The mechanical Turk: a short history of ‘artificial artificial intelligence’

Abstract

ABSTRACT This paper undertakes a comparative analysis of the famous eighteenth-century chess-playing automaton known as Mechanical Turk and the Amazon microwork platform of the same name. The original Mechanical Turk was a life-sized automaton made in 1770 and publicly exhibited until the mid-1800s, and which played games of chess with the audience. Its movements were fully mechanical, but even more remarkably, it was promoted as the world’s first ‘thinking machine,’ deciding each move of the chess pieces for itself. From the outset, it was widely assumed that the Mechanical Turk was a hoax, and that a human must be hidden inside the machine, directing the game. But it was a clever hoax whose trick was never discovered, and widely admired as such. Amazon’s Mechanical Turk job platform functions in a similarly open way, this paper argues, as a sort of open technological hoax. Mechanical Turk provides a source of human cognitive labour that can be used to invisibly operate digital systems and programs that are widely assumed to be fully automated. Artificial intelligence is a twenty-first century thinking machine, it requires a human brain to make it work. Amazon’s Mechanical Turk is a marketplace in which companies can hire piecemeal cognitive labour to patch gaps and train programs to keep those systems functioning. Providing what Jeff Bezos has called ‘artificial artificial intelligence,’ Amazon’s Mechanical Turk, like Kempelen’s automaton, both draws attention to and obfuscates the limits of automation and artificial intelligence. Taking the two iterations of the Mechanical Turk as rich cultural figures of automation for their respective periods, this paper will argue that the open secret of their artificial artificial intelligence is itself a form of misdirection that hides other, more successfully guarded secrets: the true extent of that labour, and the conditions in which it is performed.