The Fine Balance Between Helping With Your Job and Taking It: AI Code Assistants Come to the Fore
- 29 January 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Software
- Vol. 41 (6) , 111-118
Abstract
AI code generation tools are reshaping the software engineering landscape. We provide recommendations for practitioners interested in these tools based on narratives we have collected regarding two AI code generation tools, GitHub Copilot and Tabnine.Keywords
Funding Information
- Natural Sciences and Engineering Research Council of Canada (RGPIN-2014-04870, GR023171)
- National Council for Scientific and Technological Development (420406/2023-9, 442779/2023-2)
This publication has 9 references indexed in Scilit:
- Expectation vs. Experience: Evaluating the Usability of Code Generation Tools Powered by Large Language Models2022
- Neural software analysisCommunications of the ACM, 2021
- Naturally!: How Breakthroughs in Natural Language Processing Can Dramatically Help DevelopersIEEE Software, 2021
- Perfection Not Required? Human-AI Partnerships in Code Translation2021
- The SPACE of Developer ProductivityQueue, 2021
- Dimensions of artificial intelligence anxiety based on the integrated fear acquisition theoryTechnology in Society, 2020
- Reboot for the AI revolutionNature, 2017
- What's hot in software engineering Twitter space?2015
- Software engineering at the speed of light: how developers stay current using twitter2014