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

TL;DR

This paper investigates how programmers interact with AI-assisted coding tools like GitHub Copilot, developing a taxonomy to understand behaviors, identify inefficiencies, and suggest improvements for human-AI collaboration.

Contribution

Introduces CUPS, a taxonomy of programmer activities with Copilot, and provides empirical insights into user interactions and associated costs, guiding interface design enhancements.

Findings

CUPS effectively categorizes programmer activities with Copilot.

Identifies common inefficiencies and time costs in user interactions.

Provides insights for designing better AI-assisted programming interfaces.

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.