Do Zombies Understand? A Choose-Your-Own-Adventure Exploration of Machine Cognition
arXiv Preprint Archive March 1, 2024 Ariel Goldstein, Gabriel Stanovsky
Large language models' capacity for understanding text is debated because opponents hold different definitions of understanding, particularly regarding the role of consciousness. A thought experiment involving an open-source chatbot that excels on all benchmarks yet lacks subjective experience shows that different schools of AI research answer the question of its understanding differently, revealing terminological disagreement. The paper proposes two working definitions for understanding that explicitly address consciousness, connecting to philosophy, psychology, and neuroscience literature.