Initial results of the Digital Consciousness Model

TL;DR

The paper introduces the Digital Consciousness Model (DCM), a systematic probabilistic framework to assess AI consciousness, finding current large language models unlikely to be conscious but with inconclusive evidence.

Contribution

It presents the first structured, multi-theory approach to evaluate consciousness in AI systems, enabling comparison and tracking over time.

Findings

Evidence suggests 2024 LLMs are unlikely to be conscious.

The evidence against LLM consciousness is weaker than for simpler AI.

Current evidence is not decisive regarding AI consciousness.

Abstract

Artificially intelligent systems have become remarkably sophisticated. They hold conversations, write essays, and seem to understand context in ways that surprise even their creators. This raises a crucial question: Are we creating systems that are conscious? The Digital Consciousness Model (DCM) is a first attempt to assess the evidence for consciousness in AI systems in a systematic, probabilistic way. It provides a shared framework for comparing different AIs and biological organisms, and for tracking how the evidence changes over time as AI develops. Instead of adopting a single theory of consciousness, it incorporates a range of leading theories and perspectives - acknowledging that experts disagree fundamentally about what consciousness is and what conditions are necessary for it. This report describes the structure and initial results of the Digital Consciousness Model. Overall, we find that the evidence is against 2024 LLMs being conscious, but the evidence against 2024 LLMs being conscious is not decisive. The evidence against LLM consciousness is much weaker than the evidence against consciousness in simpler AI systems.