The Role of LLM in Next-Generation Integrated Development Environments

Abstract

The role of Large Language Models (LLM) in new generation integrated development environments (IDEs). Tools such as GitHub Copilot, IntelliCode and Alice Code Assistant are explored in the context of their use in programming. The authors examine how LLMs enable the automation of key development tasks, including code autocompletion, error detection, refactoring, and code generation, which result in increased development efficiency and improved code quality. Special emphasis is placed on how LLMs affect developers' cognitive processes, such as problem-solving abilities, creativity, and professional skills. A review of existing integrated development environments that utilize large language models. LLM functionality for code autocompletion, fragment generation, error detection and correction was evaluated. Comparative methods were applied to evaluate the effectiveness of LLM compared to traditional development tools. Special attention was paid to analyzing the cognitive load caused by the use of LLMs and assessing their impact on the creative process. The novelty of the research consists in the complex analysis of LLM application in modern IDEs, as well as in revealing their potential for increasing developers' productivity and improving the quality of program code. It is concluded that LLM integration into IDEs allows not only speeding up the process of code creation, but also considerably increasing its quality due to intellectual support and automation of the routine tasks. However, while the benefits of integrating LLMs into IDEs are clear, limitations related to cognitive load, ethical issues, data security, and the need to maintain a balance between automation and development of programmers' skills are also identified.

References

  1. Иванов К. Н., Захарова О. И. Обработка естественного языка. Применение языковых моделей // Актуальные проблемы информатики, радиотехники и связи. – 2023. – С. 155-156.
  2. Korostin O. Comparative analysis of NLP algorithms for optimizing communications in the maritime industry // Journal of science. Lyon. – 2024. – № 56. – C. 19-22.
  3. Qin Z., Yang S., Zhong Y. Hierarchically gated recurrent neural network for sequence modeling // Advances in Neural Information Processing Systems. – 2024. – V. 36.
  4. Узких Г. Ю. Применение трансформеров в обработке естественного языка // Вестник науки. – 2024. – Т. 4. – № 8 (77). – С. 186-189.
  5. Gweon H., Schonlau M. Automated classification for open-ended questions with BERT // Journal of Survey Statistics and Methodology. – 2024. – V. 12. – № 2. – P. 493-504.
  6. Liukko V., Knappe A., Anttila T., Hakala J. ChatGPT as a Full-Stack Web Developer // Generative AI for Effective Software Development. – Cham: Springer Nature Switzerland. – 2024. – P. 197-215.
  7. Ponomarev E. Optimizing android application performance: modern methods and practices // Sciences of Europe. – 2024. – № 149. – C. 62-64.
  8. Макарьян О. С. Разработка программного обеспечения с использованием искусственного интеллекта // Вестник магистратуры. – 2024. – С. 23.
  9. Бобунов А. Ю. Cравнение практик автоматизации тестирования в традиционных банках и финтех-компаниях // Дневник науки. 2024. № 8 [Электронный ресурс]. URL: http://www.dnevniknauki.ru/images/publications/2024/8/technics/Bobunov.pdf
  10. Koyanagi K., Wang D., Noguchi K., и т. д. Exploring the effect of multiple natural languages on code suggestion using github copilot // 2024 IEEE/ACM 21st International Conference on Mining Software Repositories (MSR). – 2024. – P. 481-486.
  11. Oh S., Lee K., Park S., Kim D. Poisoned chatgpt finds work for idle hands: exploring developers’ coding practices with insecure suggestions from poisoned ai models //2024 IEEE Symposium on Security and Privacy (SP). – 2024. – P. 1141-1159.
  12. Жикулина К. П., Перфильева Н. В., Мань Л. Цифровой страт парадигмы языка // Вестник Российского университета дружбы народов. Серия: Теория языка. Семиотика. Семантика. – 2024. – Т. 15. – № 2. – С. 364-375.
  13. Пекарева, В. В. Семантический анализ дефиниции «информация» в целях систематизации подходов и факторов обеспечения информационной безопасности в условиях цифровизации / В. В. Пекарева, Ю. И. Фроловская // Аграрное и земельное право. – 2024. – № 3(231). – С. 89-92. – doi: 10.47643/1815-1329_2024_3_89. – EDN PQGQDB
  14. Verner D. Integration of artificial intelligence in backend development // Annali d’Italia. – 2024. – № 59. – P. 88-91.

Supplementary files

Supplementary Files
Action
1. JATS XML

Согласие на обработку персональных данных

 

Используя сайт https://journals.rcsi.science, я (далее – «Пользователь» или «Субъект персональных данных») даю согласие на обработку персональных данных на этом сайте (текст Согласия) и на обработку персональных данных с помощью сервиса «Яндекс.Метрика» (текст Согласия).