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.

Cited by in corpus (10)

• A Survey on State-of-the-art Deep Learning Applications and Challenges
• Eight challenges in developing theory of intelligence
• Synergising Human-like Responses and Machine Intelligence for Planning in Disaster Response
• On the attribution of confidence to large language models
• AI Alignment vs. AI Ethical Treatment: 10 Challenges
• Hypothesis on the Functional Advantages of the Selection-Broadcast Cycle Structure: Global Workspace Theory and Dealing with a Real-Time World
• Humanoid Artificial Consciousness Designed with Large Language Model Based on Psychoanalysis and Personality Theory
• Informed Consent for AI Consciousness Research: A Talmudic Framework for Graduated Protections
• Meta-ethics and AI: exploring the novel meta-ethical questions in the era of AI
• Can "consciousness" be observed from large language model (LLM) internal states? Dissecting LLM representations obtained from Theory of Mind test with Integrated Information Theory and Span Representation analysis