I gave it a quick try (Fedora 44/Python/pyenv) with some Tkinter code which is supposed to just work... It doesn't.

After further exploration, it does work, but not without fiddling around with the tkinter code that exists. Not bad results; better than the original Tkinter rendering, anyway, unless you like that retro look.

Can you please tell me exactly what happened, so I could fix it? Thank you!

Vibe coded slop does not actually work, what a surprise

Connect any TV to a laptop/desktop computer... running Linux, of course.

How about a light themed version for those of us with vision problems?

Sometimes, I skim the generated text. I mean, most of it is supposition and filler, right? The rest of the time, I cut to the chase: does the code work? If not, I ignore all the generated text, pass along the errors/warnings, and go from there. What I like best about working with AI is that I feel like a leader developer again (I've been retired from programming for almost 30 years.) It's pleasant and I don't need to worry about how snarky I get when going over bad code.

> It's pleasant and I don't need to worry about how snarky I get when going over bad code.

Yes, reviewing an LLM code is at times infuriating, but at least I can be brief and direct, rather than spend 2x the effort trying to make sure it won't be interpreted as harsh.

You took the words right out of my mouth. LOL

Have people been finding bugs? Having trouble with it? It does work, right? Surely, this is just bureaucratic nonsense.

The same thing happened in Canada in the 1930's, but the force behind it was neither artificial nor intelligent, just greedy.

I love how the shortcomings of the extremely wealthy are considered the failings of all humans.

This just confirms what I've suspected all my life... I should have been a plumber.

Why don't these hackers do something useful... like redistribute the contents of all the billionaires' bank accounts.