Consciousness in human and machine: A theory and some falsifiable predictions

Abstract

To solve the hard problem of consciousness we first note that alf cognitive systems of sufficient power must get into difficulty when trying to analyze consciousness concepts, because the mechanism that does the analysis will bottom out in such a way that the system declares these concepts to be both real and ineffable. Rather than use this observation to dismiss consciousness as an artifact, we propose a unifying interpretation that allows consciousness to be regarded as explicable at a meta level, while at the same time being mysterious and inexplicable on its own terms. It is further suggested that science must concede that there are ' some aspects of the world that deserve to be called 'real', but which are beyond explanation. The main conclusion is that thinking machines of the future will, inevitably, have just the same subjective consciousness that we do, Some testable predictions can be derived from this theory. Copyright © 2008, The Second Conference on Artificial General Intelligence (agi-09.org). All rights reserved.