一句话：首个关于程序员如何与 Copilot 交互的扎根理论研究，发现交互呈现加速与探索两种模式。
本文研究程序员如何与代码生成模型（如 GitHub Copilot）交互，旨在刻画这类 AI 编程助手带来的新型编程方式。作者对 20 名具有不同 Copilot 使用经验的参与者进行观察，让他们在四种语言上完成多样编程任务，并采用扎根理论方法分析交互过程。核心发现是交互呈双模态：在加速模式中，程序员清楚下一步做什么，借助 Copilot 更快实现；在探索模式中，程序员不确定如何推进，借助 Copilot 探索可能方案。基于该理论，作者为未来 AI 编程助手的可用性改进提出建议。
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.
@article{paperbot2039,
title = {Grounded Copilot: How Programmers Interact with Code-Generating Models},
author = {Shraddha Barke and Michael B. James and Nadia Polikarpova},
journal = {Proceedings of the ACM on Programming Languages},
volume = {7},
number = {OOPSLA1},
year = {2023},
doi = {10.1145/3586030}
}