AI & ML
DuoSketch: How Pairs Navigate Challenges in AI-Supported Collaborative Design Ideation
arXiv cs.HC0 views
arXiv:2610.10249v1 Announce Type: new Abstract: Generative AI offers new resources for collaborative design ideation, yet how designers work with it as a shared concept develops remains underexplored. We developed DuoSketch, integrating a shared canvas and live transcripts with a separate AI for each member of a pair. An exploratory qualitative study with 12 pairs identified three challenges: unresolved fit between AI proposals and shared design purposes, shared meanings not expressed in AI responses, and agreed changes missing from later outputs. We found that pairs navigated these challenges through bridging work in two directions: AI -> Shared Design (reworking features, developing uses, and assessing fit with shared requirements) and Shared Design -> AI (supplying materials, explaining meanings, and communicating decisions). We discuss how future AI systems can support the joint exploration and articulation of design ideas.
Source:https://arxiv.org/abs/2610.10249PreviousEEG and Eye-Tracking Evidence That AI Disclosure Shapes Face EvaluationNextActive Inference for Interaction-Mediated Control of a High-Dimensional Robotic Arm
Related posts
Heated mirror reveals hidden 3D patterns in rising air near a wall
0Phys.org Tech
Infrared-transparent aerogel boosts performance of subambient daytime radiative cooling materials by up to 5.2°C
0Phys.org Tech
Tracing the online networks behind AI-generated nude images
0Phys.org Tech
Microsoft's AI Risk Report Misses This Key Detail
0Dark Reading
Introducing the Grid Protectors Program
0OpenAI Blog
The world has a new plan to save nature, but it still needs the money
0Ars Technica