Trees of Knowledge: Designing with Artificial Intelligence in the Urban Landscape

In our ongoing speculative design project entitled Topos, we propose a public-facing, tangible user interface (TUI) that makes legible and accessible the AI systems embedded in near-future urban landscapes. By imagining AI as a public service, Topos interrogates the creation of public trust between people and AI systems through the medium of physical structures in public space. We propose that urban landscapes will contain “AI-parks” containing trees of knowledge that physicalize machine learning (ML) pathways that take on or augment the responsibilities of city departments and bureaus. The trees of knowledge are TUIs where humans can read and revise the inputs that civic AI systems learn from—an interaction that we call “pruning”. Topos suggests that the interactions between AI systems and humans should be embodied and spatial in nature, so as to highlight the ways in which civic-oriented AI systems will directly affect the lived environments and multiple infrastructures of the urban landscape.