Is GitHub copilot a substitute for human pair-programming?
Author:
Top Cited Papers
Open Access
- 21 May 2022
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 319-321
Abstract
This empirical study investigates the effectiveness of pair programming with GitHub Copilot in comparison to human pair-programming. Through an experiment with 21 participants we focus on code productivity and code quality. For experimental design, a participant was given a project to code, under three conditions presented in a randomized order. The conditions are pair-programming with Copilot, human pair-programming as a driver, and as a navigator. The codes generated from the three trials were analyzed to determine how many lines of code on average were added in each condition and how many lines of code on average were removed in the subsequent stage. The former measures the productivity of each condition while the latter measures the quality of the produced code. The results suggest that although Copilot increases productivity as measured by lines of code added, the quality of code produced is inferior by having more lines of code deleted in the subsequent trial.Keywords
This publication has 3 references indexed in Scilit:
- How We Refactor, and How We Know ItIEEE Transactions on Software Engineering, 2011
- AI-Based Software Defect Predictors: Applications and Benefits in a Case StudyProceedings of the AAAI Conference on Artificial Intelligence, 2010
- Using task context to improve programmer productivity2006