Framing Generative AI applications as tools for cognition in education

Generative AI applications enable different useful functions for learning based on the generation of content. This paper aims to offer a theoretical framework to understand them as tools for cognition (TFC), framed in the perspective of sociocultural theory and activity theory and distributed cognition. This perspective exemplifies how thought is not only packaged inside the individual's mind, but is distributed among subjects, objects, and artifacts, where tools mediate human activity and help in the executive functions of thought. The perspective of TFC embodies an educational socio-constructivist vision where learners build their knowledge with these tools, taking advantage of their affordances. It is the concept of learning "with" technology instead of the traditional vision of learning "from" technology, where technological applications are limited to providing information and evaluating the students' responses. Finally, we describe Generative AI applications as HPC following David Jonassen's pragmatic and pedagogical criteria, i.e. the capacity of knowledge representation of different subjects, the facilitation of critical and meaningful thinking (based on questioning and prompting) and how they enable complex thinking among students when used in learning tasks, only when executive functions are on the side of the learner.