Search and Filter

"Can You Feel The Vibes?": An Exploration Of Novice Programmer Engagement With Vibe Coding

Date

AI Overview

Why it matters

Vibe coding promises to democratize software development through natural language prompting, but its educational implications and effectiveness for novice learners remain underexplored.

Study at a glance
  • Question: How do novice and mixed-experience teams use generative AI to build software prototypes during an educational hackathon?
  • Setting and data: A Brazilian public university, 31 undergraduate students from computing and non-computing majors in nine teams, one-day hackathon.
  • Method: Mixed methods including non-participant observations, an exit survey, and semi-structured interviews.
  • AI tools: ChatGPT, Claude, Lovable, V0, Cursor, Copilot
Key findings
  • Most participants reported that their final applications were functional, but 22 of 27 survey respondents noted their prototypes contained bugs requiring rework.
  • Teams chained multiple generative AI tools in pipeline workflows, using natural language prompts to rapidly scaffold interfaces while relying on human judgment for refinement.
  • Generative AI accelerated early drafting but encouraged premature convergence, as most participants explored five or fewer ideas during ideation.

Summary drafted with AI from the full paper and may contain errors. See the full paper for details.

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 investigating how novice programmers and mixed-experience teams engage with vibe coding. We organized an inclusive event at a Brazilian public university with 31 undergraduate participants from computing and non-computing disciplines, divided into nine teams. Through observations, an exit survey, and semi-structured interviews, we examined creative processes, tool usage patterns, collaboration dynamics, and learning outcomes. Findings reveal that vibe coding enabled rapid prototyping and cross-disciplinary collaboration, with participants developing prompt engineering skills and delivering functional demonstrations within time constraints. However, we observed premature convergence in ideation, uneven code quality requiring rework, and limited engagement with core software engineering practices. Teams adopted sophisticated workflows combining multiple AI tools in pipeline configurations, with human judgment remaining essential for critical 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.