Abstract
This methodologically important essay aims to trace a genealogical account of Herbert Simon’s media philosophy and to contest the histories of artificial intelligence that overlook the organizational capacities of computational models. As Simon’s work demonstrates, humans’ subjection to large-scale organizations and divisions of labor is at the heart of artificial intelligence. As such, questions of procedures are key to understanding the power assumed by institutions wielding artificial intelligence. Most media-historical accounts of the development of contemporary artificial intelligence stem from the work of Warren S. McCulloch and Walter Pitts, especially the 1943 essay “A Logical Calculus of the Ideas Immanent in Nervous Activity.” Yet Simon’s revenge is perhaps that reinforcement learning systems adopt his prescriptive approach to algorithmic procedures. Computer scientists criticized Simon for the performative nature of his artificially intelligent systems, mainly for his positivism, but he defended his positivism based on his belief that symbolic computation could stand in for any reality and in fact shape that reality. Simon was not looking to actually re-create human intelligence; he was using coercion, bad faith, and fraud as tactical weapons in the reordering of human decision-making. Artificial intelligence was the perfect medium for his explorations.
