Use Your Brain: Engineering Standards in the Age of LLMs

This article discusses the impact of large language models (LLMs) on software development practices. It argues that while LLMs enable faster coding, many engineers fall into the 'vibe-coding' trap, producing low-quality code without understanding it. The author emphasizes the importance of maintaining engineering standards, code ownership, and the ability to explain and debug code independently. It warns against relying solely on LLMs for edits, which can lead to loss of control and codebase degradation. The piece advocates for balanced AI use with rigorous processes, testing, and best practices to avoid becoming a 'cowboy coder' in the pursuit of speed.