Kai Zhang, Vyom Kumar and Max Zhang, USA

In the history of computer science, the development of algorithms has long been pivotal to building the many programs used every day by civilians, such as programs for texting, entertainment, research, and anything on the internet. However, this programming remains time-consuming, and expensive, and requires years of expertise to master. Even if completing a singular project is not particularly difficult, the knowledge required to create that project might take years to learn. Since the development of AI, the process of fabricating algorithms has been shortened greatly. Anybody with internet access can make software using AI, but a novice in programming would still struggle with creating new code from a Pseudocode created by AI. By utilizing the OpenAI API, we created InteractiveWeb, a program that takes input from a user, sends it to ChatGPT, and, after creating an initial model of that program, repeatedly develops a new and improved version based on previous code. With this program, the AI could accurately develop instructed projects, allowing it to create the fully working games of Minesweeper, Connect 4, and even Chess by repeatedly refining code based on user feedback and self-debugging. InteractiveWeb aims to lower barriers to entry for novice programmers, foster creativity, and reduce burnout often associated with manual code development. Key results demonstrate improved coding efficiency, accuracy of results, and user satisfaction, highlighting the system’s potential as a transformative educational and development tool.

AI, OpenAI, ChatGPT, Code Generation, Software Engineering using AI, AI-created Software