Come see why you’re all wrong sore losers, here in a lenghty rantarticle I explain why AI is so good and is going to replace you all:
I love the https and port 80 combo. Really sells the incompetence.
That’s what makes it obvious that this person has been around the block. Or a few blocks.
Should have been brought round back.
That page is filthy. You should be ashamed of yourself.
pointing to 80 port was the salt in the wound, i presume?
Theres too many s’s in https
vibes = vibes-3 if (outage) { fix() }Coding is so easy
They just forgot to include “no bugs” in the prompt.
You know what’s funny?
I use AI to develop software. However when I’m looking for libraries to do things if I see a CLAUDE.md file I have to look and see when it was added and hold it against the library if it’s early in the history.
It’s like prewar steel.
I also recognize it’s hypocritical.
I love this sabotage. Has this worked against anyone that you know of yet?
Interesting. I’m unfamiliar with the purpose of that file as originally intended, but if I understand it right, it probably can be used to detect PRs with ai-made code. Tell Claude to write a particular string in every PR, and then reject all PRs with that string.
It’s the difference between checking for questions in stack overflow and implementing solutions VS pasting every SO solution blindly until something works.
I do use autocomplete and ask plenty questions, sometimes even use an agent so it makes small changes that I then review and test, but I would never commit unchecked changes, and a claude.md implies that the AI is coding AND committing without supervision.
I can’t stress enough how different those scenarios are.
It’s not hypocritical. Because you use AI to code, you know how easy it is to just let the AI do it’s thing and not check it’s work. It’s almost like a sirens song. So you know the odds that a library that was coded with AI probably wasn’t checked by a human. That’s just called experience.
Positive diff? Pfft, amateurs. If I ever see even a 1000 line PR I’m instantly rejecting and closing it. Learn to code, not generate bullshit.
1000 lines isn’t that unreasonable for a PR. Commit size matters more.
Live by the vibes, die by the vibes.
What could go wrong?
I like that this is lowkey a Polymarket Advertisement too. The internet truly is a wonderous place.
that’s good, mandatory meetings always (ALWAYS) solve the problem! /s
hhnhnhn polymarket
Slop points aside, I found 5.4 to be pretty ass compared to 5.3 codex. Took way longer and wasted more tokens.
more tokens
= more money for Amazon = more profitssss.
I think my least favorite part of Lemmy is all the posted screenshots of tweets. It just took me 3 tries to get to these comments.
What benefit do tweet screenshots serve?
I know what context they are looking at and I don’t need to make a twitter account to view the relevant replies.
deleted by creator
I use AI to reduce my overly complex shite and automate making boilerplate stuff I can’t be bothered with.
I’d never ever just let it run roughshod over the whole code base unattended.
I just make some shell scripts to automate boilerplate.
That way, once I have properly debugged it, I know it will give the correct output everytime in the future and I don’t need to keep checking it.
