English

Building Software by Rolling the Dice: A Qualitative Study of Vibe Coding

Software Engineering 2026-01-01 v2 Human-Computer Interaction

Abstract

Large language models (LLMs) are reshaping software engineering by enabling "vibe coding," in which developers build software primarily through prompts rather than writing code. Although widely publicized as a productivity breakthrough, little is known about how practitioners actually define and engage in these practices. To shed light on this emerging phenomenon, we conducted a grounded theory study of 20 vibe-coding videos, including 7 live-streamed coding sessions (about 16 hours, 254 prompts) and 13 opinion videos (about 5 hours), supported by additional analysis of activity durations and prompt intents. Our findings reveal a spectrum of behaviors: some vibe coders rely almost entirely on AI without inspecting code, while others examine and adapt generated outputs. Across approaches, all must contend with the stochastic nature of generation, with debugging and refinement often described as "rolling the dice." Further, divergent mental models, shaped by vibe coders' expertise and reliance on AI, influence prompting strategies, evaluation practices, and levels of trust. These findings open new directions for research on the future of software engineering and point to practical opportunities for tool design and education.

Keywords

Cite

@article{arxiv.2512.22418,
  title  = {Building Software by Rolling the Dice: A Qualitative Study of Vibe Coding},
  author = {Yi-Hung Chou and Boyuan Jiang and Yi Wen Chen and Mingyue Weng and Victoria Jackson and Thomas Zimmermann and James A. Jones},
  journal= {arXiv preprint arXiv:2512.22418},
  year   = {2026}
}

Comments

Accepted for publication at the ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2026)

R2 v1 2026-07-01T08:42:16.734Z