🤖 AI Summary
This study addresses the limitation of traditional human-AI collaboration, which often confines humans to merely evaluating AI outputs while overlooking their active role in shaping the creative process. Drawing on Schön’s theory of reflective practice, this work proposes SOSS (Shape, Observe, Stir, Select), an interaction framework that positions generative AI as a dynamic creative medium, enabling humans to explore and shape creative spaces through perturbation and curation within an ongoing dialogue. The authors developed Loom, a creative writing probe system integrating generative AI with multi-agent simulation, allowing users to orchestrate narrative agents for collaborative storytelling. Empirical evaluation demonstrates that this paradigm effectively enhances generative quality and expands creative possibilities, offering a novel design pathway and practical foundation for human-AI co-creativity.
📝 Abstract
Human-AI collaboration research has largely positioned the human as a judge of AI output, centering effort on evaluating whether rec- ommendations are reliable enough to accept. This decision-support framing leaves little room for the human as creator. We argue that for creative work, this framing misdirects human effort toward eval- uating correctness rather than exploring and shaping the creative space. Drawing on Schön's theory of reflective practice, we propose an alternative: treating generative AI as an active creative medium. As a potter works with clay, humans Shape, Observe, Stir, and Se- lect (SOSS) their medium through ongoing conversation. Where generative AI actively tends toward convergence and resolution, the human role of disruption and curation becomes essential for sustaining creative quality. We present a creative writing probe, Loom, in which users orchestrate simulated narrative agents. We also introduce the SOSS framework for this mode of engagement, and discuss design implications.