Exploring the Impacts and Challenges of Vibe Coding Paradigm to Children's Programming Learning and Practices

要旨

Recent advances in generative AI have introduced a new programming paradigm—vibe coding, a natural language–driven mode of AI collaboration. While promising for adults, little is known about how children engage with this approach, especially in block-based environments. To explore this gap, we conducted workshops with children of varying Scratch experience (n=41) and interviewed five Scratch teachers. Our study investigates how vibe coding impacts children’s programming learning and practice, and what challenges arise. Findings show that vibe coding has both positive and negative impacts across three key contexts of children’s programming experience: acquisition, application, and creation. Across the stages of vibe coding—goal articulation, information interpretation, and outcome evaluation—children encounter distinct challenges. By examining the mismatches between core assumptions of vibe coding and children’s needs, and analyzing its applicability across different contexts, we offer child-centered design implications for future vibe coding systems and GenAI tools.

著者
Janice Jianing SI
University of Macau, Macao, China
Donglin Li
Anhui University of Science and Technology, huainan, Anhui, China
Qiuning Wang
Anhui Normal University, Wuhu, China
Alicia Wanyi Liu
University of Macau, Macau, China
Xin Lin
University of Macau, Macau, China
Yujun Zhu
Anhui Normal University, Wuhu, Anhui, China
Xiaobo Zhou
University of Macau, Macau, China
April Yi. Wang
ETH Zurich, Zurich, Switzerland
Kanye Ye WANG
University of Macau, Macao, China

会議: CHI 2026

ACM CHI Conference on Human Factors in Computing Systems

セッション: AI, Learning and Inclusion in Education

P1 - Room 114
7 件の発表
2026-04-16 20:15:00
2026-04-16 21:45:00