acedTrex

Im not TYPING a lot of code by hand anymore (still some, inference is slower than typing in a few cases) but im still in the shell zipping around doing other stuff like i always have, the LLM is helpful in a lot of ways but it in no way shape or form is the ideal way to interact with a computer.

So i still get daily use out of these tricks.

Are there people that are literally ONLY interacting with a computer via an LLM? thats crazy if its true

I dont think an article title "dropping ebpf cpu cost with memoization" really needs to be accessible to a broad audience.

multiple of them in this very thread lol, what a disaster for all of us.

[flagged]

Thx claude

Mise is really sloppily vibe coded these days

Not even a little bit to be frank. The joy of things came from their implementation to me. I will write something and then peruse its code on github for hours afterwards just looking, like one would at an art gallery.

If I did not toil on it I wont use it most likely. There's a very very small amount of software I ACTUALLY desperately need in a way that I would not care how it came to exist.

Do not get me wrong, those things exist, i have a plethora of dog shit vibe code websites, clis and tuis and other random stuff on a self hosted forgejo. They did their job now they die. But it brought me no joy, in fact it was rather unpleasant the entire time doing it.

That would fall under "careful engineering"

Fully agree with this, careful work is foundationally engineering. Slopping and not reviewing work is not.

Use and learn the tools, even if it sucks and is painful. It does not take long to feel how they work at all.

Once you have that you can pick and choose when to engage this new tool at will to "not fall behind."

It doesn't have to be all or nothing.

ya i find all LLM output to be incredibly boring and unskillful, I can ship vibe bugs fast with the best of them but it brings me no joy.

I'll never let myself be left behind but the joy professionally of writing quality software is 100% gone.

In no way shape or form is the distinction between LLMs and Humans arbitrary in any sense.

They are two different things, LLMs are not humans.

No, its a very easy line to draw. Rallying and bringing together humans is COMPLETELY different than having an LLM do something. They are not comparable.

This is BY FAR the worst part of LLMs to me. The idea guys were always incredibly annoying but very ignorable. Now they are constantly in your face but providing the exact same 0 value as always.

> And why can't that apply to people who use generative AI?

Because they did not do anything? Theres nothing to celebrate, no skill to honor, no sweat and tears to salute. It just exists

> I remain convinced that handcrafted will always beat AI generated crafts. The IKEA vs the carpenter analogy fails because a carpenter has to create each piece of furniture from scratch

I appreciate this statement, it really hammers home some of the differences ive been feeling from the analogy. You put it in words better.

This resonated with me incredibly heavily. I will say one thing, i've adopted LLM tools fairly heavily for various things. But im doing so on my terms and strictly using them in a way that to me enhances my rigorous understanding of a given system.

Its not QUITE the same thing but its a close enough approximation that i can enjoy the fruits of the output as if it were my own. Just my own 2cents on my personal struggle

yep, this is how it goes, you just ignore the llm brained people.

Nip it in the bud quickly

or, even better, block the model from writing comments entirely

This shit is just vibe coder astrology lol

For full self attention yes

Maybe all these vital infrastructure companies should not have spent the past decades in a race to the bottom of cybersecurity. There is going to be a reckoning.

This is exactly what i do, i have a pi extension that blocks all comments.

I was investigating an ansible playbook yesterday that had a 45 line comment to explain a single apt install command, completely and utterly useless. I am updating my neovim to just collapse all comments, the noise is unbearable.

All of the internet has become basically unusable its very sad, what used to be my place to relax has become a source of stress.

Nothing is forever i suppose, doesn't make it hurt any less though.

It feels inevitable that many systems will have to go to a login/trusted ip source type system. Its just not feasible to continue to operate with 99% of your traffic being fake.

Because the crawlers dont care, they are the internets parasites. Their creators care nothing for people or systems downstream of their greed.

I have it set up to pop up an approval dialogue that shows me the comments its trying to write and if i reject it the model is told essentially "no comments allowed, retry the patch without them."

It usually only takes one of those in the context for the model to reorient its behavior for future edits.

Its a personal extension i wrote myself, maybe I should put it up somewhere.. Its so simple though i dont know if its worth it vs just "go build it yourself"