Artificial Consciousness as Interface Representation

TL;DR

This paper introduces a framework with SLP-tests to evaluate whether AI systems possess consciousness-like properties through interface representations modeled by category theory, making the question empirically testable.

Contribution

It proposes a novel set of criteria and a formal modeling approach to operationalize and empirically assess artificial consciousness.

Findings

SLP-tests operationalize subjective experience as interface functions.

Category theory models interface representations as mappings between substrates.

Framework enables empirical testing of consciousness-like properties in AI.

Abstract

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.