If coding is solved, what now?: Measuring the sloppiness of code
The author discusses the challenge of measuring 'code sloppiness' in an era where LLMs can generate formally correct code. The piece argues that while AI excels at functional correctness, it often fails to maintain code quality, leading to unnecessary complexity.
Why it matters
This highlights a growing concern in software engineering regarding the long-term maintainability of AI-generated codebases.
From: Sebastian < sebastian@earendil.com >
Subject: If coding is solved, what now?: Measuring the sloppiness of code
LLMs have become almost perfect at generating code, but that isn’t the end of the story. Just because the code is formally correct doesn’t mean that it is not introducing unnecessary abstractions, creating duplicates, or just making bad decisions overall. This is not a groundbreaking observation, most people who have vibe-coded a project, have realized that each additional feature can sometimes lead to an explosion of lines of code (LOC).
This results in a loss of human agency, because in projects that are adding millions of LOC per month, it is hard for humans to keep up. 1 Some people might say that that is not an issue at all, because they trust their agents to deal with it. I have bad news for you, agents can't really deal with the slop either.
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