Detecting Synthetic Phenomenology in a Contained Artificial General Intelligence
arXiv Preprint Archive November 6, 2020 Jason M. Pittman, Ashlyn Hanks
Assuming that artificial general intelligence (AGI) can and will be created, the authors argue for the necessity of safe and trusted development through containment or boxing. They analyze existing measures of phenomenology via qualia and extend these ideas to the context of a contained AGI, exploring how phenomenology might be detected under the operational constraints of such a system.