Mediated Authorships: The Designer as the Instructor of Machines

Abstract

The implementation and use of artificial intelligence (AI), and automatic learning in particular, are ushering in a methodological and conceptual updating of creative practices and their associated theory. The roots of these changes lie in disciplinary traditions associated with research into automatism promoted in the 1960s, with the introduction of cybernetics and computational sciences. This article focuses on the spread of the notion of authorship in architecture in the digitalization process and takes the discussion of systematic automatism in home design as a case study. For doing so it revises the main theoretical references, particularly the work by Gordon Pask, unfolds projects from the 60 s to post the main questions raised by AI today in the Design Field in respect to Authorship. While Gordon Pask suggested the transformation of the architect into a systems designer, now we can state that this is an environment in which the architect is transformed into an educator and a critic, an educator in the sense that they have to design the datasets, or conditions of possibility of learning; they have to instruct the generative and discriminative neural networks through numerous groups of “examples” and guide this learning through weighted assessment protocols.