Code for All: Educational Applications of the "Vibe Coding" Hackathon in Programming Education across All Skill Levels

TL;DR

This study explores the educational impact of vibe coding using large language models in a hackathon setting, analyzing how participants of various skill levels engage with AI-generated code tasks.

Contribution

It provides insights into how AI-assisted coding influences learning processes and practices across different skill levels in a competitive educational environment.

Findings

Participants with diverse backgrounds adapt their prompting and debugging as task complexity increases.

The no manual editing constraint affects how participants interact with AI-generated code.

The study offers implications for integrating AI tools into programming education and competitions.

Abstract

The emergence of large language models has enabled vibe coding, a natural language approach to programming in which users describe intent and AI generates or revises code, potentially broadening access to programming while preserving meaningful learning outcomes. We investigate its educational value through a month-long online hackathon that welcomed participants from multiple countries, ranging from complete beginners to experienced developers. The hackathon offered three tracks with increasing technical demands. Spark emphasized basic frontend functionality and dynamic features such as buttons, forms, and API calls. Build required backend or database integration. Launch targeted production ready web applications, including deployment. Participants were required to develop projects using only LLM generated code without manual edits and submitted complete chat histories, source code, demo videos, and functionality reports. We assessed educational effectiveness with a mixed methods design that combined standardized project evaluations across functionality, user interface and user experience design, impact, prompt quality, and code readability, along with post-hackathon surveys of perceived learning outcomes and thematic analysis of open-ended feedback. Our findings describe how participants with different backgrounds engage with vibe coding as task complexity increases, how the no manual editing constraint shapes prompting and debugging practices, and what these patterns imply for integrating AI assisted development into programming education and competitive learning environments.