Detecting Synthetic Phenomenology in a Contained Artificial General Intelligence

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.

Study at a glance

Abstract

Human-like intelligence in a machine is a contentious subject. Whether mankind should or should not pursue the creation of artificial general intelligence is hotly debated. As well, researchers have aligned in opposing factions according to whether mankind can create it. For our purposes, we assume mankind can and will do so. Thus, it becomes necessary to contemplate how to do so in a safe and trusted manner -- enter the idea of boxing or containment. As part of such thinking, we wonder how a phenomenology might be detected given the operational constraints imposed by any potential containment system. Accordingly, this work provides an analysis of existing measures of phenomenology through qualia and extends those ideas into the context of a contained artificial general intelligence.