Conscious enactive computation
This work tackles the theoretical problem of consciousness in AI for philosophers and cognitive scientists, but it is incremental as it builds on existing debates without introducing new empirical results.
The paper addresses obstacles to building artificial conscious agents by analyzing enactive computation based on organizational closure, and it defends against criticisms of extended consciousness while proposing a new perspective on human-machine interaction.
This paper looks at recent debates in the enactivist literature on computation and consciousness in order to assess major obstacles to building artificial conscious agents. We consider a proposal from Villalobos and Dewhurst (2018) for enactive computation on the basis of organizational closure. We attempt to improve the argument by reflecting on the closed paths through state space taken by finite state automata. This motivates a defense against Clark's recent criticisms of "extended consciousness", and perhaps a new perspective on living with machines.