Vibe coders not understanding their code because they didn't write it.
Me not understanding my code because I wrote it a month ago.
Vibe coders not understanding their code because they didn't write it.
Me not understanding my code because I wrote it a month ago.
I'm going to lose my mind if I get any more support tickets where someone has cut and pasted the output from Claude instead of telling me what the problem actually was.
My job has basically turned into guessing what bad info Claude has given
My god, had someone send in a merge request with utter garbage, with Claude describing some nonsensical "root cause" as to why a function didn't work. Claude made two changes:
So I needed to know the debug data for what really went wrong, but the submitter got all pissy and said Claude already sorted it out and why can't I just accept their slop merge request as-is, refusing to believe that all it did was catch and silently drop any and all errors associated with the code instead of fixing it. Wouldn't run the procedure I stated would show them they had messed up data as a result of their 'fix'.
Looks like there is an angry cryptobro downvoting responses who dare talk shit about claude in this thread lol
I like to tell them, “well my Claude said this.”
You can just point out the issues to Claude and get it to spew out AI slop on how those issues are the worst thing in the world, horrible bad bugs.
Fighting fire with fire. Except you’re actually trying, which means you can’t really loose.
In their defence, the one thing AI does do well is Code review. But, it makes too many absolutely sh** assumptions when helping customers troubleshooting.
I feel the problem is that because its a paid tool, it's not a good look if they simply acknowledge "we're guessing, and its a crap guess"
We had a customer demand support for a competitors product, because Google AI told them that we owned that company.
Just complete the AI slop trough and copy and paste the ticket back into Claude to fix and open an MR and then have Claude review it and merge and then when there is a bug repeat the process.
I honestly don't know what people are thinking, both employees and employers when people start copy pasting LLM shit. Why do I need you if all you are is a glorified macro? I strongly suspect the human is there to be the fall guy when the LLM invariably does something really stupid.
Imagine all the recursive meat proxies we have in the industry right now, like an infinite redirect loop with MITM to do the networking.
Work slop! Just love people using LLMs to hand the heavy lifting over to me.
The fabled meat proxies.
Honestly, this isn't even an AI issue, people have been doing that long before AI became a thing
Getting a ticket "I need you to change blah" and the request is either nonsense or "fixes" something unrelated to what the user is actually experiencing, but they're so sure they know
This weirdly is way worse when you support technical teams, it makes it pretty clear how much Dunning Kruger is going around in IT... But yeah, AI is making it so much worse
I used to write a ton of code while caffeinated.
Now I write less, better code since quitting caffeine.
There was a brief period where I was incapable of doing anything at all between the state of high caffeination and no caffeination.
since quitting caffeine
Sorry, can you explain this part?
I don't understand how you can quit breathing caffeine
I moved to half caff for a few weeks, then to decaf. I still have a cup of coffee every morning as part of my routine. The headaches were brutal on both changes, and I regret not taking longer to do so.
It began when I noticed caffeine pouches being sold at a gas station. Not pills, which feel like a drug, pouches, just like the Zyn pouches. The difference is caffeine can be sold to minors. I realized when I saw them that caffeine is simply another insidious drug being peddled to the masses to keep us locked in addictions, feeding the machine with our hard earned money.
You do not need the stimulant. You do not need the pacifier. You will not enjoy going without, until you learn how much better you feel without.
What about us caffeinated autistic vibe coders? Slop production through the roof bb!
I put together a new modpack for minecraft this year and from that i can verify that this comment definitely checks out.
Be me AudADHD locking the fuck in doing 10 hours of work in 2 hours when the legal meth kicks in. But it's at 11:37pm and sometimes it's wikiholes on GBU stabilizer fin evolutions instead of work.
And then I waste the rest of the next 2 days.
Ah, actually, caffeine can be really contra-productive for autistic people.
I was only ever observed to have autism, but I highly suspect that I'm audhd. What kind of hell is this where caffeine can help my ADHD focus but harms my autistic focus
Caffeine be like:

If it's any consolation, I'm AuDHD myself (ADHD diagnosed first) and I would have never made it this far without copius amounts of caffeine.
Edit: To expand on this, my autistic tastebuds have rejected the taste of coffee until I was like 21. Imagine the astonishment following my first cup when I was bustling around actually getting things done for once.
I dont know how you can code while caffeinated I need to drink to write code
Back when I was studying, I had a final exam on my last year (so basically one of the most important exams in my career) that was about PHP. It was 3h, and we had to complete a theory part and then code a bunch of stuff.
I attended that exam while completely drunk. So much so that I don't remember anything about it. Somehow I didn't get kicked out.
I genuinely expected to fail it, and instead I got my best grade up to that point, an 8/10.
Just caffeine? I thought a sizeable portion of yinz are on adderrrall.
ADHD is wildly common in the field. Everyone in my infosec department has it, which is amazing because we all get the struggle.
top 50 comments