Live Coding and Machine Learning is Dangerous: Show us your Algorithms

Machine learning encompasses computer algorithms able to learn through experience and by using data, with the primary aim of the optimization of automation processes. In integrating machine learning with live coding questions are raised around: what to optimize; which processes to automate; the role of the performer; and how to present ML algorithms and processes to the audience. Although there are no strict boundaries or limits in the practice of live coding, the TOPLAP draft manifesto has often provided a guiding philosophy for the development of practices. In combining live coding with ML, we find some tensions and frictions in staying true to the concepts presented in the manifesto. Although the authors do not advocate puritanism, in considering the combination of live coding and ML from the lens of the TOPLAP draft manifesto, we find an axis on which to generate discussion contemplating the limits, potentials and challenges in combining two technological practices which at times seem to sit at opposite ends of the spectrum when it comes to core live coding principles such as transparency, liveness, and legible processes.