一句话：通过一日教育黑客松的观察与访谈，揭示 vibe coding 对新手在原型速度、协作与学习上的收益与局限。
“Vibe coding”指用自然语言提示而非直接编写代码来构造软件，随生成式 AI 与 AI 辅助编程兴起，被认为可推动软件开发民主化，但其教育意义尚缺实证。本文报告在巴西公立大学 UFPE 举办的一场为期一天的教育黑客松，参与者为计算与非计算专业的本科生。作者通过现场观察、离场问卷与半结构化访谈，考察其创作过程、工具使用、协作动态与学习情况。结果显示：vibe coding 支持快速原型与协作，参与者发展出提示工程能力并能交付可运行演示；但也出现创意过早收敛、代码质量参差需要返工、对核心软件工程实践参与有限等现象。团队通常组合多种 AI 工具，人的判断在精修环节仍不可或缺。9 小时的短时长形式对新手建立信心有效，也便于时间有限的参与者加入。作者认为，若配以发散思维、AI 输出批判性评估与对生产级质量的合理预期的显式支架，vibe coding 黑客松可作为低风险的学习环境。
Emerging alongside generative AI and the broader trend of AI-assisted coding, the term “vibe coding” refers to creating software via natural language prompts rather than direct code authorship. This approach promises to democratize software development, but its educational implications remain underexplored. This paper reports on a one-day educational hackathon at a Brazilian public university – Universidade Federal de Pernambuco (UFPE) – with undergraduate participants from computing and non-computing disciplines. Through observations, an exit survey, and semi-structured interviews, we examined creative processes, tool usage, collaboration dynamics, and learning. Findings reveal that vibe coding enabled rapid prototyping and collaboration, with participants developing prompt engineering skills and delivering functional demonstrations. However, we also observed premature convergence in ideation, uneven code quality requiring rework, and limited engagement with core software engineering practices. Teams combined multiple AI tools, with human judgment remaining essential for refinement. The short format (9 hours) proved effective for confidence-building among newcomers while accommodating participants with limited availability. We conclude that vibe coding hackathons can serve as valuable low-stakes learning environments when coupled with explicit scaffolds for divergent thinking, critical evaluation of AI outputs, and realistic expectations about production quality.
@inproceedings{paperbot12021,
title = {"Can you feel the vibes?": An exploration of novice programmer engagement with vibe coding},
author = {Kiev Gama and Filipe Calegario and Victoria Jackson and Alexander Nolte and Luiz Morais and Vinicius Cardoso Garcia},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3786580.3786992}
}