Programming Quantum Computers with Large Language Models

TL;DR

This paper investigates the capability of GPT-4 to generate quantum circuits for different hardware platforms, highlighting its relative strengths and limitations in quantum programming accessibility.

Contribution

It provides an initial assessment of GPT-4's ability to write quantum circuits for IBM and Xanadu hardware, a novel exploration in quantum programming with LLMs.

Findings

GPT-4 performs better with IBM's superconducting qubit systems.

GPT-4's quantum circuit generation is limited for Xanadu's photonic devices.

The study highlights the potential and current limitations of LLMs in quantum programming.

Abstract

Large language models (LLMs) promise transformative change to fields as diverse as medical diagnosis, legal services, and software development. One reason for such an impact is LLMs' ability to make highly technical endeavors more accessible to a broader audience. Accessibility has long been a goal for the growing fields of quantum computing, informatics, and engineering, especially as more quantum systems become publicly available via cloud interfaces. Between programming quantum computers and using LLMs, the latter seems the more accessible task: while leveraging an LLM's fullest potential requires experience with prompt engineering, any literate person can provide queries and read responses. By contrast, designing and executing quantum programs -- outside of those available online -- requires significant background knowledge, from selection of operations for algorithm implementation to configuration choices for particular hardware specifications and providers. Current research is exploring LLM utility for classical software development, but there has been relatively little investigation into the same for quantum programming. Consequently, this work is a first look at how well an uncustomized, publicly available LLM can write straightforward quantum circuits. We examine how well OpenAI's ChatGPT (GPT-4) can write quantum circuits for two hardware providers: the superconducting qubit machines of IBM and the photonic devices of Xanadu. We find that ChatGPT currently fares substantially better with the former.