掷骰子式软件开发：关于氛围编码的质性研究 (Building Software by Rolling the Dice: A Qualitative Study of Vibe Coding)

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

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.

翻译：大型语言模型（LLMs）正通过催生“氛围编码”重塑软件工程实践，在该模式下开发者主要通过提示而非编写代码来构建软件。尽管这一模式被广泛宣传为生产力突破，但从业者如何实际定义并参与此类实践尚不明确。为阐明这一新兴现象，我们对20个氛围编码视频进行了扎根理论研究，包括7场直播编码会话（约16小时，254条提示）和13个观点视频（约5小时），并辅以对活动时长和提示意图的补充分析。研究发现了一系列行为谱系：部分氛围编码者几乎完全依赖AI且不检查代码，而另一些人则会审查并调整生成结果。无论采用何种方式，所有从业者都必须应对生成过程的随机性，调试与优化常被描述为“掷骰子”。此外，由编码者专业背景和对AI依赖程度所塑造的差异化心智模型，深刻影响着提示策略、评估实践及信任水平。这些发现为软件工程未来研究开辟了新方向，并为工具设计与教育实践提供了现实启示。