From indicators to biology: the calibration problem in artificial consciousness
For researchers in artificial consciousness, the paper highlights a critical calibration problem that undermines current evaluation methods, but offers no concrete results or numbers.
The paper argues that current indicator-based approaches to artificial consciousness are epistemically under-calibrated due to theoretical fragmentation and lack of validation, making probabilistic attribution to AI systems premature. It proposes redirecting effort toward biologically grounded engineering such as biohybrid and neuromorphic systems.
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.