Computer Science Achievement and Writing Skills Predict Vibe Coding Proficiency

2026-03-14

AI Summary

This study addresses the lack of systematic understanding regarding the key competencies that underpin effective “vibe coding”—programming mediated by large language models. Employing a cross-sectional design within a controlled environment that simulates real-world tooling, the research investigates how computer science proficiency, general cognitive ability, and written communication skills predict vibe coding performance. Drawing on expert consensus to develop evaluation tasks and following a preregistered protocol with multiple regression analyses, the study provides the first empirical evidence that both writing ability and foundational computer science knowledge significantly predict success in vibe coding. Notably, computer science proficiency retains unique predictive power even after accounting for general cognitive factors. These findings offer crucial empirical insights for shaping programming education and designing developer tools in the AI era.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Language and Vision
• Humans and AI: Other Foundations of Human Computation & AI

Application Category

• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success

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.

Problem

• vibe coding
• programming skills
• predictors
• natural language programming
• software development

Innovation

• vibe coding
• LLM-driven programming
• writing skills
• computer science achievement
• predictive assessment