We characterize and demonstrate how the principles of direct manipulation can improve interaction with large language models. This includes: continuous representation of generated objects of interest; reuse of prompt syntax in a toolbar of commands; manipulable outputs to compose or control the effect of prompts; and undo mechanisms. This idea is exemplified in DirectGPT, a user interface layer on top of ChatGPT that works by transforming direct manipulation actions to engineered prompts. A study shows participants were 50% faster and relied on 50% fewer and 72% shorter prompts to edit text, code, and vector images compared to baseline ChatGPT. Our work contributes a validated approach to integrate LLMs into traditional software using direct manipulation. Data, code, and demo available at https://osf.io/3wt6s.

翻译：我们描述并论证了直接操作原则如何改善与大语言模型的交互。这包括：生成对象的连续表示；将提示语法复用到命令工具栏中；可操作的输出以组合或控制提示效果；以及撤销机制。该思想在DirectGPT中得到体现，这是一个基于ChatGPT的用户界面层，通过将直接操作行为转换为工程化提示来工作。一项研究表明，与基线ChatGPT相比，参与者在编辑文本、代码和矢量图像时速度提高了50%，且提示使用量减少50%，提示长度缩短72%。我们的工作提供了一种经过验证的方法，通过直接操作将大语言模型集成到传统软件中。数据、代码和演示见https://osf.io/3wt6s。