Problems with mechanisms of thinking and cognition in many ways remain unresolved. Why are a priori inferences possible? Why can a human understand but a computer cannot? It has been shown that when creating new concepts, generalization is contradictory in the sense that to be created concepts must exist a priori, and therefore, they are not new. The process of knowledge acquisition is also contradictory, as it inevitably involves recognition, which can be realized only when there is an a priori standard. Known approaches of the framework of artificial intelligence (in particular, Bayesian) do not determine the origins of knowledge, as these approaches are effective only when “good” hypotheses are made. The formation of “good” hypotheses must occur a priori. To address these issues and paradoxes, a fundamentally new approach to problems of cognition that is based on completely innate behavioral programs is proposed. The process of cognition within the framework of the concept of a quantum metalanguage involves the selection of adequate a priori existing (innate) programs (logical variables and rules for working with them) that are most adequate to a given situation. The quantum properties of this metalanguage are necessary to implement such programs.

Knowledge acquisition, Chinese Room, Understanding, Metalanguage, Quantum decision making, Generalization