Examining Autocompletion as a Basic Concept for Interaction with Generative AI

Abstract

Autocompletion is an approach that extends and continues partial user input. We propose to interpret autocompletion as a basic interaction concept in human-AI interaction. We first describe the concept of autocompletion and dissect its user interface and interaction elements, using the well-established textual autocompletion in search engines as an example. We then highlight how these elements reoccur in other application domains, such as code completion, GUI sketching, and layouting. This comparison and transfer highlights an inherent role of such intelligent systems to extend and complete user input, in particular useful for designing interactions with and for generative AI. We reflect on and discuss our conceptual analysis of autocompletion to provide inspiration and a conceptual lens on current challenges in designing for human-AI interaction.

arXiv commentThis is an author version, see DOI for original article

References in corpus (8)

• Efficient Estimation of Word Representations in Vector Space
• Image Inpainting via Generative Multi-column Convolutional Neural Networks
• Generative Image Inpainting with Contextual Attention
• Pythia: AI-assisted Code Completion System
• GRIDS: Interactive Layout Design with Integer Programming
• Auto-completion for Data Cells in Relational Tables
• Sketchforme: Composing Sketched Scenes from Text Descriptions for Interactive Applications
• BlackBox Toolkit: Intelligent Assistance to UI Design

Cited by in corpus (2)

• CatAlyst: Domain-Extensible Intervention for Preventing Task Procrastination Using Large Generative Models
• Strategyproof Learning: Building Trustworthy User-Generated Datasets