The Suicide of Multivac: From Asimov’s Science Fiction to Consciousness Testing

Abstract

Isaac Asimov, the well-known author of novels that featured positronic robots, also penned tales featuring Multivac, an immense electronic brain that grappled with the weighty and intricate decisions impacting all of humankind. In his 1958 short story All the Troubles of the World, Asimov introduced us to a Multivac tormented by the consciousness of its own thought processes to the extent that it desired its own demise. Through this narrative, Asimov delved into the existential dimensions of artificial consciousness: he depicted the Multivac’s adeptness in planning, reflexivity, and intentionality aimed at self-terminating — qualities that, in a tragic parallel, are also observed in certain cases of human suicidal behavior. Starting from these suggestions, we propose an existentialist and self-reflection criterion for consciousness, intertwining phenomenal consciousness with an entity’s capability to conceive thoughts about its own mortality. We argue that, according to certain psychological literature and the existentialist essays of Emil M. Cioran, artificial systems might be deemed conscious if they possess death-thought accessibility— the capacity, akin to that of humans, to conceive thoughts about their own mortality and intentionally conceive self-termination. Naturally, this criterion shares the inherent challenges associated with defining intentionality, reflexivity, and, ultimately, the very concept of consciousness as it pertains to humans.