Reading between the lines: Modeling user behavior and costs in AI-assisted programming

H Mozannar, G Bansal, A Fourney… - Proceedings of the CHI …, 2024 - dl.acm.org
Code-recommendation systems, such as Copilot and CodeWhisperer, have the potential to
improve programmer productivity by suggesting and auto-completing code. However, to fully …

When to show a suggestion? Integrating human feedback in AI-assisted programming

H Mozannar, G Bansal, A Fourney… - Proceedings of the AAAI …, 2024 - ojs.aaai.org
AI powered code-recommendation systems, such as Copilot and CodeWhisperer, provide
code suggestions inside a programmer's environment (eg, an IDE) with the aim of improving …

Grounded copilot: How programmers interact with code-generating models

S Barke, MB James, N Polikarpova - Proceedings of the ACM on …, 2023 - dl.acm.org
Powered by recent advances in code-generating models, AI assistants like Github Copilot
promise to change the face of programming forever. But what is this new face of …

Taking Flight with Copilot: Early insights and opportunities of AI-powered pair-programming tools

C Bird, D Ford, T Zimmermann, N Forsgren… - Queue, 2022 - dl.acm.org
Over the next five years, AI-powered tools likely will be helping developers in many diverse
tasks. For example, such models may be used to improve code review, directing reviewers …

Evaluating the code quality of ai-assisted code generation tools: An empirical study on github copilot, amazon codewhisperer, and chatgpt

B Yetiştiren, I Özsoy, M Ayerdem, E Tüzün - arXiv preprint arXiv …, 2023 - arxiv.org
Context: AI-assisted code generation tools have become increasingly prevalent in software
engineering, offering the ability to generate code from natural language prompts or partial …

A large-scale survey on the usability of ai programming assistants: Successes and challenges

JT Liang, C Yang, BA Myers - Proceedings of the 46th IEEE/ACM …, 2024 - dl.acm.org
The software engineering community recently has witnessed widespread deployment of AI
programming assistants, such as GitHub Copilot. However, in practice, developers do not …

Bing developer assistant: improving developer productivity by recommending sample code

H Zhang, A Jain, G Khandelwal, C Kaushik… - Proceedings of the …, 2016 - dl.acm.org
In programming practice, developers often need sample code in order to learn how to solve
a programming-related problem. For example, how to reuse an Application Programming …

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

J Prather, BN Reeves, P Denny, BA Becker… - ACM Transactions on …, 2023 - dl.acm.org
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 …

Github copilot ai pair programmer: Asset or liability?

AM Dakhel, V Majdinasab, A Nikanjam… - Journal of Systems and …, 2023 - Elsevier
Automatic program synthesis is a long-lasting dream in software engineering. Recently, a
promising Deep Learning (DL) based solution, called Copilot, has been proposed by …

Studying the effect of AI code generators on supporting novice learners in introductory programming

M Kazemitabaar, J Chow, CKT Ma, BJ Ericson… - Proceedings of the …, 2023 - dl.acm.org
AI code generators like OpenAI Codex have the potential to assist novice programmers by
generating code from natural language descriptions, however, over-reliance might …