Write code like a human will maintain it
One of the best things about LLMs is that they'll write code for you, all day long. Who cares about DRY? You don't have to be the one updating the same long con...
One of the best things about LLMs is that they'll write code for you, all day long. Who cares about DRY? You don't have to be the one updating the same long conditional in four different files - the AI will just do it for you! Right? I've noticed myself letting it slide recently on a project I'd been building with AI. I needed the same access check in a handful of places: a route handler, a background job, an API endpoint, a webhook, etc. Each time, I'd describe what I needed, the model would generate something that worked, and I'd merge it. Each version looked roughly like this: if…
saved by
related reading
- Here’s how I use LLMs to help me write codesimonwillison.net
- GitHub - multica-ai/andrej-karpathy-skills: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. · GitHubgithub.com
- crawshaw - 2025-01-06crawshaw.io
- Best practices for Claude Code - Claude Code Docsanthropic.com
- I Know When You're Vibe Coding | Alex Kondovalexkondov.com
- What We’ve Learned From A Year of Building with LLMs – Applied LLMsapplied-llms.org
- Prevent cognitive debt by manually retyping LLM-generated code — Ankur Sethi's Lab Notebookankursethi.com
- Scaling LLMs to larger codebases - Kieran Gillblog.kierangill.xyz
- Code is cheap. Show me the talk. - nadh.innadh.in
- Writing for LLMs So They Listen · Gwern.netgwern.net
- Coding Models Are Doing Too Much | whnrehiew.github.io
- Lean Software Scaling Laws · Gwern.netgwern.net