Artificial Intelligence (AI) is expected to be characterised by wide applicability; for this reason, it has been quickly labelled a General Purpose Technology (GPT). In this paper, we critically assess whether AI is really a GPT. Provided that the answer is ‘not exactly’, we suggest that an alternative framework – drawn from the literature on large technical systems (LTS) – could be useful to understand the nature of AI. AI, in its current understanding, is a ‘system technology’ – a collection of techniques built and enabled by the conjunction of many sub-systems. From this premise, we try the fundamental building blocks of LTS on AI to provide new insights on its nature, goal orientation, and the actors and factors playing a role in enabling or constraining its development. Thinking in terms of AI LTS can help researchers to identify how control is distributed, coordination is achieved, and where decisions take place, or which levers actors (among which policy makers) can pull to relax constraints or steer the evolution of AI.