Dis//assemblages of AI: repair labor and resistance in the automated workplace

Breakdowns and repairs are seldom present in dominant narratives about Artificial Intelligence that depict these technologies as a seamless source of optimization. Yet, AI systems are replete with moments of downtime and delayed action that feminist science and technology scholars have theorized as openings to reimagine technological systems. The following article engages the concept of friction to contend with the contradictory ways in which workers tasked with the continual labor of sustaining Artificial Intelligence technologies simultaneously transform parts of the system. Drawing upon seven months of ethnographic research at a recycling facility integrated with various forms of automation, including AI-powered sorting robots, we show how moments of machine malfunction provide fleeting windows for workers to bring to life alternative AI configurations. Our analytical and observational focus on glitches and breakdown allow us to make two related contributions to the study of the automated workplace: (1) We propose friction as a lens that aids in navigating the messy paradox of reproduction and resistance inherent to repair labor and (2) empirically demonstrate how friction emerges from workers' material practices that contest datafied technological imaginaries through embodied science and move against pressures to optimize for efficiency and revenue by prioritizing communal care.