Billy the graphic designer that never coded “makes” an app using Claude, he is vibe coding

See, I don’t know Billy, and I don’t know what his app looks like. If Billy is a logically thinking, good graphic designer who communicates well with his clients, understands what they want, and can express all that in logically coherent statements, Billy’s first app using LLMs might be great. Probably not, but it stands a chance. Everybody starts somewhere.

If Billy just says "hey, like, I want an app that runs on Android and iPhone and desktops too, and I want it to do this list of random stuff, some of which is internally conflicting, and while I’m at it I’m going to spec that I want it in Scala, because reptiles are cool (like cold blooded, get it?) Yeah, Billy’s first app is only likely to be awesome for Billy.

Now, when I fire up Claude Fable and ask it to make me a webserver in Python, how does Codeberg determine if my app is “Vibe coded” or not?

As someone who can code, has coded for 40 years for a living, I’ll say: LLMs can be heavily abused to write a lot of garbage. I’ll also say: give a human enough time, and they can write almost as much garbage but they usually get discouraged by all the errors and crashes and have the good sense to give up - but these humans armed with LLMs can at least make stuff that runs.

I’ll also say: LLMs can be used as very effective tools, if you exercise the kind of care and planning that has always been required to write “good” (whatever your definition of “good” may be) software. They do speed up development - some development ends up in a good place, some… not so much. It was always like this even long before LLMs, but LLMs help get to those endpoints much faster.

And: false positives? How much fun is it to go to clone your repo and find it locked because something (probably an AI algorithm) decided your project was “vibe coded”?

Does anybody still subscribe to HBO? Back in the 1980s we had HBO and I had an afternoon-evening shift at a store nearby. HBO would start a movie in the early afternoon, I’d get to watch half of it before I had to leave for my shift. Luckily, they’d also usually show the exact same movie later that night - timed such that when I got home from work I could sit down and see the end of it starting from about 5 minutes before I had to leave.

The 1990 Berlin Concert video is also worth a watch…

There was a thing called the AcousticBrainz project that enables smart playlists like that which also keep “similar sounding” songs together. You can have a folder with Metallica and Enya, and if you pick Enya mood tracks, the algorithm can pick and choose through the Metallica catalog to play for you only those tracks that are most “Enya-like” - unfortunately, the program was shutdown a couple of years ago - seems like interest / funding was lacking for an open project that does Spotify / Pandora like music classification without also pushing promoted tracks at the same time.

Speaking of low effort releases, a lot of “Deluxe Editions” have come out lately which have “rare recordings” of the same tracks at different live performances. As “unlistenable” goes, hearing Saturday Night’s Alright for Fighting for the third time in 20 minutes gets to be challenging.

The whole album? Was it a double?

Genesis’ ABACAB seemingly put “Whodunnit?” on there just to make listening to the whole album… challenging.

Thick as a Brick is in my random playlist, it comes up about once every 6 weeks…

Most, yes. Then you get to producers like Alan Parsons (Abbey Road, Dark Side of the Moon, all of his own stuff…) He’s rare in the industry, but many have followed his style of album arrangement since then.

Absolutely this.

Now, when I was in High School, I realized that I had owned “The Wall” for 3 months and still never had 90 minutes of consecutive available listening time to listen to it all the way through… parent enforced bedtime was a big part of that, but still… life can be too hectic sometimes.

The problem with carbon based fuels is that we’re unburying them and releasing carbon into the atmosphere which was sequestered under the ground for millions of years, a LOT of it.

If he’s taking solar power + CO2 from the air to make his fuel, then when he burns it it’s just a closed cycle system, at least no new harm done, just returning the carbon previously captured from the air in the process.

It’s actually quite a lot more than a bit more secure. Think of it as the difference between traversing no-mans land on a bicycle (current systems) vs in an armored personnel carrier with armor thick enough to stop EVERYTHING that the other side can throw at it. Sure, you could just open the door of the APC and take a hit, but if you don’t do that, you’re pretty safe.

I do not understand why these two things make their users so enthusiastic

Are you trying to think logically about that question? Because that would be a huge mistake.

flatpak, which is something which would really get to my nerves.

Yeah, not my favorite either. A BIG part of why I’m not loving the majority of the immutable systems I have investigated is because they all seem to heavily lean on tech like flatpak, snaps, etc. and there are valid logical reasons for that, but I’d really rather not go there…

Everything is possible. The point of immutability is the ability to restore to “factory fresh” state with a power cycle.

In theory, the data section is treated as data only, not executable. Software (games) can, and will, improperly store and execute code there, but at least they can be identified when they do and disabled/removed without breaking the underlying system.

easily solved by not giving them root access.

Root vs non-root is, in a nutshell, a tangled mess with millions of opportunities for “oops, didn’t think of that” situations: https://www.cve.org/downloads

Immutable keeps the legacy system confituration basically unchanged, but also restores it “from ROM” every time you power on. (not real ROM, but effectively.) In an immutable system, the attack surface is dramatically reduced, and much more diverse among systems than with a mutable OS.

Immutable means: every time you power it on, it’s the same.

So, if you get infected by a virus, power cycle and it’s like it never happened.

That, like everything you read on the internet, is a gross oversimplification, caveats apply, etc. etc. but for the most part, that’s what immutable means: the running system has no ability to persist changes (except in very specific, controlled, secure, easier to protect circumstances…)

It’s the kind of thing they should have developed to release-ready state 20 years ago - when hard drives were already absurdly large vs needs of the OS and data.

I believe it’s plug and play.

I forget what the latest I ran the numbers on was, but $100K up front and $20K per year running costs seemed like it had a decent chance of being useful to our department of 10 software engineers, which isn’t bad, but it’s an LLM on par with 6 months ago’s frontier models.

If I could get those prices for a local instance of Fable 5, I’d be pushing the paperwork to make it happen.