Code Readability in the Age of Large Language Models: An Industrial Case Study from Atlassian

TL;DR

This study investigates code readability in the era of large language models, showing that LLM-generated code is as readable as human-written code and emphasizing its importance for trust and adoption in software development.

Contribution

It provides an industrial case study comparing LLM-generated and human-written code readability, highlighting the continued importance of readability and trust in LLM-assisted development.

Findings

Readability remains crucial in software development.

LLM-generated code has comparable readability to human code.

Practitioners trust and adopt LLM-based development platforms.

Abstract

Software engineers spend a significant amount of time reading code during the software development process, especially in the age of large language models (LLMs) that can automatically generate code. However, little is known about the readability of the LLM-generated code and whether it is still important from practitioners' perspectives in this new era. In this paper, we conduct a survey to explore the practitioners' perspectives on code readability in the age of LLMs and investigate the readability of our LLM-based software development agents framework, HULA, by comparing its generated code with human-written code in real-world scenarios. Overall, the findings underscore that (1) readability remains a critical aspect of software development; (2) the readability of our LLM-generated code is comparable to human-written code, fostering the establishment of appropriate trust and driving the broad adoption of our LLM-powered software development platform.