Building Software by Rolling the Dice: A Qualitative Study of Vibe Coding
By: Yi-Hung Chou , Boyuan Jiang , Yi Wen Chen and more
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.
Similar Papers
A Survey of Vibe Coding with Large Language Models
Artificial Intelligence
Helps computers write code by watching results.
"Can you feel the vibes?": An exploration of novice programmer engagement with vibe coding
Software Engineering
Lets anyone build computer programs by talking.
Good Vibrations? A Qualitative Study of Co-Creation, Communication, Flow, and Trust in Vibe Coding
Software Engineering
Helps coders work with AI more smoothly.