I am an Associate Professor in Philosophy at the University of Massachusetts, Amherst. I work mainly in Formal Semantics, Pragmatics, Philosophy of Language, Cognitive Science and AI. My current research explores the ways in which an automatic, unconscious capacity to compute logical inferences and information maximization operations shapes our capacity to encode and decode information in natural languages. I also work on related topics in the foundations of cognitive science and AI, including the structure of concepts and their effect on categorization and reasoning. Recently, I also started to explore topics in mechanistic interpretability and alignment in AI systems.
gdelpinal@umass.edu
