Infrastructuring AI: The stabilization of 'artificial intelligence' in and beyond national AI strategies

Abstract

This paper explores how AI policy documents mediate the stabilization of socio-technical assemblages. It does so by developing the theory-methods package of ‘discursive infrastructuring’ and applying it to the U.K.’s National AI Strategy. By centering the conceptual slipperiness of emerging technologies such as AI, this framework sheds light on how policy documents work to stabilize emerging socio-technical assemblages comprising specific actors, ideologies, flows of capital, and relationships of power. In the context of the National AI Strategy, discursive infrastructuring reveals how the document stabilises: AI as an autonomous and inevitable force; a technical/social dualism which privileges the technical over the social in driving innovation; the ‘heroic engineer’ as an individual, masculine and rational archetype; and, the U.K. as a dominant and modernising player on AI’s global stage. This assemblage does not only exist in the document’s words; it is translated into practice through the funding of institutions, the centring of technical pedagogies of AI, and the opening of visa routes for ‘globally mobile individuals’. The application of ‘discursive infrastructuring’ to the National AI Strategy thus elucidates the constitutive role of policy discourse in stabilising politically situated material-semiotic conceptions of AI.