Detecting Qualia in Natural and Artificial Agents
arXiv Preprint Archive December 11, 2017 via arXiv
Summary
AI-generated from the abstractThe paper argues that the hard problem of consciousness is not an illusion and that computers can have subjective experiences, making them at least rudimentarily conscious with potential for superconsciousness. It proposes a test to confirm certain subjective experiences in an agent and discusses the benefits and problems of conscious machines, including implications for computing, machine rights, and artificial intelligence safety.
Study at a glance
| Characteristics | Theoretical or philosophical paper Peer reviewed |
|---|---|
| Keywords | Cs.ai |
| Key finding | Proposes that computers can have subjective experiences, making them rudimentarily conscious, and offers a test to confirm such experiences. |
Abstract
The Hard Problem of consciousness has been dismissed as an illusion. By showing that computers are capable of experiencing, we show that they are at least rudimentarily conscious with potential to eventually reach superconsciousness. The main contribution of the paper is a test for confirming certain subjective experiences in a tested agent. We follow with analysis of benefits and problems with conscious machines and implications of such capability on future of computing, machine rights and artificial intelligence safety.