From indicators to biology: the calibration problem in artificial consciousness
arXiv Preprint Archive March 29, 2026 via arXiv
Summary
AI-generated from the abstractEvaluating 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.
Study at a glance
| Characteristics | Theoretical or philosophical paper Peer reviewed |
|---|---|
| Keywords | Cs.ai Q-bio.nc |
| Key finding | Argues that probabilistic consciousness attribution to current AI systems is premature and proposes redirecting effort toward biologically grounded engineering that reduces the gap with living systems. |
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.