Are conscious machines valuers?

Summary

Even if artificial systems achieve consciousness through computational functionalism, they likely lack valenced experience—the felt quality of being good or bad. Valence requires a non-derivative goal like self-preservation, which silicon-based systems do not possess. Four potential routes to artificial valence are examined and found insufficient. Consequently, artificial consciousness may not entail sentience.

Study at a glance

Abstract

Recent proposals in neuroscience and philosophy suggest that coarse-grained computational functionalism may suffice for artificial consciousness. However, I argue that even if such accounts are right, there is no reason to assume that consciousness so realised would, by default, be valenced. On a naturalistic conception of value, valence—the affective quality of subjective experience—presupposes entities for whom things can be non-derivatively good or bad. In living organisms, valence is primordially grounded in a predisposition toward self-preservation, relative to which states of the world can be objectively better or worse. Silicon-based artificial systems appear to lack functionally equivalent dispositions relative to which certain states of the world would be objectively preferable for them over others. This, I argue, gives rise to a value grounding problem : if artificial systems do not possess non-derivative goals, it becomes unclear what could ground subjective attributions of value on their part, i.e. valenced states. I discuss four potential pathways to artificial valence—designer-independent goals, reinforcement learning, rational evaluation, and hallucinations—arguing that none satisfactorily solves the value grounding problem. If the account offered here is correct, it is unlikely that recent proposals for artificial consciousness will entail valenced states, that is, sentience.

Tags