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.
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
> 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.
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
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
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.
reply