Consciousness in Artificial Intelligence: Insights from the Science of Consciousness
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.
Keywords
Cite
@article{arxiv.2308.08708,
title = {Consciousness in Artificial Intelligence: Insights from the Science of Consciousness},
author = {Patrick Butlin and Robert Long and Eric Elmoznino and Yoshua Bengio and Jonathan Birch and Axel Constant and George Deane and Stephen M. Fleming and Chris Frith and Xu Ji and Ryota Kanai and Colin Klein and Grace Lindsay and Matthias Michel and Liad Mudrik and Megan A. K. Peters and Eric Schwitzgebel and Jonathan Simon and Rufin VanRullen},
journal= {arXiv preprint arXiv:2308.08708},
year = {2023}
}