论文标题
接地副标题：程序员如何与代码生成模型互动
Grounded Copilot: How Programmers Interact with Code-Generating Models
论文作者
论文摘要
在代码生成模型的最新进展中，像Github Copilot这样的AI助手承诺将永远改变编程的面貌。但是，这是编程的新面孔？我们介绍了第一个基础理论分析，即程序员如何与Copilot互动，基于观察20名参与者（使用助手的一系列经验），他们解决了四种语言的各种编程任务。我们的主要发现是，与编程助手的互动是双峰的：在加速模式下，程序员知道下一步该怎么做，并使用Copilot来更快地到达那里；在勘探模式下，程序员不确定如何进行和使用Copilot探索他们的选项。基于我们的理论，我们提供了改善未来AI编程助理的可用性的建议。
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.
