If 1) you're smart or practised enough to be able to generate what you're asking the AI to do for yourself, 2) you're able to take what the AI generates and debug, check and correct it using non-AI tools like your own brain, 3) you're sure this whole AI-inclusive process will save time and money, and 4) you're sure using AI as a crutch won't cause you brain-rot in the long term, go nuts.

Caveat: Those last two are tricky traps. You can be sure and wrong.

Otherwise, grab the documentation or a bunch of examples and start hacking and crafting. Leave the AI alone. Maybe ask it a question about something that isn't clear, but on no account trust it. It might have developed the same confusion that you have for precisely the same reasons.

So anyway, Linus clearly fits 1 and 2, and believes 3 and 4 or else he wouldn't be using an AI. Let's just hope he hasn't fallen into the traps.

[–] luciferofastora@feddit.org 3 points 14 hours ago* (last edited 14 hours ago)

As I understand it, he doesn't actually know how to do it himself in python. It also seems like a little side project he's bullshitting together anyways, so I guess it's a nice testing ground for trying what it can do. I don't really see Linus investing a lot of time into learning python.

He's also made it very clear that he doesn't want AI slop in the Linux kernel, which is what I'd be more concerned about.

Edit: The project is an attempt to learn about digital audio processing. The visualiser part, not the actual logic, was hacked together from the outset, probably because he's more interested in the actual processing.

These are -- like the analog circuits that started my journey -- toy effects that you shouldn't take seriously. The main design goal has been to learn about digital audio processing basics. Exactly like the guitar pedal was about learning about the hardware side.

From the README of his project, emphasis mine.