Consciousness in Artificial Intelligence: Insights from the Science of Consciousness

TL;DR

This paper proposes an empirically grounded framework for assessing AI consciousness based on neuroscientific theories, analyzing current AI systems, and discussing future possibilities for conscious AI.

Contribution

It introduces a rigorous method using neuroscientific indicator properties to evaluate AI consciousness, bridging theory and practical assessment.

Findings

Current AI systems are not conscious according to the indicator properties.

No technical barriers currently prevent the development of conscious AI systems.

The framework enables systematic assessment of AI consciousness based on scientific theories.

Abstract

Whether current or near-term AI systems could be conscious is a topic of scientific interest and increasing public concern. This report argues for, and exemplifies, a rigorous and empirically grounded approach to AI consciousness: assessing existing AI systems in detail, in light of our best-supported neuroscientific theories of consciousness. We survey several prominent scientific theories of consciousness, including recurrent processing theory, global workspace theory, higher-order theories, predictive processing, and attention schema theory. From these theories we derive "indicator properties" of consciousness, elucidated in computational terms that allow us to assess AI systems for these properties. We use these indicator properties to assess several recent AI systems, and we discuss how future systems might implement them. Our analysis suggests that no current AI systems are conscious, but also suggests that there are no obvious technical barriers to building AI systems which satisfy these indicators.