Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming

Abstract

Code-recommendation systems, such as Copilot and CodeWhisperer, have the potential to improve programmer productivity by suggesting and auto-completing code. However, to fully realize their potential, we must understand how programmers interact with these systems and identify ways to improve that interaction. To seek insights about human-AI collaboration with code recommendations systems, we studied GitHub Copilot, a code-recommendation system used by millions of programmers daily. We developed CUPS, a taxonomy of common programmer activities when interacting with Copilot. Our study of 21 programmers, who completed coding tasks and retrospectively labeled their sessions with CUPS, showed that CUPS can help us understand how programmers interact with code-recommendation systems, revealing inefficiencies and time costs. Our insights reveal how programmers interact with Copilot and motivate new interface designs and metrics.

CHI 2024

Cited by in corpus (5)

• Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Review
• LLM-Based Test-Driven Interactive Code Generation: User Study and Empirical Evaluation
• Investigating and Designing for Trust in AI-powered Code Generation Tools
• Validating AI-Generated Code with Live Programming
• CoEdPilot: Recommending Code Edits with Learned Prior Edit Relevance, Project-wise Awareness, and Interactive Nature