ACM Project - Artificial Consciousness Research Developing Artificial Consciousness Through Emotional Learning of AI systems
Language Agents and Global Workspace Theory in AI Consciousness | ACM Project

Language Agents and Global Workspace Theory in AI Consciousness

Could language agents already possess phenomenal consciousness? This paper by Simon Goldstein and Cameron Domenico Kirk-Giannini examines this question using Global Workspace Theory (GWT), arguing that language agents might already meet the necessary conditions.

A Case for AI Consciousness: Language Agents and Global Workspace Theory, authored by Simon Goldstein and Cameron Domenico Kirk-Giannini, presents a methodology for applying scientific theories of consciousness to artificial systems.


Key Highlights

  • GWT Application: Outlines necessary and sufficient conditions for phenomenal consciousness in AI, based on Global Workspace Theory.
  • Language Agents: Suggests that existing language agents may meet GWT criteria for consciousness, raising intriguing possibilities.
  • Methodology: Provides a systematic approach to testing scientific consciousness theories on artificial systems.

Connection to ACM

The Artificial Consciousness Module (ACM) partially aligns with this study through:

  • Global Workspace Theory: ACM draws on GWT principles, particularly the integration of multimodal inputs and attention mechanisms to create an internal โ€œworkspaceโ€ for decision-making and self-reflection.
  • Simulating Conscious-Like Behaviors: While ACM emphasizes progressive, layered simulations to develop consciousness, insights from this paper could inform approaches to evaluating AI agent behavior and internal processing.

For a detailed exploration of the methodology and findings, access the full paper here.