If coding is solved, what now?: Measuring the sloppiness of code | EARENDIL
earendil.com · 1,216 words · saved by 1 readers
Exploring how to measure code sloppiness, why correct code can still erode a codebase, and why human intuition and taste still matter.
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…
saved by
related reading
- How coding agents read your code (and how to write for them)modem.dev
- Benchmarking Coding Agents on Databricks’ Multi-Million Line Codebasedatabricks.com
- Killing Coding Agent Slop With Adversarial Self-Playusetelos.ai
- Cognitive load is what mattersminds.md
- claude code is not making your product betterethanding.substack.com
- Code was our medium for thoughtwattenberger.com
- Coding Models Are Doing Too Much | whnrehiew.github.io
- Here’s how I use LLMs to help me write codesimonwillison.net
- Vibe engineeringsimonwillison.net
- Lean Software Scaling Laws · Gwern.netgwern.net
- Thoughts on slowing the fuck downmariozechner.at
- Agentic Coding is a Trap | Lars Fayelarsfaye.com