Hacker Newsnew | past | comments | ask | show | jobs | submit | submain's commentslogin

I have been doing this and the results have been fairly good.

I use claude to build requirements.md -> implementation.md -> todo.md. Then I tell opencode + openrouter to read those files and follow the todo using a cheap (many times free) model.

It works 90% of the time. The other 10% it will get stuck, in which case I revert to claude.

That has allowed me to stay on the $20/month claude subscription as opposed to the $100.


Great work :). Go doesn't have TCO. That means functional languages (no for loops) could blow up the stack. How did you solve that?

You can just compile any tail recursive function to a function with a loop and no recursion.

This is in fact how Elm does it! Tail call recursion compiles to a while loop.

That does not address the use case where I find tail recursion most tempting. That would be mutually recursive functions.

If the function can be written as an idiomatic loop I probably would do so in the first place.


You _can_ do trampolines, but that is kind of infectious, or needs to be very explicit with extra code, etc.

Indeed. It's not very efficient though. If I remember correctly Scala does this.

Right but recursion is only a smaller part of why the optimization is important. It means tail-called functions still build on the stack and long function chains—as is common with fp—can overflow

> And don't even let me get started on how bad Claude client has become

The latest versions of claude code have been freezing and then crashing while waiting on long running commands. It's pretty frustrating.


bots perhaps? Anyways, mods should remove this post.


> If you search for problems on linux, you will get much higher quality answers.

Not only that, but in the past I've cooked hacky bash scripts to work around issues while waiting for upstream fixes. I'd imagine that'd be harder with other OSs.


I usually define functional programming as "how far away a language is from untyped lambda calculus". By that definition, different languages would fall in different parts of that spectrum.


> The real secret to agent productivity is letting go of your understanding of the code and trusting the AI to generate the proper thing

The few times I've done that, the agent eventually faced a problem/bug it couldn't solve and I had to go and read the entire codebase myself.

Then, found several subtle bugs (like writing private keys to disk even when that was an explicit instruction not to). Eventually ended up refactoring most of it.

It does have value on coming up with boilerplate code that I then tweak.


You made the mistake of looking at the code, though. If you didn't look at the code, you wouldn't have known those bugs existed.


fixing code now is orders of magnitude cheaper than fixing it in month or two when it hits production.

which might be fine if you're doing proof of concept or low risk code, but it can also bite you hard when there is a bug actively bleeding money and not a single person or AI agent in the house that knows how anything work


"Magic Leap raises $827M in Series C". Aged like wine.


They're still doing well today, right? IIRC they provide the lenses for Metas in-development AR glasses


This is great! Coincidentally, I just started replacing my collection of bespoke security bash scripts with an app like yours. WIP here: https://github.com/leolimasa/age-vault

We all keep reinventing the same thing :)


Yeah, I run macos for the same reason.

However, I went back to linux on my personal laptop (nixos on my case) and I am pleasantly surprised how many things now just work.

The only thing that still annoys me is the laptop not sleeping properly and therefore using too much battery power when idle.

It has made great strides on the last two or so years.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: