zanderwohl

Thanks for the link. Software is all about managing complexity. I like the point about testing and external reasoning. LLMs can write a lot of tests in short order, many of which don't do much to help the program. It enjoys "pinning" behavior, which is basically just confirming a golden path and doing nothing to actually examine the behavior of a module under various conditions.

I feel I fall into two camps for different projects. I have a hobby project where I'm writing native UI components by hand without AI, and managing memory in an Arena allocator I wrote myself. I also have a hobby project where I honestly don't touch the code, I just think in terms of systems run per frame and the time complexity of different algorithms, making Claude do it. Most personal projects are somewhere in between. I don't think either approach is insane, immoral, or any other hyperbole.

If you're working on a CRUD/web app, absolutely. There's so much data for web apps out there that LLMs now produce better web app code than most of my coworkers from 2022 or so, since it follows consistent style rules. Web app code all looks the same, anyway.

Not through farming a larger area of land, that's for sure. It's been mostly up to improvements in crops, nitrogen fixing, the invention of the reefer car, and other things.

Additionally, I'd like to remind you that we have a lot of wiggle room: if we stop growing alfalfa and stop doing stupid things like biofuel, that will free up an enormous amount of land.

To be fair, overpopulation was never an actual concern. Since the 1800s, food production growth rates have outpaced population growth rates. Underpopulation _is_ a concern when infrastructure and social structures may not be able contract quickly enough to sustain our current quality of life.

I think these are very fun and I would love to see more content you can visit with curl. I'm setting up a home chores + calendar + weather station that runs off my homeserver. I was contemplating making a plaintext version so very stupid devices could still read and display interesting data.

> people overwhelming dislike

Just a little thing. :)

The article talks about this too:

> Can this be gamed? Teaching the AI to write less like stock Claude and stock ChatGPT? Yes, absolutely. And honestly that would be great. Because half of the irritation is that all these AI-written article sound the same!

> They are not eligible for the sparkle icon on the feed page

This is the opposite of how most places use the sparkle icon!

It was relaxing to see some minor typos and stylistic awkwardness in this article, I have to be honest.

Thanks. I would have asked Claude or something but I know so little about this topic that I wouldn't have been skeptical enough of its answer.

This may be a stupid question, but I've always heard to never plug a generator into an outlet - what makes these safe enough that you can?

I read it and I understand it, but the style of the writing is anathema to me.

It essentially lets you define a communication protocol where things have to happen in a certain order. At compile-time, your ordering is checked against certain rules, and certain classes of deadlocks and hangs can be avoided. The order of actions is then enforced at runtime.

I have not understood, and still do not understand, why everyone locks themselves into github's CI/CD pipeline. It's not hard to set up checks that run on a generic docker setup. I have a home server that I use for all my builds and checks, with a github actions config to run manually if I can't VPN into my home network.

Besides being more reliable, it's just faster to run on a machine you control.