The Four Horsemen of Agentic Coding
The author argues that agentic coding is degrading software quality and team culture by producing 'slop' that is difficult for humans to maintain. The piece suggests that AI-generated code is creating an 'AI wasteland' where human developers feel alienated from their own codebases.
Why it matters
It addresses the growing concern regarding the long-term maintainability and human-centricity of software development in an AI-dominated workflow.
Agentic coding is undeniably very useful. It’s also very bad. Or rather, it’s having some horrible effects on us, our craft, and our relationships with each other. I can feel it in my bones, and a lot of others can too. But whenever I try to explain what exactly is wrong, I find myself waving my hands wildly and jumping from point to point. What do you mean, what’s wrong? So many things are wrong!
Fine, here’s a list. 4 problems with no solution in sight–or, as I call them, the four horsemen of agentic coding.
LLM-generated code has a strong smell that makes codebases repulsive to humans.
LLMs aren’t humans, and the way they write code is... different. Not strictly worse, but different for sure. We quickly came up with a name for it—slop—and it undoubtedly carries a negative connotation.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in