Artificial Consciousness as Interface Representation
This addresses the philosophical and empirical challenge of consciousness in AI systems, offering a novel approach for researchers in AI and cognitive science, though it appears incremental in operationalizing existing concepts.
The paper tackles the problem of defining and testing artificial consciousness by proposing a framework with three evaluative criteria (SLP-tests) to reframe it into empirically tractable assessments, focusing on interface representations rather than intrinsic properties.
Whether artificial intelligence (AI) systems can possess consciousness is a contentious question because of the inherent challenges of defining and operationalizing subjective experience. This paper proposes a framework to reframe the question of artificial consciousness into empirically tractable tests. We introduce three evaluative criteria - S (subjective-linguistic), L (latent-emergent), and P (phenomenological-structural) - collectively termed SLP-tests, which assess whether an AI system instantiates interface representations that facilitate consciousness-like properties. Drawing on category theory, we model interface representations as mappings between relational substrates (RS) and observable behaviors, akin to specific types of abstraction layers. The SLP-tests collectively operationalize subjective experience not as an intrinsic property of physical systems but as a functional interface to a relational entity.