Results 1 to 10 of about 29,781 (199)

Asleep at the Keyboard? Assessing the Security of GitHub Copilot’s Code Contributions

2022 IEEE Symposium on Security and Privacy (SP), 2022
There is burgeoning interest in designing AI-based systems to assist humans in designing computing systems, including tools that automatically generate computer code. The most notable of these comes in the form of the first self-described “AI pair programmer,” GitHub Copilot, which is a language model trained over open-source GitHub code. However, code
Hammond Pearce, Ramesh Karri
exaly   +4 more sources

Is GitHub Copilot a Substitute for Human Pair-programming? An Empirical Study

2022 IEEE/ACM 44th International Conference on Software Engineering: Companion Proceedings (ICSE-Companion), 2022
This empirical study investigates the effectiveness of pair programming with GitHub Copilot in comparison to human pair-programming. Through an experiment with 21 participants we focus on code productivity and code quality.
Saki Imai
exaly   +3 more sources

Assessing GitHub Copilot in Solidity Development: Capabilities, Testing, and Bug Fixing

IEEE Access
In the rapidly evolving landscape of blockchain technology, the development of reliable and secure smart contracts represents one of several crucial challenges.
Gavina Baralla, Giacomo Ibba, Roberto Tonelli   +2 more
exaly   +4 more sources

AI in software programming: understanding emotional responses to GitHub Copilot

Information Technology and People
PurposeThe applications of Artificial Intelligence (AI) in various areas of professional and knowledge work are growing. Emotions play an important role in how users incorporate a technology into their work practices. The current study draws on work in the areas of AI-powered technologies adaptation, emotions, and the future of work, to investigate how
Farveh Farivar
exaly   +3 more sources

GitHub Copilot

Encuentro Internacional de Educación en Ingeniería, 2022
Durante el programa de ingeniería de sistemas se ha podido trabajar con muchas herramientas las cuales facilitan las enseñanzas de los temas que están enfocados al desarrollo del software al igual que el cloud computing. En esta ocasión se hablará de un nuevo método que salió recientemente, se llama GitHub Copilot; es un asistente que sirve para ...
Brayan Stiven Torrres Ovalle
openaire   +2 more sources

Assessing the quality of GitHub copilot’s code generation

Proceedings of the 18th International Conference on Predictive Models and Data Analytics in Software Engineering, 2022
The introduction of GitHub’s new code generation tool, GitHub Copilot, seems to be the first well-established instance of an AI pair-programmer. GitHub Copilot has access to a large number of open-source projects, enabling it to utilize more extensive code in various programming languages than other code generation tools.
Burak Yetistiren, Isik Ozsoy, Eray Tuzun
openaire   +3 more sources

An empirical evaluation of GitHub copilot's code suggestions

Proceedings of the 19th International Conference on Mining Software Repositories, 2022
GitHub and OpenAI recently launched Copilot, an “AI pair programmer” that utilizes the power of Natural Language Processing, Static Analysis, Code Synthesis, and Artificial Intelligence.
Nhan Nguyen, Sarah Nadi
openaire   +2 more sources

Practices and Challenges of Using GitHub Copilot: An Empirical Study [PDF]

International Conferences on Software Engineering and Knowledge Engineering, 2023
The 35th International Conference on Software Engineering and Knowledge Engineering (SEKE)
Beiqi Zhang, Peng Liang 0001, Xiyu Zhou, Aakash Ahmad, Muhammad Waseem   +4 more
openaire   +3 more sources

Measuring GitHub Copilot's Impact on Productivity

Communications of the ACM
Case study asks Copilot users about its impact on their productivity, and seeks to find their perceptions mirrored in user data.
Albert Ziegler 0001, Eirini Kalliamvakou, X. Alice Li, Andrew Rice, Devon Rifkin, Shawn Simister, Ganesh Sittampalam, Edward Aftandilian   +7 more
openaire   +2 more sources

On the Robustness of Code Generation Techniques: An Empirical Study on GitHub Copilot [PDF]

2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE), 2023
Software engineering research has always being concerned with the improvement of code completion approaches, which suggest the next tokens a developer will likely type while coding. The release of GitHub Copilot constitutes a big step forward, also because of its unprecedented ability to automatically generate even entire functions from their natural ...
Mastropaolo, Antonio, Pascarella, Luca, Guglielmi, Emanuela, Ciniselli, Matteo, Scalabrino, Simone, Oliveto, Rocco, Bavota, Gabriele   +6 more
openaire   +3 more sources