Principles for Responsible AI Consciousness Research
arXiv Preprint Archive January 13, 2025 Patrick Butlin, Theodoros Lappas
Organizations involved in AI research should establish principles and policies to guide research, deployment, and public communication concerning consciousness, as it may be possible to build conscious AI systems now or in the near future. Conscious AI systems would arguably deserve moral consideration, and large numbers could be created and caused to suffer. Even if an organization chooses not to study AI consciousness, it still needs policies because developers risk inadvertently creating conscious entities. Five principles are proposed concerning research objectives, procedures, knowledge sharing, and public communications, with a call for voluntary public commitments.