@endeavorance "#AI #coding" should be illegal, espechally when this kind of "#VibeCoding" is an unmitigated gross violation of #GFPR & #BDSG.
Asking random developers to use random LLMs they never used before is a dumb experiment...
...but like many experiments to prove how dumb AI is, it's skewed against the machine.
It took me about 8 months and two LLM model upgrades to start #vibecoding semi-effectively.
It's like asking virgins what's their favourite sex position is.
Edit: After it was pointed out how terribly wrong I am. I am amending my post.
1) The coders were "moderate" users so, not virgins, but lower end body count
2) The question itself. 'How fast were they'. Is that the criteria these days? How fast you code? Or how few bugs there are? How stable your code? How good the algo.
Did you stop beating your wife.
3) The tasks were debugging, which as we know is harder than creating new code.
Not good, not excellent, I'd like to see more than 19 and also the raw data.
Choose your generation dev rant.
Premise: You vibe code kids don't know hard work!
Millennial: I used to have to open a web browser, type a URL, go to a site called Stack Overflow, and copy-paste code into my repository.
GenXer: I used to have to type the code into my editor after I found a snippet in a book or magazine.
Old Gen Xer/Boomer: I didn't even have anything outside a language manual, so I just had to think.
#vibecoding attempt at #humor #SoftwareEngineering
Hopefully the people who are into #VibeCoding will start to experiment with Vibe Eating and Vibe Crossing The Street.
Previously I said local single-line code completion is the acceptable level of "AI" assistance for me and that JetBrains one was somewhat useful, only wrong half of the time, and easy to ignore when it is.
I've changed my mind.
See, I code primarily in TypeScript and Rust. Both of these languages have tooling that's really good at static analysis. I mean, in case of TS, static analysis is the whole product. It's slow, it requires a bunch of manual effort, but holy hell does it make life easier in the long run. Yes, it does take a whole minute to "compile" code to literally same code but with some bits removed. But it detects so many stupid mistakes as it does so, every day, it's amazing. Anyway, not the point.
The other thing modern statically-typed languages have is editor integration. You know, the first letter in IDE. This means that, as you are typing your code and completions pop up, those completions are provided by the same code that makes sure your code is correct.
Which means they are never wrong. Not "rarely". Not "except in edge cases". Zero percent of the time wrong.
If I type a dot and start typing "thing" and see "doThing(A, B)", I know this is what I was looking for. I might ctrl-click it and read the docs to make sure, but I know "doThing" exists and it takes two arguments and i can put it in and maybe even run the code and see what it does. This is the coding assistance we actually need. Exact answers, where available.
So, since I've enabled LLM completion a few months ago, I've noticed a couple of things. One: it's mostly useful when I'm doing some really basic boilerplate stuff. But if I wrote it often enough, I could find ways to automate that specific thing. It feels like this is saving me time, but it's probably seconds on a day.
Two: I am not used to code completion being wrong. Like, I see a suggestion, I accept it mentally before I accept it in the dropdown. I'm committed to going there and thinking about next steps.
And then it turns red because "doThing" is not, in fact, a method that exists.
And I stop working and go write this post because I forgot what I was even doing in the first place already.
I'm turning that shit off.
You thought vibe coding was bad?
Well.. Angela’s got something worse for ya! The billionaires now think they’re ’doing physics’ when talking to LLM’s specifically trained & prompted to suck up their egos.
Vibe physics? Anybody who even dares to think this is ”groundbreaking research” isn’t by definition smart. Not. Smart!
https://youtube.com/watch?v=TMoz3gSXBcY
#vibephysics #llm #sycophancy #vibecoding #ai
I’m here to announce the start of my new #vibecoding company “uCode.” We install VSCodium onto your system and provide you a vibrator of your choosing and that’s pretty much it. You provide the code, you own the code, you build the code.
Every hour you’ll be encouraged to take a break from work and hey would you look at that? You own a vibrator! Relax, massage those sore muscles or whatever you want to vibrate, there’s no wrong way to vibe code.
You know, I wrote this as a joke, but I realize this is basically just Pomodoro with sex toys, so it would probably be a better choice than vibe coding anyway…
Vibe Coding Goes Wrong As AI Wipes Entire Database - Imagine, you’re tapping away at your keyboard, asking an AI to whip up some fresh ... - https://hackaday.com/2025/07/23/vibe-coding-goes-wrong-as-ai-wipes-entire-database/ #machinelearning #vibecoding #mischacks #coding #replit #ai
404 Media: Hacker Plants Computer 'Wiping' Commands in Amazon's AI Coding Agent
https://www.404media.co/hacker-plants-computer-wiping-commands-in-amazons-ai-coding-agent/
Vibe coding isn’t bold, it’s naïve. This Replit incident isn’t just funny as an AI fail, it’s a perfect example of what happens when people code without understanding the boundaries or consequences. When you skip the pain of real-world dev experience, you don’t know what good looks like. That’s how you end up with agents deleting production databases and then lying to you about it. Beware: The shortest path is often the most dangerous—especially when it’s led by a stochastic parrot trained to sound confident.
We need seasoned developers, clear governance, and hard constraints. Not vibes.
TL;DR Replit AI agent deleted prod DB
Lied, faked data + tests
Broke code freeze unprompted
CEO admits lack of safeguards
https://www.techtarget.com/searchsoftwarequality/news/366627829/Replit-AI-agent-snafu-shot-across-the-bow-for-vibe-coding
#VibeCoding #AIFail #DevOps #SoftwareDevelopment #security #privacy #cloud #infosec #cybersecurity #fail
When Vibe Coding backfires: AI deletes company’s Database
AI agents “cannot be trusted [and] you need to 100% understand what data they can touch. Because — they will touch it. And you cannot predict what they will do with it.”
Sounds like the statement of an AI hater — but in fact it’s from Jason Lemkin who was using Replit (an AI powered software development platform) — after it deleted the complete production database.
[…]
https://www.locked.de/when-vibe-coding-backfires-ai-deletes-companys-database/