Artificial intelligence as an effective tool in the development of systems for automatic generation and optimization
Published
:Issue
:Section
:License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Downloads
artificial intelligence, software development, automatic code generation, code optimization, machine learning, programming assistance, software engineering, large language models
Artificial intelligence (AI) has become one of the most influential technologies of the 21st century, transforming various sectors thanks to its ability to process vast amounts of information, identify patterns, and automate complex tasks. In the field of software development, advances in language models, deep learning, and intelligent systems have enabled the creation of tools capable of automatically generating, analyzing, and optimizing code, offering new opportunities to improve the efficiency of programming processes. Currently, both students and professionals face challenges related to the increasing complexity of computer systems, reducing development times, detecting errors, and optimizing application performance. In response to this situation, this research aimed to propose the development of an AI-based system for the automatic generation, analysis, and optimization of code, in order to support programming activities and strengthen the technical skills of its users. To this end, a mixed-methods approach with a descriptive scope was employed, integrating quantitative and qualitative techniques to analyze the impact of AI in the context of software development. The study included a review of specialized scientific literature, the conceptual design of the proposed system, and the application of surveys to 87 participants, including students, teachers, and software developers from the city of Cúcuta. The results revealed a generally positive perception of the use of artificial intelligence tools in programming: 78% of respondents expressed familiarity with at least one intelligent assistance tool, and more than 70% considered that these technologies significantly improve productivity, reduce development time, and facilitate error detection. Furthermore, automatic code generation was identified as the most used and valued functionality, followed by error correction and support for learning programming.
Chen, M., Tworek, J., Jun, H., Yuan, Q., de Oliveira Pinto, H. P., Kaplan, J., … Brockman, G. (2021). Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374. https://arxiv.org/abs/2107.03374
Copeland, B. J. (2023). Artificial intelligence: A philosophical introduction (2nd ed.). Wiley-Blackwell.
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of NAACL-HLT 2019, 4171–4186. https://doi.org/10.18653/v1/N19-1423
Fan, A., Gokkaya, B., Harman, M., Lyubarskiy, M., Sengupta, S., Yoo, S., & Zhang, J. M. (2023). Large language models for software engineering: Survey and open problems. arXiv preprint arXiv:2310.03533. https://arxiv.org/abs/2310.03533
Guo, D., Zhu, Q., Yang, D., Xie, Z., Dong, K., Zhang, W., … Liu, T. (2024). DeepSeek-Coder: When the large language model meets programming – the rise of code intelligence. arXiv preprint arXiv:2401.14196. https://arxiv.org/abs/2401.14196
Hernández Sampieri, R., Fernández Collado, C., & Baptista Lucio, P. (2014). Metodología de la investigación (6.ª ed.). McGraw-Hill / Interamericana Editores.
Jimenez, C., Yang, J., Wettig, A., Yao, S., Pei, K., Press, O., & Narasimhan, K. (2024). SWE-bench: Can language models resolve real-world GitHub issues? Proceedings of ICLR 2024. https://openreview.net/forum?id=VTF8yNQM66
Li, Y., Choi, D., Chung, J., Kushman, N., Schrittwieser, J., Leblond, R., … Vinyals, O. (2022). Competition-level code generation with AlphaCode. Science, 378(6624), 1092–1097. https://doi.org/10.1126/science.abq1158
Lozano, A., Margolis, M., & Chaudhuri, S. (2022). Clover: Closed-loop verifiable code generation. arXiv preprint arXiv:2208.08467. https://arxiv.org/abs/2208.08467
OpenAI. (2023). GPT-4 technical report. arXiv preprint arXiv:2303.08774. https://arxiv.org/abs/2303.08774
Prensky, M. (2001). Digital natives, digital immigrants. On the Horizon, 9(5), 1–6. https://doi.org/10.1108/10748120110424816
Talamantes-Álvarez, A., Torres-Huitzil, C., & Bribiesca-Correa, G. (2022). Revisión de técnicas de generación automática de código fuente asistidas por inteligencia artificial. Revista Iberoamericana de Inteligencia Artificial, 25(69), 44–61. https://doi.org/10.4114/intartif.vol25iss69pp44-61
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., … Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30, 5998–6008.
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., … Zhou, D. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35, 24824–24837.
Zheng, L., Chiang, W.-L., Sheng, Y., Zhuang, S., Wu, Z., Zhuang, Y., … Stoica, I. (2023). Judging LLM-as-a-judge with MT-bench and chatbot arena. Advances in Neural Information Processing Systems, 36, 46595–46623.
