Tag
An improved AI-based tool for detecting and analyzing code comments in software development.
The article introduces the term 'yap' to describe excessive, non-substantive text in LLM-generated code comments, highlighting challenges in human review of AI-augmented software development.
The article describes a tool that distinguishes AI-generated comments from human-written ones in code using linguistic features like character frequency, and discusses its methodology and implications.
Raymond Chen discusses the difference between comments that belong in code vs those in pull request descriptions, emphasizing durable code comments and point-in-time PR justifications.
The article criticizes poor documentation and commit messages in software development, warning that leaving no explanation for decisions is like giving future developers the middle finger.
This paper analyzes 35,361 GitHub code comments referencing AI use to develop a taxonomy of AI-assisted development activities, finding that developers primarily use LLMs for code implementation and enhancement, with subsequent human refactoring and bug fixes, and a temporal shift toward conceptual support over direct code generation.
The article argues that code and comments should be wrapped to different columns, with comment width relative to the comment start, and discusses how current editor tools don't properly support relative wrapping.