Singularity? Limitations, possibilities, and differences of artificial intelligence compared to human intelligence

Abstract

In this paper, we reflect on whether AI has reached the level of human intelligence, some of the reasons that lead us to that state of opinion, as well as on some of the fundamental differences between AI and human intelligence. We briefly review the historical development of AI and delineate the real capacities and important limitations of deep learning techniques, underlying most of the recent advancements in AI. We particularly explain the argument of how complex cognitive skills are inseparable from a biological body interacting with a physical and socio-cultural world. This view contradicts the dualist and cognitivist axiom on which IA is fundamentally based, which has been criticized as incomplete or partial. We finalize considering some current real risks of AI and some speculations on its future development.