Paul Tennent

Generative AI is rapidly transforming creative practice, yet its limitations (bias, censorship, opacity, instability, and ethical uncertainty) are often treated as flaws to be fixed. Artists, however, have historically worked with the malfunctions of emerging technologies as creative material. Drawing on interviews with 13 contemporary artists, we identify five recurring forms of constraint in GenAI systems and five design orientations artists use to rework them: Exposure (making seams visible), Redirection (working around constraints), Systematisation (making failure repeatable), Practiced Governance (ethical self-regulation), and Scaffolding (designing interpretive contexts for audiences). Instead of hiding seams, artists treat them as resources for reflection, critique, and creative expansion. We frame these practices as forms of seamful and constraint-based design, arguing that artists working at the edge of GenAI systems offer HCI a model for designing with limitations rather than against them.

We introduce "Dimensional Design Diagrams" (DDDs) to HCI as a form of intermediate-level design knowledge. DDDs are diagrams in which typically two or three continuous dimensions are drawn orthogonally to create a design space on which design instances, literature and study data may be mapped. We analyse sixteen examples of DDDs, primarily drawn from the work of two laboratories, and reveal them to be a sophisticated tool for design thinking. We show how the application of various diagrammatic techniques including identifying regions, strategies and tensions; performing a 45-degree turn to identify and deconstruct orthogonal and contrarian perspectives on the design space; and charting inter- and intra-experience trajectories to show how user experiences unfold over time, can bring greater analytic and generative depth to DDDs. We position DDDs alongside other forms of intermediate-level design knowledge and show how they are integrated, and ultimately advance intermediate-level design knowledge development in HCI.

We present a rehearsal-oriented system for creating responsive built environments during theatre devising workshops. The system connects bespoke sensing modules for gesture, position, and speech recognition to light and sound outputs through a visual no-code programming layer. It was developed, used, and refined across six workshops with eight professional performance-makers, where participants created light-and-sound scores, gesture- and position-triggered scenes, responsive architectures, participatory prototypes, and a multi-room scratch performance. Rather than presenting a production-ready show-control platform, this demo focuses on how sensing and actuation can be made available as compositional materials during early-stage creative experimentation for immersive theatrical compositions. The system is designed to support quick configuration, visible mappings, and in-room testing, allowing performers to experiment with responsive spaces with minimal technical support. We describe the system architecture, its workshop use, and the practical conditions that helped integrate interactive sensing into embodied performance-making.

Volumetric video capture (VVC) technologies are finding applications in multiple sectors that desire realistic and immersive mixed reality content. However, VVC is also emerging as a tool for traditional filmmaking: in theory, the capture technology allows directors to view a scene from every angle and choose how to frame the story all in post-production. To investigate this, we conducted two pilot studies. The first was a set of preliminary interviews with film industry practitioners, who demonstrated a cautious curiosity for the technology’s applications and expanded on its implications for direction and performance. The second study is a comparison exercise where two versions of the same devised scene were captured and developed for viewing: one was filmed via conventional means, the other was filmed with a VVC solution. The process of production and post-production was recorded for both versions, supplemented by observational notes from the actors and an auto-ethnographic account from the author. The final stage of this study was a feedback session with returning interviewees, who reacted positively to the VVC version and reflected on this in light of their previous speculations. Lastly, this article investigates the issue of access and democratisation in relation to VVC and illustrates further pathways for future human-led research for volumetric capture technologies.