AUTHOREA
Log in Sign Up Browse Preprints
LOG IN SIGN UP
Sadi Evren SEKER
Sadi Evren SEKER
Professor at Istanbul University
Prof. Dr. Şadi Evren Şeker is a renowned academic and expert in the fields of data science, artificial intelligence, and computer science. He is known for his research contributions in machine learning, natural language processing, big data, and decision support systems. Dr. Şeker has authored numerous publications and often focuses on innovative applications of AI and data analytics to solve complex problems across various sectors. Professional Background Academic Roles: He has served as a professor and researcher at various institutions, contributing to the development of curricula related to data science and AI. Research Interests: His work covers AI models, machine learning algorithms, predictive analytics, and their applications in finance, healthcare, and public services. Public Speaking and Consulting: Dr. Şeker frequently delivers talks and provides consultancy services on topics related to AI, big data, and digital transformation. Given his expertise, many companies and institutions collaborate with him for research projects, consultancy, and to leverage his insights in data-driven innovation.
Istanbul

Public Documents 1
Experiences and Challenges in AI-Driven Modular Software Development Using Large Lang...
Sadi Evren SEKER

Sadi Evren SEKER

October 12, 2024
The development of a modular software platform using large language models (LLMs) for code generation presents unique opportunities and challenges. This paper explores the experiences and difficulties encountered during the creation of an AI-driven business intelligence platform built with LLM assistance. By using an iterative approach to generate modular code, the project aimed to accelerate development and automate routine tasks. However, challenges such as inconsistency in the generated code, hallucinations, lack of long-term memory, and integration complexities emerged. These limitations necessitated manual intervention for code refinement, debugging, and integration to ensure project-wide consistency. The study discusses strategies to address these issues, including structured prompting, automated testing, and iterative refinement. The findings reveal that while LLMs significantly reduce development time and facilitate rapid prototyping, they are not a complete substitute for human expertise. The paper offers practical insights into optimizing the use of LLMs in software engineering, demonstrating both the potential benefits and current limitations of AI-assisted code generation in modular software projects.

| Powered by Authorea.com

  • Home