What's really ugly is it makes really good code with fucking terrible bugs. My last job for all of six weeks was trying to fix and integrations wrapper of an integrations wrapper on a 3rd party library of integrations.

It looked like really good code, but the architecture was fucked beyond repair. I was supposed to support it for a fortune 50. I quit before they could put me in the on call rotation.

Using an LLM to code is like using a block of wood as a hammer. It's fast, and it'll do a very specific thing quickly, but eventually it'll splinter to the point of uselessness.

I can't wait until all the copy/code is created by LLMs, and they run out of things to train the LLMs on that won't result in immediate hallucinations.

Maybe they'll start working on a real AI to replace the LLMs, instead of just marketing LLMs as AI.

(probably not)

I recently removed in editor AI cause I noticed I was acquiring muscle memory for my brain, not thinking through the rest past the start of a snippet that would get an LLM to auto complete. I'm still using LLMs, particularly for languages and libraries I'm not familiar with, but using the artifacts editors in ChatGPT and Claude.

Preface: If all you want is to get a simple script/program going that will more or less work for your purposes, then I understand using AI to make it. But doing much more than this with it will not help you.

If you want to actually learn to code, then using AI to write code for you is a crutch. It's like trying to learn how to write an essay by having ChatGPT write the essays for you. If you want to use an API in your code, then you're setting yourself up for greater failure the more you depend on AI.

Case in point: if you want to make a module or script for Foundry VTT, then they explicitly tell you not to use AI, partly because the models available online have outdated information. In fact, training AI on their documentation is explicitly against the terms of service.

Even if you do this and avoid losing your license, you run a significant risk of getting unusable code because the AI hallucinated a function or method that doesn't actually exist. You will likely wind up spending more time scouting the documents for what you actually want to do than if you'd just done it yourself to begin with.

And if the code works perfectly now, there's no guarantee that it will work forever, or even in the medium term. The software and API receive updates regularly. If you don't know how to read the docs and write the code you need, you're screwed when something inevitably gets deprecated and removed. The more you depend on AI to write it for you, the less capable you'll be of debugging it down the line.

This begs the question: why would you do any of this if you wanted to make something using an API?

AI and the discussion around it doesn't live in a vacuum.

Occasionally you'll get shit opinions like this. Easy slutty greek frat bro strawmen that'll sleep with anything that moves and then dodge child support payments.

We all have to remember the true Chad argument against AI is that it's built on degenerate theft and corporate soulless shills. AI is the Shikrelli of creativity.

I'd rather be a bad programmer that gets stuff done than a good programmer who's just jerking off about proper design

t. good programmer

The same logic can explain why Teslas crash so often. You turn on all the assists, and eventually forget how to change gears.