# When happy accidents spark creativity: Bringing collaborative speculation to life with generative AI

arXiv: https://arxiv.org/abs/2206.00533 · HTML: https://mlsanity.com/paper/2206.00533/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jun 2022.

## Built on by (most cited first, 9 of 9)

- [Art and the science of generative AI: A deeper dive](https://mlsanity.com/paper/2306.04141/) (2023)
- [CoQuest: Exploring Research Question Co-Creation with an LLM-based Agent](https://mlsanity.com/paper/2310.06155/) (2023)
- ["An Adapt-or-Die Type of Situation": Perception, Adoption, and Use of Text-To-Image-Generation AI by Game Industry Professionals](https://mlsanity.com/paper/2302.12601/) (2023)
- [AI-Assisted Causal Pathway Diagram for Human-Centered Design](https://mlsanity.com/paper/2403.08111/) (2024)
- [Trash to Treasure: Using text-to-image models to inform the design of physical artefacts](https://mlsanity.com/paper/2302.00561/) (2023)
- [The Cultivated Practices of Text-to-Image Generation](https://mlsanity.com/paper/2306.11393/) (2023)
- [AI Rivalry as a Craft: How Resisting and Embracing Generative AI Reshape Writing Professions](https://mlsanity.com/paper/2503.09901/) (2025)
- [Exploring Collaborative GenAI Agents in Synchronous Group Settings: Eliciting Team Perceptions and Design Considerations for the Future of Work](https://mlsanity.com/paper/2504.14779/) (2025)
- [Computational Scaffolding of Composition, Value, and Color for Disciplined Drawing](https://mlsanity.com/paper/2509.17268/) (2025)

## Abstract (arXiv)

Generative AI techniques like those that synthesize images from text (text-to-image models) offer new possibilities for creatively imagining new ideas. We investigate the capabilities of these models to help communities engage in conversations about their collective future. In particular, we design and deploy a facilitated experience where participants collaboratively speculate on utopias they want to see, and then produce AI-generated imagery from those speculations. In a series of in-depth user interviews, we invite participants to reflect on the generated images and refine their visions for the future. We synthesize findings with a bespoke community zine on the experience. We observe that participants often generated ideas for implementing their vision and drew new lateral considerations as a result of viewing the generated images. Critically, we find that the unexpected difference between the participant's imagined output and the generated image is what facilitated new insight for the participant. We hope our experimental model for co-creation, computational creativity, and community reflection inspires the use of generative models to help communities and organizations envision better futures.