AI-Augmented Code Generation
DOI:
https://doi.org/10.70356/jafotik.v3i1.53Keywords:
AI-augmented code generation, Software development, Deep learning modelsAbstract
AI-augmented code generation is transforming software development by enhancing productivity, reducing repetitive tasks, and improving code quality. Tools like GitHub Copilot, OpenAI Codex, and IntelliCode assist developers by providing real-time code suggestions, generating functions from natural language prompts, and detecting potential errors. This technology simplifies coding workflows, allowing programmers to focus on complex problem-solving rather than routine coding tasks.AI-powered tools rely on deep learning models trained on vast code repositories to understand context and generate relevant code snippets. While these tools significantly speed up development, they also introduce challenges such as security risks, computational costs, and the need for human oversight. Despite these concerns, AI-driven coding assistants are proving invaluable in modern software engineering, supporting applications in cloud computing, competitive programming, and full-stack development.Beyond simple code suggestions, AI assists with debugging, performance optimization, and even full project generation. As AI models continue to evolve, their integration into software development will further enhance efficiency and accessibility.
Downloads
References
S. L. France, “Navigating software development in the ChatGPT and GitHub Copilot era,” Bus. Horiz., vol. 67, no. 5, pp. 649–661, 2024, doi: https://doi.org/10.1016/j.bushor.2024.05.009.
I. A. Zahid et al., “Unmasking large language models by means of OpenAI GPT-4 and Google AI: A deep instruction-based analysis,” Intell. Syst. with Appl., vol. 23, no. February, p. 200431, 2024, doi: https://doi.org/10.1016/j.iswa.2024.200431.
Y. Xiao, X. Zuo, X. Lu, J. Song, and X. Cao, “Promises and perils of using Transformer-based models for SE research,” Neural Networks, vol. 184, no. July 2024, p. 107067, 2025, doi: https://doi.org/10.1016/j.neunet.2024.107067.
D. Cotroneo, R. De Luca, and P. Liguori, “DeVAIC: A Tool for Security Assessment of AI-generated Code,” Inf. Softw. Technol., vol. 177, no. April 2024, p. 107572, 2024, doi: https://doi.org/10.1016/j.infsof.2024.107572.
U. Bezirhan and M. von Davier, “Automated reading passage generation with OpenAI’s large language model,” Comput. Educ. Artif. Intell., vol. 5, no. May, p. 100161, 2023, doi: https://doi.org/10.1016/j.caeai.2023.100161.
K. S. Kalyan, “A survey of GPT-3 family large language models including ChatGPT and GPT-4,” Nat. Lang. Process. J., vol. 6, no. December 2023, p. 100048, 2024, doi: https://doi.org/10.1016/j.nlp.2023.100048.
D. Benfenati, G. M. De Filippis, A. M. Rinaldi, C. Russo, and C. Tommasino, “A Retrieval-augmented Generation application for Question-Answering in Nutrigenetics Domain,” Procedia Comput. Sci., vol. 246, no. C, pp. 586–595, 2024, doi: https://doi.org/10.1016/j.procs.2024.09.467.
A. Namoun, A. Alrehaili, Z. U. Nisa, H. Almoamari, and A. Tufail, “Predicting the usability of mobile applications using AI tools: The rise of large user interface models, opportunities, and challenges,” Procedia Comput. Sci., vol. 238, pp. 671–682, 2024, doi: https://doi.org/10.1016/j.procs.2024.06.076.
R. Pierdicca, F. Tonetto, M. Paolanti, M. Mameli, R. Rosati, and P. Zingaretti, “DeepReality: An open source framework to develop AI-based augmented reality applications,” Expert Syst. Appl., vol. 249, no. PA, p. 123530, 2024, doi: https://doi.org/10.1016/j.eswa.2024.123530.
K. Misiejuk, R. Kaliisa, and J. Scianna, “Augmenting assessment with AI coding of online student discourse: A question of reliability,” Comput. Educ. Artif. Intell., vol. 6, no. December 2023, p. 100216, 2024, doi: https://doi.org/10.1016/j.caeai.2024.100216.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 juan jacob erizo
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
