Coding With AI: From a Reflection on Industrial Practices to Future Computer Science and Software Engineering Education
Hung-Fu Chang, MohammadShokrolah Shirazi, Lizhou Cao, Supannika Koolmanojwong Mobasser
TL;DR
The paper investigates how large language model (LLM) coding tools are used in professional practice and their implications for education by analyzing 57 curated YouTube videos (Dec 2024–Oct 2025). It defines vibe coding and agentic coding as two AI-enabled development modes and situates them along a spectrum with AI-assisted coding, comparing them to traditional coding. Key findings show that AI accelerates code production and broadens participation while shifting bottlenecks to code review, testing, and system-level reasoning, and raise concerns about code quality, security, ethics, and skill erosion among beginners. The study offers educational guidance, arguing for curricular shifts toward problem-solving, architectural thinking, specification-driven development, and early project-based learning that integrate LLM tools. These insights provide an industry-grounded basis for aligning computer science and software engineering education with rapidly evolving professional practices.
Abstract
Recent advances in large language models (LLMs) have introduced new paradigms in software development, including vibe coding, AI-assisted coding, and agentic coding, fundamentally reshaping how software is designed, implemented, and maintained. Prior research has primarily examined AI-based coding at the individual level or in educational settings, leaving industrial practitioners' perspectives underexplored. This paper addresses this gap by investigating how LLM coding tools are used in professional practice, the associated concerns and risks, and the resulting transformations in development workflows, with particular attention to implications for computing education. We conducted a qualitative analysis of 57 curated YouTube videos published between late 2024 and 2025, capturing reflections and experiences shared by practitioners. Following a filtering and quality assessment process, the selected sources were analyzed to compare LLM-based and traditional programming, identify emerging risks, and characterize evolving workflows. Our findings reveal definitions of AI-based coding practices, notable productivity gains, and lowered barriers to entry. Practitioners also report a shift in development bottlenecks toward code review and concerns regarding code quality, maintainability, security vulnerabilities, ethical issues, erosion of foundational problem-solving skills, and insufficient preparation of entry-level engineers. Building on these insights, we discuss implications for computer science and software engineering education and argue for curricular shifts toward problem-solving, architectural thinking, code review, and early project-based learning that integrates LLM tools. This study offers an industry-grounded perspective on AI-based coding and provides guidance for aligning educational practices with rapidly evolving professional realities.