The Role of Culture in the Intelligence of AI

Abstract

Artificial intelligence has received a new boost from the recent hype about large lan- guage models. However, to avoid misconceptions, it is better to speak of 'machine intelligence'. In addition to reflecting on current processes, the cultural sector can benefit from very specific machine learning approaches to transfer literary me- thods such as 'distant readings' and find new connections in cultural data. In light of resource and exploitation problems, what is needed is a 'critical technical practice' (Agre) that brings together various actors, productively engages with AI's own logics and error cultures, and uses its potential to cope with the flood of information. Artificial intelligence has received a new boost from the recent hype about large lan- guage models. However, to avoid misconceptions, it is better to speak of 'machi- ne intelligence'. In addition to reflecting on current processes, the cultural sector can benefit from very specific machine learning approaches to transfer literary me- thods such as 'distant readings' and find new connections in cultural data. In light of resource and exploitation problems, what is needed is a 'critical technical practice' (Agre) that brings together various actors, productively engages with AI's own logics and error cultures, and uses its potential to cope with the flood of information.