Just aware enough: Evaluating awareness across artificial systems

TL;DR

This paper proposes a practical, domain-sensitive method for evaluating awareness in artificial systems, focusing on their information processing abilities to improve assessment, comparison, and discourse on AI consciousness.

Contribution

It introduces a structured, scalable approach to measure awareness across diverse AI systems, emphasizing domain sensitivity and ability prediction.

Findings

Developed a method for assessing awareness in various AI architectures.

Demonstrated the approach's applicability across different operational domains.

Facilitated comparison of AI systems based on awareness profiles.

Abstract

Recent debates on artificial intelligence increasingly emphasise questions of AI consciousness and moral status, yet there remains little agreement on how such properties should be evaluated. In this paper, we argue that awareness offers a more productive and methodologically tractable alternative. We introduce a practical method for evaluating awareness across diverse systems, where awareness is understood as encompassing a system's abilities to process, store and use information in the service of goal-directed action. Central to this approach is the claim that any evaluation aiming to capture the diversity of artificial systems must be domain-sensitive, deployable at any scale, multidimensional, and enable the prediction of task performance, while generalising to the level of abilities for the sake of comparison. Given these four desiderata, we outline a structured approach to evaluating and comparing awareness profiles across artificial systems with differing architectures, scales, and operational domains. By shifting the focus from artificial consciousness to being just aware enough, this approach aims to facilitate principled assessment, support design and oversight, and enable more constructive scientific and public discourse.