Hehehe, ok.

Those require lines there, they’re importing code written elsewhere. We call that code a library. Take the first one:

var zero = require("number-zero");

defines a variable called zero, imports a library called number-zero (not a real library btw, just a joke), and assigns its value (assumed to be the constant 0) to the variable. Later in line 19, zero is read.

The joke is that you wouldn’t even write line 2 and use a simple 0 instead of zero in line 19. The code is full of unnecessary imports of basic language components.

Everything is from an imported library

Does using Rust magically make LLM products non-sloppy?

I guess not.

as unknown as any

slop perhaps?

Orange cats cannot overthink anything

only there for you half the time

TS dev here. Yep.

There’s worse, but not by much. Looking at you, PHP

I’m an absolute layperson in chemistry, but I’m reminded of something from Ryan McBeth’s earlier content. It was around the start of the war in Ukraine, and someone had asked him about self-destruct explosives on personnel or personnel carriers. His answer was dismissive on the grounds that manufacturing, handling, and more importantly combat application of explosives always carries a combination of unreliability, both to explode and not to explode. Basically, the failsafes needed to safely and reliably implement self-destruction on a large scale will eventually result in troops getting blown up by their own equipment.

My take from this, is that if you would manufacture degrading mines in huge numbers, the degradation mechanism might very well make some mines a random time bomb, simply because of the inherent properties of explosives. I can’t argue for or against the plausibility of chemically engineering a safe and reliable temporary mine, but I would only take expert opinions into consideration.

The internet has a tendency to enable laypeople to act as if they’re entitled to be given the same consideration as an expert in any given field. This is why I think taking a big step back from this question is the right thing to do for me and for those who I think are no more qualified to make statements on this than I am. But it’s good to be hopeful.

I doubt there’s a safe way to make explosives degrade.

Did you read the article? It’s long, but worth it. It describes analytical problem solving and software development.

Did I miss anything supporting your claim that the article argues about art?

The premise was that this language is significantly different from other languages in terms of being understood and replicated by an LLM.

The result showed that an LLM does exactly as well with it as you would expect.

The Uncle Fucker song from South Park: Bigger, Longer, Uncut prolly

This. I know some people who have switched to vapes and have steadily reduced their nicotine to 0.

Gotcha. Sorry for being snarky.

Blaming sexual violence on porn seems the same kind of cheap virtue-signalling as blaming gun violence on video games.

Being choked feels good. Your partner sometimes asks you to choke them, sometimes in the heat of the action.

The most important thing is that there really is no safe way to do it, and it should be never done. Upvoted your post for visibility. For the sceptics, here is an article (in German) about one medical doctor accidentally killing another during sex.

How the hell is 8GB a small amount for a side utility? Are you using LLMs to count to 50?

I’ve once worked on a project where your commits to your dev branch were supposed to be helpful to colleagues for reviews, but they had to be squashed for the feature branch, with comments adhering to the conventional commit “standard”. On the other side of it, there was a horrible pedant of a middle manager, who was rejecting merges based on (debatable) “misformats”.

This affected billing. They supposedly had some scripts evaluating merge requests, and they’d shrug and say “the script rejected it”. This was before LLMs. Come to think of it, they’re probably replaced by an LLM now, prompted by the customer to “try to defraud and fuck with the workforce on every commit”.

So to sum up, maybe OP’s in some sort of corporate hell, or maybe they want a bit more than going git commit -m every time.

As well-intentioned as this might be, I doubt they understand how trained models work.