Detecting Synthetic Phenomenology in a Contained Artificial General Intelligence
This addresses the safety and trust concerns for researchers and developers working on artificial general intelligence, though it appears incremental as it builds on existing ideas.
The paper tackles the problem of detecting synthetic phenomenology in a contained artificial general intelligence by analyzing existing measures of qualia and extending them to this context, but it does not report any concrete results or numbers.
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.