Grounded Copilot: How Programmers Interact with Code-Generating Models-Reference-Cited by-同舟云学术

Grounded Copilot: How Programmers Interact with Code-Generating Models

Published:2023-04-06 Issue:OOPSLA1 Volume:7 Page:85-111
ISSN:2475-1421
Container-title:Proceedings of the ACM on Programming Languages
language:en
Short-container-title:Proc. ACM Program. Lang.

Author:

Barke Shraddha¹^ORCID,James Michael B.¹^ORCID,Polikarpova Nadia¹^ORCID

Affiliation:

1. University of California at San Diego, USA

Abstract

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 programming? We present the first grounded theory analysis of how programmers interact with Copilot, based on observing 20 participants—with a range of prior experience using the assistant—as they solve diverse programming tasks across four languages. Our main finding is that interactions with programming assistants are bimodal : in acceleration mode , the programmer knows what to do next and uses Copilot to get there faster; in exploration mode , the programmer is unsure how to proceed and uses Copilot to explore their options. Based on our theory, we provide recommendations for improving the usability of future AI programming assistants.

Publisher

Association for Computing Machinery (ACM)

Subject

Safety, Risk, Reliability and Quality,Software

Link

https://dl.acm.org/doi/pdf/10.1145/3586030

Reference67 articles.

1. Matej Balog , Alexander L Gaunt , Marc Brockschmidt , Sebastian Nowozin , and Daniel Tarlow . 2016 . Deepcoder: Learning to write programs. arXiv preprint arXiv:1611.01989. Matej Balog, Alexander L Gaunt, Marc Brockschmidt, Sebastian Nowozin, and Daniel Tarlow. 2016. Deepcoder: Learning to write programs. arXiv preprint arXiv:1611.01989.

2. Mohammad Bavarian Heewoo Jun Nikolas Tezak John Schulman Christine McLeavey Jerry Tworek and Mark Chen. 2022. Efficient Training of Language Models to Fill in the Middle. Jul https://doi.org/10.48550/arXiv.2207.14255 arXiv:2207.14255 [cs]. 10.48550/arXiv.2207.14255

3. Mohammad Bavarian Heewoo Jun Nikolas Tezak John Schulman Christine McLeavey Jerry Tworek and Mark Chen. 2022. Efficient Training of Language Models to Fill in the Middle. Jul https://doi.org/10.48550/arXiv.2207.14255 arXiv:2207.14255 [cs].

4. Tom Brown , Benjamin Mann , Nick Ryder , Melanie Subbiah , Jared D Kaplan , Prafulla Dhariwal , Arvind Neelakantan , Pranav Shyam , Girish Sastry , and Amanda Askell . 2020. Language models are few-shot learners. Advances in neural information processing systems, 33 ( 2020 ), 1877–1901. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, and Amanda Askell. 2020. Language models are few-shot learners. Advances in neural information processing systems, 33 (2020), 1877–1901.

Cited by 18 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Incorporating Generative AI into Software Development Education;Proceedings of the 8th Conference on Computing Education Practice;2024-01-05

2. Challenges Engaging Formal CBSE in Industrial Applications;Formal Aspects of Component Software;2024

3. The Robots Are Here: Navigating the Generative AI Revolution in Computing Education;Proceedings of the 2023 Working Group Reports on Innovation and Technology in Computer Science Education;2023-12-22

4. Evaluating the Usability and Functionality of Intelligent Source Code Completion Assistants: A Comprehensive Review;Applied Sciences;2023-12-07

5. Generating Programs Trivially: Student Use of Large Language Models;Proceedings of the ACM Conference on Global Computing Education Vol 1;2023-12-05