Computer Science Achievement and Writing Skills Predict Vibe Coding Proficiency
Human-Computer InteractionSoftware Engineering
Summary
The authors studied how well students can use "vibe coding," a way of programming by giving instructions in natural language instead of writing code directly. They tested 100 students on their computer science knowledge, general thinking skills, writing ability, and vibe-coding performance. Their results showed that students' writing skills and computer science knowledge both helped them do better at vibe coding. Even when considering general thinking skills, computer science knowledge still stood out as important. This suggests that learning both programming basics and how to write clear instructions is useful for this type of coding.
Authors
Sverrir Thorgeirsson, Theo B. Weidmann, Zhendong Su
Abstract
Many software development platforms now support LLM-driven programming, or "vibe coding", a technique that allows one to specify programs in natural language and iterate from observed behavior, all without directly editing source code. While its adoption is accelerating, little is known about which skills best predict success in this workflow. We report a preregistered cross-sectional study with tertiary-level students (N = 100) who completed measures of computer-science achievement, domain-general cognitive skills, written-communication proficiency, and a vibe-coding assessment. Tasks were curated via an eight-expert consensus process and executed in a purpose-built, vibe-coding environment that mirrors commercial tools while enabling controlled evaluation. We find that both writing skill and CS achievement are significant predictors of vibe-coding performance, and that CS achievement remains a significant predictor after controlling for domain-general cognitive skills. The results may inform tool and curriculum design, including when to emphasize prompt-writing versus CS fundamentals to support future software creators.