submain

> because you could build your own and maintain it

One would argue that the effort to build and maintain it is why we have cookie cutter software, agentic built or not.

Aren't servers depreciating assets owned by the company and tracked on the balance sheet?

If so, on a liquidation event, I'd imagine they'd have to be sold to compensate the shareholders.

In my country of origin (not US) that's how it worked starting in high school. Homework was called "suggested problems". The teacher reviewed them in class. No grading. We ended up doing it because that was almost the only way to pass the exams (which, btw, could be up to 50 questions long...)

I stopped reading three sentences in when I realized it was getting hard to follow. AI explains it.

Do you need to keep taking Dramamine, or do you adapt to it eventually?

I literally created a /plain-language skill.

The documentation is really hard to read. It's full of claudisms and verbosity. I highly recommend you to do a human review on the whole thing.

Which is why we need competition. Which is almost non-existent in US healthcare as comparing prices is near impossible.

Unproven, but it could very well be some problems require consciousness to be solved.

It's amazing how exhausting AI text is to read.

Likewise. I signed up for woodworking classes. I think I'm in for a rude awakening.

NVidia seems to want them. They have a lot of lobbying power.

Not op, but I use it for seeing the joystick + throttle and the "real" instruments in flight simulator.

The investors will get their money back on the IPO. They'll dump all their stocks in the market and run away, leaving retail with the bill.

I think that's a fair take. We could also frame it as society in the past has carried a lot of the burden of raising kids.

Tribes and communities helped raise kids. That's no longer true in an individualistic and institutionalized society.

Is that enough though? Women change their entire bodies, sacrifice years of their lives, and go through considerable stress to have a baby. And at the end, the benefits of that ordeal are not clear.

Society would need to offer something to offset all those costs.

I agree. It comes down to the opportunity cost for women to have babies.

On pre-industrialized societies, women have barely a choice. On industrialized ones they do. And it turns out that, when given the choice, they choose not to have babies.

It seems to me China is chasing widespread adoption, while the US is chasing the AGI dream.

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?

> 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.

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

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.

This echoes my sentiment that LLMs are higher level programming languages. And, as every layer of abstraction, they add assumptions that may or may not fit the use case. The same way we optimize SQL queries by knowing how the database makes a query plan, we need to optimize LLM outputs, specially when the assumptions given are not ideal.

Type checking is indeed an advantage of ORMs. You pay for it with object relational impedance mismatch. That impedance grows as your schema grows.

In my experience, the way to get the best of both worlds is to use a query builder as opposed to a full ORM.