If coding is solved, what now?: Measuring the sloppiness of code
The article argues that while LLMs have become proficient at generating syntactically correct code, they often introduce unnecessary complexity and redundancy that undermine human oversight. The author critiques current industry approaches, such as using AI as a judge, for being unreliable and lacking the nuance required to assess code quality. To address this, the text proposes quantitative metrics like lines of code, verbosity, and erosion to objectively measure and mitigate the accumulation of 'sloppy' code in AI-generated projects.
- ▪LLMs can generate formally correct code but frequently introduce unnecessary abstractions and duplicates that lead to an explosion in lines of code.
- ▪Using AI models to judge the quality of their own code is considered unreliable because it often fails to provide consistent or meaningful evaluations.
- ▪The author identifies simple metrics like the change in lines of code as surprisingly effective indicators of code sloppiness despite their limitations.
- ▪Advanced metrics such as verbosity and erosion are proposed to quantify code quality by measuring duplicated lines and the concentration of complexity in large functions.
Hacker News (Front Page) files mainly under programming. We currently carry 1,487 of its stories. Top-voted stories on Hacker News.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Earendil |
| Canonical URL | https://earendil.com/posts/measuring-code-sloppiness/ |
| Publication time | Fri, 11 Sep 2026 13:42:28 +0000 |
| Retrieval time | 2026-09-11T14:12:51.500Z |
| Last seen | 2026-09-11T14:12:51.500Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | zRvLccgLx7ue · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
If coding is solved, what now?: Measuring the sloppiness of code Date:Thu, 10 Sep 2026 From:Sebastian <[email protected]> To:You 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).
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Earendil.
Discussion
0 commentsMore from Earendil
