Choose Your Programming Copilot: A Comparison of the Program Synthesis Performance of GitHub Copilot and Genetic Programming
Created by W.Langdon from
gp-bibliography.bib Revision:1.8098
- @Misc{DBLP:journals/corr/abs-2111-07875,
-
author = "Dominik Sobania and Martin Briesch and
Franz Rothlauf",
-
title = "Choose Your Programming Copilot: A Comparison of the
Program Synthesis Performance of {GitHub} Copilot and
Genetic Programming",
-
howpublished = "arXiv",
-
volume = "abs/2111.07875",
-
year = "2021",
-
month = "15 " # nov,
-
keywords = "genetic algorithms, genetic programming, Program
Synthesis, Genetic Programming, Large-Scale Language
Models, Codex, GitHub Copilot, Software Engineering",
-
URL = "https://arxiv.org/abs/2111.07875",
-
eprinttype = "arXiv",
-
eprint = "2111.07875",
-
timestamp = "Tue, 16 Nov 2021 00:00:00 +0100",
-
biburl = "https://dblp.org/rec/journals/corr/abs-2111-07875.bib",
-
bibsource = "dblp computer science bibliography, https://dblp.org",
-
size = "9 pages",
-
abstract = "GitHub Copilot, an extension for the Visual Studio
Code development environment powered by the large-scale
language model Codex, makes automatic program synthesis
available for software developers. This model has been
extensively studied in the field of deep learning,
however, a comparison to genetic programming, which is
also known for its performance in automatic program
synthesis, has not yet been carried out. In this paper,
we evaluate GitHub Copilot on standard program
synthesis benchmark problems and compare the achieved
results with those from the genetic programming
literature. In addition, we discuss the performance of
both approaches. We find that the performance of the
two approaches on the benchmark problems is quite
similar, however, in comparison to GitHub Copilot, the
program synthesis approaches based on genetic
programming are not yet mature enough to support
programmers in practical software development. Genetic
programming usually needs a huge amount of expensive
hand-labelled training cases and takes too much time to
generate solutions. Furthermore, source code generated
by genetic programming approaches is often bloated and
difficult to understand. For future work on program
synthesis with genetic programming, we suggest
researchers to focus on improving the execution time,
readability, and usability.",
- }
Genetic Programming entries for
Dominik Sobania
Martin Briesch
Franz Rothlauf
Citations