"It's Weird That it Knows What I Want": Usability and Interactions with Copilot for Novice Programmers

TL;DR

This study investigates how novice programmers interact with GitHub Copilot, revealing perceptions, interaction patterns, and challenges, and discusses design improvements to better support learning with AI-assisted coding tools.

Contribution

First observational study of novice students using GitHub Copilot in a classroom setting, highlighting interaction behaviors and cognitive challenges.

Findings

Students perceive Copilot as helpful but sometimes confusing.

New interaction patterns include reliance and verification behaviors.

Students face cognitive and metacognitive difficulties when using Copilot.

Abstract

Recent developments in deep learning have resulted in code-generation models that produce source code from natural language and code-based prompts with high accuracy. This is likely to have profound effects in the classroom, where novices learning to code can now use free tools to automatically suggest solutions to programming exercises and assignments. However, little is currently known about how novices interact with these tools in practice. We present the first study that observes students at the introductory level using one such code auto-generating tool, Github Copilot, on a typical introductory programming (CS1) assignment. Through observations and interviews we explore student perceptions of the benefits and pitfalls of this technology for learning, present new observed interaction patterns, and discuss cognitive and metacognitive difficulties faced by students. We consider design implications of these findings, specifically in terms of how tools like Copilot can better support and scaffold the novice programming experience.