Tools for automated software code generation with prompt engineering, efficiency and the educational utilization potentials: A brief review
TL;DR
Fundamental concepts of generative artificial intelligence, the importance of prompt engineering, prompting techniques and strategies for improving the quality of responses generated by large language models, and the potential applications of these tools in programming education are presented.
Abstract
The development of generative artificial intelligence and large language models (LLMs) has enabled significant progress in automatic code generation and the application of AI systems in education and software engineering. This paper presents fundamental concepts of generative artificial intelligence, the importance of prompt engineering, prompting techniques and strategies for improving the quality of responses generated by large language models. Special attention is given to AI tools for code generation, their characteristics, operating principles and application in software development. The paper also analyzes studies that evaluate the performance, accuracy and quality of AI-generated code, as well as the potential applications of these tools in programming education. In addition to the advantages, challenges such as inaccurate responses, model bias, academic ethics and the need for human supervision are also discussed.