Hacker News Reader

I think the issue is deeper than prompts, agents.md, smart flows, etc. I think the problem is that LLMs are searchers, trained on preferring some results. So, if the dumb solution is there, and the smart solution is not there, they won't spit it out.

> AGENTS.md

-- which will be ignored just often enough that you can never quite trust it.

Yup. No matter how much you tell it to keep things simple, modular, crisp, whatever, it generates tons of garbage much too often.

And yet still less often than the average developer.

Btw it may be obvious but afaik claude by default only reads CLAUDE.md and not AGENTS.md

By all means elaborate. I can't imagine "don't have stupid ideas or write messy code" is going to make much difference.

To elaborate: That advice isn’t as objective as you think.

What one developer calls clean the other calls messy.

My advice is to use it, then document the issues when it gets messy. It takes some time, but no more than recruiting, training, paying another engineer.