What is it like to program with artificial intelligence?

TL;DR

This paper examines how large language models like Codex and AlphaCode are transforming programming, highlighting their unique properties, challenges, and implications for both expert and end-user programmers.

Contribution

It provides a comprehensive analysis of LLM-assisted programming, identifying its distinct characteristics and practical challenges compared to traditional programming assistance methods.

Findings

LLM-assisted programming shares similarities with compilation, pair programming, and search-based coding.

Fundamental differences exist in technical capabilities and user experience.

User study shows challenges faced by non-expert users in LLM-assisted tasks.

Abstract

Large language models, such as OpenAI's codex and Deepmind's AlphaCode, can generate code to solve a variety of problems expressed in natural language. This technology has already been commercialised in at least one widely-used programming editor extension: GitHub Copilot. In this paper, we explore how programming with large language models (LLM-assisted programming) is similar to, and differs from, prior conceptualisations of programmer assistance. We draw upon publicly available experience reports of LLM-assisted programming, as well as prior usability and design studies. We find that while LLM-assisted programming shares some properties of compilation, pair programming, and programming via search and reuse, there are fundamental differences both in the technical possibilities as well as the practical experience. Thus, LLM-assisted programming ought to be viewed as a new way of programming with its own distinct properties and challenges. Finally, we draw upon observations from a user study in which non-expert end user programmers use LLM-assisted tools for solving data tasks in spreadsheets. We discuss the issues that might arise, and open research challenges, in applying large language models to end-user programming, particularly with users who have little or no programming expertise.