AI-powered programming assistants are increasingly gaining popularity, with GitHub Copilot alone used by over a million developers worldwide. These tools are far from perfect, however, producing code suggestions that may be incorrect or incomplete in subtle ways. As a result, developers face a new set of challenges when they need to understand, validate, and choose between AI's suggestions. This paper explores whether Live Programming, a continuous display of a program's runtime values, can help address these challenges. We introduce Live Exploration of AI-Generated Programs, a new interaction model for AI programming assistants that supports exploring multiple code suggestions through Live Programming. We implement this interaction model in a prototype Python environment LEAP and evaluate it through a between-subject study. Our results motivate several design opportunities for future AI-powered programming tools.

翻译：人工智能编程助手正日益普及，仅GitHub Copilot一项就已拥有全球超过一百万名开发者。然而，这些工具远非完美，它们生成的代码建议可能以微妙的方式存在错误或不完整。因此，开发者在理解、验证和选择人工智能的建议时面临着一系列新挑战。本文探讨了实时编程（一种持续显示程序运行时值的技术）是否有助于应对这些挑战。我们引入了"AI生成程序的实时探索"这一面向AI编程助手的新型交互模型，该模型支持通过实时编程来探索多个代码建议。我们在原型Python环境LEAP中实现了该交互模型，并通过组间实验对其进行了评估。研究结果为未来AI编程工具的设计提供了若干机遇。