It does curb demand.

> if the only penalty the company/agency gets

What is the penalty for the government?

Elon Musk

> I would love to figure out how to stop that from happening automatically.

AGENTS.md

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.

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

And yet still less often than the average developer.

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.

> Sometimes HN drives me crazy.

You can tell the difference between those who build businesses and those who simply use them.

I was gonna say it's a difference between producing something to make money, and producing something meant for people to like and perhaps love, but same thing :)

To state the obvious, "good engineering/design practices" will not tell you what features are used or not.

> Git has served us well for 20+ years

Funny. I think that, but the usual HN narrative is that Git is UX hostile.

> This was bad enough that Node.js eventually changed unhandled rejections from a warning to a process crash, and browsers added unhandledrejection events. A feature designed to improve error handling managed to create an entirely new class of silent failures that didn’t exist with callbacks.

Java has this too.

You can choose for attackers not to use AI?

"Artisanal art" as it were.

You are in violent agreement.

> inference is indeed profitable

> So you're asking for some type of equity that's private?

To read more: https://en.wikipedia.org/wiki/Private_equity