Probing for Consciousness in Machines
arXiv Preprint Archive November 25, 2024 Mathis Immertreu, Achim Schilling, Andreas Maier et al.
Artificial agents trained via reinforcement learning can develop rudimentary forms of self and world models—key components of core consciousness as defined by Antonio Damasio. In a virtual environment, an agent learning to play a video game formed internal representations that allowed probes (feedforward classifiers) to predict the agent's spatial position from its neural activations. These results suggest that machine consciousness may be possible as a byproduct of goal-directed learning, offering foundational insights for AI development.