Large language model (LLM)-based ai for code model (e.g., Copilot) demonstrates the potential of using ai in specialized domains such as software engineering. While previous research has focused on fine-tuning models ...
详细信息
ISBN:
(纸本)9798350344172
Large language model (LLM)-based ai for code model (e.g., Copilot) demonstrates the potential of using ai in specialized domains such as software engineering. While previous research has focused on fine-tuning models with additional data and computational cost to construct models optimized for specific domains, our research focuses on prompt engineering methods that maximize the performance of existing models. We conducted a quantitative and qualitative user study using the ai for code model and identified two limitations that hinder the recommendation performance of the model. We propose two methods to address these limitations through effective prompt engineering. Finally, we identified the potential for the use of our proposed methods to be utilized and discussed the direction of future research for the effective use of the LLM.
In the rapidly evolving landscape of software engineering, the integration of Artificial Intelligence (ai) into the Software Development Life-Cycle (SDLC) heralds a transformative era for developers. Recently, we have...
详细信息
In the rapidly evolving landscape of software engineering, the integration of Artificial Intelligence (ai) into the Software Development Life-Cycle (SDLC) heralds a transformative era for developers. Recently, we have assisted to a pivotal shift towards ai-assisted programming, exemplified by tools like GitHub Copilot and Openai’s ChatGPT, which have become a crucial element for coding, debugging, and software design. In this paper we provide a comparative analysis between the current state of ai-assisted programming in 2024 and our projections for 2030, by exploring how ai advancements are set to enhance the implementation phase, fundamentally altering developers’ roles from manual coders to orchestrators of ai-driven development ecosystems. We envision HyperAssistant, an augmented ai tool that offers comprehensive support to 2030 developers, addressing current limitations in mental health support, fault detection, code optimization, team interaction, and skill development. We emphasize ai as a complementary force, augmenting developers’ capabilities rather than replacing them, leading to the creation of sophisticated, reliable, and secure software solutions. Our vision seeks to anticipate the evolution of programming practices, challenges, and future directions, shaping a new paradigm where developers and ai collaborate more closely, promising a significant leap in SE efficiency, security and creativity.
In recent years, there has been a notable surge in the generation of coding data on various platforms, including programming competitions and educational institutions. These platforms serve as repositories for substan...
详细信息
In recent years, there has been a notable surge in the generation of coding data on various platforms, including programming competitions and educational institutions. These platforms serve as repositories for substantial volumes of real-world code, problem descriptions, test cases, and activity logs. Despite this wealth of coding data, its potential for advancing software engineering, programming, and research remains largely unexplored. To the best of our knowledge, coding data has been partially explored and utilized in previous research projects such as codeNet and Alphacode, but has not been fully considered. There exists a compelling need to explore coding data in more depth to explore its potential for programming and research endeavors. Recognizing this gap, our study undertakes a comprehensive analysis of extensive coding data obtained from a programming learning platform. The aizu Online Judge (AOJ) serves as our chosen programming platform, providing access to coding data and its associated features. We collected approximately 9 million code evaluation logs, code files, as well as a substantial number of problem descriptions and input/output test cases for thorough analysis and experimentation. The goal of this study is to explore the full potential of the coding data for latent knowledge extraction, programming, and research. We conducted experiments with code evaluation logs, code files, problem descriptions, and test cases to demonstrate the suitability of coding data for various research and applications. Additionally, this study introduces a comprehensive array of features and application programming interfaces (APIs) associated with the AOJ platform. These resources facilitate seamless access and use of coding data, making them a valuable tool for professional and educational initiatives as well as research endeavors.
暂无评论