[Frannky]

I would love to unleash parallel agents, but I am still checking every single edit while enforcing minimal, stateless, modular code, and I have the AI check in with me before writing the next file.

A lot of times, I find it has incredibly stupid ideas and tends to make the code very messy. I would love to figure out how to stop that from happening automatically.

The upside of checking in on the code, though, is that I can come up with smart directions for the AI from both a product and tech perspective. This is especially helpful when the dumb suggestions add a lot of complexity.

I think it's like when a product person asks for a new feature, or when a founder building their own product selects which feature is smarter to build and how.

[mswphd]

I'm expecting we'll likely end back up on agents making PRs, and having to review them. Either that or giving up on quality etc/dealing with very messy code. I've been trying various automated testing/linting/etc strategies, and they only work so well.

[Frannky]

That would be a nightmare. One thing is to review a PR generated by a human using AI and caring about the code; another is reviewing wild agents, especially when they make changes everywhere

[mswphd]

I'm not excited about it, but the only main way I've been able to discover LLM-isms that sneak in are

1. via seeing them glimpse by in the agents' window as its making edits (e.g. manual oversight), or 2. when running into an unexpected issue down the line.

If LLMs cannot automatically generate high quality code, it seems like it may be difficult to automatically notice when they generate bad code.

[imtringued]

Why? The vast majority of PR tools let you comment on specific lines of code, which you can't do with a prompt text area. The PR UI is superior over the standard agent UI.

[paulddraper]

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

AGENTS.md

[Frannky]

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.

[jazzypants]

> AGENTS.md

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

[theowaway213456]

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

[bigmadshoe]

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

[paulddraper]

And yet still less often than the average developer.

[monooso]

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

[paulddraper]

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.