This volume presents the results of a collaboration between researchers at the Scuola Normale Superiore, Pisa, and Princeton University. It introduces readers to Logion, the first deep neural network designed to support philologists in editing Greek texts that have reached us via manuscript transmission. The model offers suggestions for how to fill lacunae; it also helps identify and emend portions of text that seem to have been corrupted in the process of textual transmission. The different chapters explore the theory and historical practice of philology, present the AI model we designed, and make use of Logion in elucidating passages of premodern Greek. The focus is on the vast corpus of the Byzantine polymath Michael Psellos, which represents an excellent case study, from both a philological and technical perspective. Overall, the aim of this volume is both practical and intellectual. It seeks to encourage a broader dialogue between artificial intelligence and Greek philology and to present an actual model for the use of machine learning in elucidating premodern texts.