validation, and no ground truth of artificial phenomenality exists. Under these conditions, probabilistic consciousness attribution to current AI systems is premature. A more defensible near-term strategy is to redirect effort toward biologically grounded engineering -- biohybrid, neuromorphic, and connectome-scale systems -- that reduces the gap with the only domain where consciousness is empirically anchored: living systems.