A Case for AI Consciousness: Language Agents and Global Workspace Theory
Simon Goldstein, Cameron Domenico Kirk-Giannini
arXiv Preprint Archive October 15, 2024 via arXiv
Summary
If Global Workspace Theory (GWT), a leading scientific account of phenomenal consciousness, is correct, then widely used artificial language agents may already be phenomenally conscious or could easily be made so. The authors argue that existing AI systems are not necessarily non-conscious and that constructing conscious machines might not require major technological breakthroughs. They provide a methodology for applying scientific theories of consciousness to artificial systems and derive necessary and sufficient conditions for phenomenal consciousness under GWT.
Study at a glance
| Characteristics | Theoretical or philosophical paper Peer reviewed |
|---|---|
| Keywords | Cs.ai Q-bio.nc Artificial-consciousness Neuroscience Language-models |
| Key finding | Under Global Workspace Theory, existing artificial language agents may be phenomenally conscious or could be made so with minimal modification. |
Abstract
It is generally assumed that existing artificial systems are not phenomenally conscious, and that the construction of phenomenally conscious artificial systems would require significant technological progress if it is possible at all. We challenge this assumption by arguing that if Global Workspace Theory (GWT) - a leading scientific theory of phenomenal consciousness - is correct, then instances of one widely implemented AI architecture, the artificial language agent, might easily be made phenomenally conscious if they are not already. Along the way, we articulate an explicit methodology for thinking about how to apply scientific theories of consciousness to artificial systems and employ this methodology to arrive at a set of necessary and sufficient conditions for phenomenal consciousness according to GWT.