Not just enterprise, any human organisation.

Also sunk costs “should in theory” never be considered but I’ve only ever seen sunk costs considered.

I’ve made some gnarly custom forms over the years but never quite run into the problem you’re describing.

These days if starting a greenfield web app, each page has its own style/css sent in the head tag.

Because it’s usually just base layout + page specific styles/overrides then it barely adds any overhead in the scheme of things(couple of extra KB).

Maybe the base layout could be moved into a static file to be cached but whatever, it’s already ridiculously quick to render plain html/css.

If you lack a solid component system, you likely do not require complex tools to manage CSS.

CEO’s are a weird breed, pretty sure this dudes never met a real one.

A surprising number of CEOs are borderline illiterate.

Amen.

My thoughts exactly.

Dialog is easy to use with just plain JavaScript.

It's just plain easy. It boggles my mind that nobody uses it.

But then again it boggles my mind that you can pass WCAG with those "is this a motorcycle?" things or that stupid anime girl you see on Linux pages or a GDPR popup and you can. People will say "what if you have to support WCAG and GDPR?" and I say "sometimes you have to make a choice", I mean a11y work is damned if you damned and damned if you don't, just damned all the time and personally the EU screws up my life a lot more than Iran ever did.

>But what makes a human mind more "understanding"? Who says we're not simulating? Who says our mind even exists, in this space?

The people running the experiment.

And yes is the answer to what should be a rhetorical question.

They’re in a better mood though.

Just before becoming suicidal some hours later.

Refactoring already exists.

If it’s a compiled language, just change the definition and try to compile.

Indeed! You would think it would have some kind of sense that a commit that obviously won't compile is bad!

You would think.

It would be one thing if it was like, ok, we'll temporarily commit the signature change, do some related thing, then come back and fix all the call sites, and squash before merging. But that is not the proposal. The plan it proposes is literally to make what it has identified as the minimal change, which obviously breaks the build, and call it a day, presuming that either I or a future session will do the obvious next step it is trying to beg off.

Pretty sure it’s a harness or system prompt issue.

I have never seen those “minimal change” issues when using zed, but have seen them in claude code and aider. Been using sonnet/opus high thinking with the api in all the agents I have tested/used.

On my compiled language projects I have a stop hook that compiles after every iteration. The agent literally cannot stop working until compilation succeeds.

In the case I described no code changes have been made yet. It's still just planning what to do.

It's true that I could accept the plan and hope that it will realize that it can't commit a change that doesn't compile on its own, later. I might even have some reason to think that's true, such as your stop hook, or a "memory" it wrote down before after I told it to never ever commit a change that doesn't compile, in all caps. But that doesn't change the badness of the plan.

Which is especially notable because I already told it the correct plan! It just tried to change the plan out of "laziness", I guess? Or maybe if you're enough of an LLM booster you can just say I didn't use exactly the right natural language specification of my original plan.

I think your expectations are too high. Just understand the limitations and go with the flow.