Tag
An essay arguing that code review is a learnable skill, referencing research on Google's code review practices and addressing common claims about LLM-based review. Aimed at software developers.
The article argues that agentic coding, where AI generates code and humans act as orchestrators, is a trap due to increased system complexity, skill atrophy, and vendor lock-in. It highlights the negative impact on developer learning and critical thinking, contrasting this new abstraction with historical programming shifts.