Artificial intelligence (AI) has become one of the most influential technologies of the 21st century, transforming various sectors thanks to its ability to process vast amounts of information, identify patterns, and automate complex tasks. In the field of software development, advances in language models, deep learning, and intelligent systems have enabled the creation of tools capable of automatically generating, analyzing, and optimizing code, offering new opportunities to improve the efficiency of programming processes. Currently, both students and professionals face challenges related to the increasing complexity of computer systems, reducing development times, detecting errors, and optimizing application performance. In response to this situation, this research aimed to propose the development of an AI-based system for the automatic generation, analysis, and optimization of code, in order to support programming activities and strengthen the technical skills of its users. To this end, a mixed-methods approach with a descriptive scope was employed, integrating quantitative and qualitative techniques to analyze the impact of AI in the context of software development. The study included a review of specialized scientific literature, the conceptual design of the proposed system, and the application of surveys to 87 participants, including students, teachers, and software developers from the city of Cúcuta. The results revealed a generally positive perception of the use of artificial intelligence tools in programming: 78% of respondents expressed familiarity with at least one intelligent assistance tool, and more than 70% considered that these technologies significantly improve productivity, reduce development time, and facilitate error detection. Furthermore, automatic code generation was identified as the most used and valued functionality, followed by error correction and support for learning programming.
Chen, M., Tworek, J., Jun, H., Yuan, Q., de Oliveira Pinto, H. P., Kaplan, J., … Brockman, G. (2021). Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374. https://arxiv.org/abs/2107.03374
Copeland, B. J. (2023). Artificial intelligence: A philosophical introduction (2nd ed.). Wiley-Blackwell.
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of NAACL-HLT 2019, 4171–4186. https://doi.org/10.18653/v1/N19-1423
Fan, A., Gokkaya, B., Harman, M., Lyubarskiy, M., Sengupta, S., Yoo, S., & Zhang, J. M. (2023). Large language models for software engineering: Survey and open problems. arXiv preprint arXiv:2310.03533. https://arxiv.org/abs/2310.03533
Guo, D., Zhu, Q., Yang, D., Xie, Z., Dong, K., Zhang, W., … Liu, T. (2024). DeepSeek-Coder: When the large language model meets programming – the rise of code intelligence. arXiv preprint arXiv:2401.14196. https://arxiv.org/abs/2401.14196
Hernández Sampieri, R., Fernández Collado, C., & Baptista Lucio, P. (2014). Metodología de la investigación (6.ª ed.). McGraw-Hill / Interamericana Editores.
Jimenez, C., Yang, J., Wettig, A., Yao, S., Pei, K., Press, O., & Narasimhan, K. (2024). SWE-bench: Can language models resolve real-world GitHub issues? Proceedings of ICLR 2024. https://openreview.net/forum?id=VTF8yNQM66
Li, Y., Choi, D., Chung, J., Kushman, N., Schrittwieser, J., Leblond, R., … Vinyals, O. (2022). Competition-level code generation with AlphaCode. Science, 378(6624), 1092–1097. https://doi.org/10.1126/science.abq1158
Lozano, A., Margolis, M., & Chaudhuri, S. (2022). Clover: Closed-loop verifiable code generation. arXiv preprint arXiv:2208.08467. https://arxiv.org/abs/2208.08467
OpenAI. (2023). GPT-4 technical report. arXiv preprint arXiv:2303.08774. https://arxiv.org/abs/2303.08774
Prensky, M. (2001). Digital natives, digital immigrants. On the Horizon, 9(5), 1–6. https://doi.org/10.1108/10748120110424816
Talamantes-Álvarez, A., Torres-Huitzil, C., & Bribiesca-Correa, G. (2022). Revisión de técnicas de generación automática de código fuente asistidas por inteligencia artificial. Revista Iberoamericana de Inteligencia Artificial, 25(69), 44–61. https://doi.org/10.4114/intartif.vol25iss69pp44-61
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., … Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30, 5998–6008.
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., … Zhou, D. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35, 24824–24837.
Zheng, L., Chiang, W.-L., Sheng, Y., Zhuang, S., Wu, Z., Zhuang, Y., … Stoica, I. (2023). Judging LLM-as-a-judge with MT-bench and chatbot arena. Advances in Neural Information Processing Systems, 36, 46595–46623.