Engineering Sentience

Recent advances in artificial intelligence (AI) research have sparked renewed controversy as to whether machines can be sentient. One commonly acknowledged problem is that we lack a broad consensus on how to define the term'sentience'. Our goal here is to develop a workable approach to the concept of'sentience' - which we call functional sentience - for AI research and to discuss its possible implementations. This approach seeks to bridge the gap between philosophical debates and practical AI system design, grounding the concept in computational frameworks that are directly applicable to AI development. An apparent dilemma is that authors are often either defining sentience in metaphysical terms (using non-empirical concepts that go beyond normal science) [1, 2] or are defining it in terms of relatively trivial functional processes, e.g. by stipulating that sentience or consciousness is just to make perceptual information globally available within the system [3]. The former is beyond the scope of our present discussion. For the latter, the relevant mechanisms are easy to implement, e.g.