On Computational Mechanisms for Shared Intentionality, and Speculation on Rationality and Consciousness
It addresses the challenge of cooperative behavior in AI and humans from a computer science perspective, offering a novel theoretical framework that complements existing sociological views.
The paper tackles the problem of enabling shared intentionality in prelinguistic computational agents by deriving necessary mechanisms using Marr's information processing model and proposing implementations for AI-based robots, while speculatively extending these mechanisms to explain human rationality and consciousness.
A singular attribute of humankind is our ability to undertake novel, cooperative behavior, or teamwork. This requires that we can communicate goals, plans, and ideas between the brains of individuals to create shared intentionality. Using the information processing model of David Marr, I derive necessary characteristics of basic mechanisms to enable shared intentionality between prelinguistic computational agents and indicate how these could be implemented in present-day AI-based robots. More speculatively, I suggest the mechanisms derived by this thought experiment apply to humans and extend to provide explanations for human rationality and aspects of intentional and phenomenal consciousness that accord with observation. This yields what I call the Shared Intentionality First Theory (SIFT) for rationality and consciousness. The significance of shared intentionality has been recognized and advocated previously, but typically from a sociological or behavioral point of view. SIFT complements prior work by applying a computer science perspective to the underlying mechanisms.