Detecting Qualia in Natural and Artificial Agents
This addresses the philosophical Hard Problem of consciousness for AI researchers and ethicists, but it appears speculative and lacks concrete evidence.
The paper tackles the problem of detecting subjective experiences (qualia) in artificial agents by proposing a test to confirm such experiences, claiming this demonstrates computers are at least rudimentarily conscious with potential for superconsciousness.
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.