AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
TL;DR
This chapter investigates how the quality of code can be automatically assessed by checking for for the presence of code smells and how this approach can contribute to automatic codecode inspection.
A systematic literature review of JavaScript code smell detection tools found that most tools use rule-based linting, which is efficient but struggles with complex architectural smells, and AI-driven detection is completely missing.
An approach to verifying the results of static code analysis using large language models (LLMs), which filters warnings to eliminate false positives, which was implemented in SharpChecker, an industrial static analyzer for C#.
The results suggest that increasing \textit{smell density} was generally associated with lower test-suite-based functional correctness, although non-smelly requirements could still produce faulty code, and motivates further investigation into task-dependent quality effects in LLM-assisted software engineering.
This study compares the structural quality of code produced by three widely adopted vibe coding tools --- Lovable, v0, and Replit --- starting from a single generation prompt and suggests that choosing between vibe coding tools involves structural trade-offs that go beyond perceived productivity.
It is observed that generated code often omits basic input validation or memory-safety checks, which can lead to overflows, resource exhaustion, or other reliability/security issues, and even the largest models frequently make simple mistakes.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.