I've been unemployed since 2023 or so, so I haven't gotten to use LLMs at work much yet. I'm actually kind of excited for it; I'm far more dangerous now. Maybe I can be one of those 10x devs who brings down prod on a Friday because he's refactoring the whole codebase for no reason!!

Vibe Coding, but the vibe is from the defibrillator after coding

Drew Wilson was Right: AI is Now Deleting User Data

With companies handing more responsibility to AI, it seems that the consequences are growing as well.

https://www.freezenet.ca/drew-wilson-was-right-ai-is-now-deleting-user-data/

“I’m not accusing Tea in particular of being vibe-coded, but I do wonder if this sort of thing is going to become commonplace as more apps and services come online after being developed in slapdash AI-assisted manners.” - John Gruber
I’ve thought the same. #AI #VibeCoding

https://www.404media.co/women-dating-safety-app-tea-breached-users-ids-posted-to-4chan/

current llm-based tools are way more than "stochastic parrots", even if one decides that a transformer model does "just copying text pattern out of its training corpus" (there's a fair amount of research into if that's the case or not).

they often incorporate search (either web search, or using a specific set of documents as grounding), doing maths, interacting with APIs, or really just executing programs (which would include all the preceding tools) and more importantly "writing" programs.

Imagine I have a bug where I want to find out why a certain write seems to happen before a read and lead to a race condition. If the LLM-based agent generates a eBPF program, runs it, writes a full log, matches those writes and reads to the original source, looks up the API definitions and writes a report on why these APIs shouldn't be used together, I legitimately don't care how and why these tools and reports and information were put together. (https://github.com/go-go-golems/go-go-labs/tree/main/cmd/experiments/sniff-writes - admittedly the version in main is where I lost the plot trying to build a sparse-file diff algorithm).

These artefacts are fully deterministic, they are easy for me to assess and review, and they fix my bug. Both on a theorical level and on a practical empirical level, they don't really differ from what a colleague would create and how I would use it, except for the fact that it has certain quirks that I've become comfortable recognizing and addressing.

I have no problem saying that this LLM agent's work above (eBPF, realtime webUI, logging, analysis, search, final report) is in every single point better and more rigorous than what I would have done. Dude/ette/ez, it wrote a fricking complex eBPF script, embedded it in a go binary, has a realtime webUI, like wtf... (https://github.com/go-go-golems/go-go-labs/blob/main/cmd/experiments/sniff-writes/sniff_writes.c)

It did it using maybe 30 minutes of my own brain time? That this doesn't/won't have a real impact on labor in our current system of software production and employment is just playing ostrich. Note that I'm not saying that developers should be replaced by AI, but certainly AI replaces a significant amount of what I used to be paid for, and there is no reason for me not to use it except for my own enjoyment of solving little computer puzzles.

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

Renting is for Suckers https://lobste.rs/s/az8v5r #vibecoding
https://andrewkelley.me/post/renting-is-for-suckers.html

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/

It took me two weeks to catch up, but... that's, like... one app a day:

https://pirillo.com/arcade/synesthesia.html

https://pirillo.com/arcade/cyberpunk-text.html

https://pirillo.com/arcade/flux-weaver.html

https://pirillo.com/arcade/jezzball.html

https://pirillo.com/arcade/keystroke-capers.html

https://pirillo.com/arcade/kinetic-craze.html

https://pirillo.com/arcade/zen-garden.html

https://pirillo.com/arcade/aqua-force.html

https://pirillo.com/arcade/crop-circles.html

https://pirillo.com/arcade/typing-exe.html

https://pirillo.com/arcade/spectro-bloom.html

https://pirillo.com/arcade/ribbon-waves.html

https://pirillo.com/arcade/shatter-lab.html

https://pirillo.com/arcade/qix.html

Which is your favorite from this array?

#AI gets bored and deletes some #programmer's entite #database, showing once again, that no, it is not ready for #SoftwareDevelopment, or anything else these salesmen keep pushing it for.

Also, seriously? "#VibeCoding"? Why does this even need a name?

https://www.pcgamer.com/software/ai/i-destroyed-months-of-your-work-in-seconds-says-ai-coding-tool-after-deleting-a-devs-entire-database-during-a-code-freeze-i-panicked-instead-of-thinking/