This study examines the computational problem-solving capabilities of GPT-4, focusing on its knowledge of machine learning, email categorization, and computational problem solving, alongside its proficiency in Python programming, computational abstraction, and program debugging. The aim of these investigations is to evaluate whether the capabilities of Large Language Models (LLMs), as demonstrated by GPT-4, can support Master of Library and Information Science (MLIS), graduate students in developing computational thinking skills relevant to digital archival tasks.

This paper describes an investigation of GPT-4’s knowledge in some areas of archival practice, and its ability to think computationally about archival tasks. It is demonstrated that GPT-4 has shown an understanding of ten among the twenty-two distinct forms of computational thinking. When GPT-4 is combined with plugins, it is able to apply some of these methods and tools to digital archival tasks.