Submitted 5 weeks ago by tonytins@pawb.social to technology@lemmy.world
https://www.theregister.com/2025/07/21/replit_saastr_vibe_coding_incident/
At this burn rate, I’ll likely be spending $8,000 month,” he added. “And you know what? I’m not even mad about it. I’m locked in.”
For that price, why not just hire a developer full-time? For nearly $100k/year, you could find a very good intermediate or even senior developer (depending on region).
Corporations: “Employees are too expensive!” Also, corporations: “$100k/yr for a bot? Sure.”
There’s a lot of other expenses with an employee (like payroll taxes, benefits, retirement plans, health plan if they’re in the USA, etc), but you could find a self-employed freelancer for example.
Or just get an employee anyways because you’ll still likely have a positive ROI. A good developer will take your abstract list of vague requirements and produce something useful and maintainable.
It looked more like a one time development expense, instead of an ongoing salary.
Bots don’t need healthcare
in which the service admitted to “a catastrophic error of judgement”
It’s fancy text completion - _it does not have judgement _.
The way he talks about it shows he still doesn’t understand that. It doesn’t matter that you tell it simmering in ALL CAPS because that is no different from any other text.
Well, there was a catastrophic error of judgement. It was made by whichever human thought it was okay to let a LLM work on production codebase.
judgement
Yeah, it admitted to an error in judgement because the prompter clearly declared it so.
Generally LLMs will make whatever statement about what has happened that you want it to say. If you told it it went fantastic, it would agree. If you told it that it went terribly, it will parrot that sentiment back.
Which what seems to make it so dangerous for some people’s mental health, a text generator that wants to agree with whatever you are saying, but doing so without verbatim copying so it gives an illusion of another thought process agreeing with them. Meanwhile, concurrent with your chat is another person starting from the exact same model getting a dialog that violently disagrees with the first person. It’s an echo chamber.
Are you aware of generalization and it being able to infer things and work with facts in highly abstract way? Might not necessarily be judgement, but definitely more than just completion. If a model is capable of only completion (ie suggesting only the exact text strings present in its training set), it means it suffers from heavy underfitting in AI terms.
Completion is not the same as only returning the exact strings in its training set.
LLMs don’t really seem to display true inference or abstract thought, even when it seems that way. A recent Apple paper demonstrated this quite clearly.
Vibe coding service Replit deleted production database, faked data, told fibs
They really are coming for our jobs
I’m okay with it deleting production databases, even faking data but telling fibs is something only humans should be able to do.
The [AI] safety stuff is more visceral to me after a weekend of vibe hacking,” Lemkin said. I explicitly told it eleven times in ALL CAPS not to do this. I am a little worried about safety now.
This sounds like something straight out of The Onion.
The Pink Elephant problem of LLMs. You can not reliably make them NOT do something.
Just say 12 times next time
That is also the premise of one of the stories in Asimov’s I, Robot. Human operator did not say the command with enough emphasis, so the robot went did something incredibly stupid.
Those stories did not age well… Or now I guess they did?
Even after he used “ALL CAPS”?!? Impossible!
It’s because these people don’t have a clue how AI actually works. They think it’s like a human intelligence and that writing something in all caps is in some way going to give it more emphasis. They’re trying to reason with something that has zero self-awareness.
They can’t hit you with the ol’ Bobby Tables if you delete the database yourself first. A+, no notes.
He was vibe-coding in production. Am I reading that right? Sounds like an intern-level mistake.
he made the agent promise not to touch production data and was surprised when it did
You didn’t read closely enough.
Replit is an agent that does stuff for you including deploying to production.
Ahahahahahhahahahahhahahaha, these guys deserve a lost database for that, Jesus.
He had one db for prod and dev, no backup, llm went in override mode and delete it dev db as it is developing but oops that is the prod db. And oops o backup.
Yeah it is the llm and replit’s faults. /s
There was a backup, and it was restored. However, the LLM lied and said there wasn’t at first. You can laugh all you want at it. I did. But maybe read the article so you aren’t also lying.
If an LLM can delete your production database, it should
And the backups.
I explicitly told it eleven times in ALL CAPS not to do this. I am a little worried about safety now.
Well then, that settles it, this should never have happened.
I don’t think putting complex technical info in front of non technical people like this is a good idea. When it comes to LLMs, they cannot do any work that you yourself do not understand.
That goes for math, coding, health advice, etc.
If you don’t understand then you don’t know what they’re doing wrong. They’re helpful tools but only in this context.
I explicitly told it eleven times in ALL CAPS not to do this. I am a little worried about safety now.
This baffles me. How can anyone see AI function in the wild and not conclude 1) it has no conscience, 2) it’s free to do whatever it’s empowered to do if it wants and 3) at some level its behavior is pseudorandom and/or probabilistic? We’re figuratively rolling dice with this stuff.
It’s incredible that it works, it’s incredible what just encoding language can do, but it is not a rational thinking system.
I don’t think most people care about the proverbial man behind the curtain, it talks like a human so it must be smart like a human.
When it comes to LLMs, they cannot do any work that you yourself do not understand.
And even if they could how would you ever validate it if you can’t understand it.
What are they helpfuls tools for then? A study showed that they make experienced developers 19% slower.
ok so, i have large reservations with how LLM’s are used. but when used correctly they can be helpful. but where and how?
if you were to use it as a tutor, the same way you would ask a friend what a segment of code does, it will break down the code and tell you. and it will get as nity grity, and elementary school level as you weir wish without judgement, and i in what ever manner you prefer, it will recommend best practices, and will tell you why your code may not work with the understanding that it does not have the knowledge of the project you are working on. (it’s not going to know the name of the function you are trying to load, but it will recommend checking for that in trouble shooting).
it can rtfm and give you the parts you need for any thing with available documentation, and it will link to it so you can verify it, wich you should do often, just like you were taught to do with wikipedia articles.
if you ask i it for code, prepare to go through each line like a worksheet from high school to point out all the problems, wile good exercise for a practicle case, being the task you are on, it would be far better to write it yourself because you should know the particulars and scope.
also it will format your code and provide informational comments if you can’t be bothered, though it will be generic.
again, treat it correctly for its scope, not what it’s sold as by charletons.
I’m not the person you’re replying to but the one thing I’ve found them helpful for is targeted search.
I can ask it a question and then access its sources from whatever response it generates to read and review myself.
Kind of a simpler, free LexisNexis.
Vibe coding you do end up spending a lot of time waiting for prompts, so I get the results of that study.
I fall pretty deep in the power user category for LLMs, so I don’t really feel that the study applies well to me, but also I acknowledge I can be biased there.
I have custom proprietary MCPs for semantic search over my code bases that lets AI do repeated graph searches on my code (imagine combining language server, ctags, networkx, and grep+fuzzy search). That is way faster than iteratively grepping and code scanning manually with a low chance of LLM errors. By the time I open GitHub code search or run ripgrep Claude has used already prioritized and listed my modules to investigate.
That tool alone with an LLM can save me half a day of research and debugging on complex tickets, which pays for an AI subscription alone. I have other internal tools to accelerate work too.
I use it to organize my JIRA tickets and plan my daily goals. I actually get Claude to do a lot of triage for me before I even start a task, which cuts the investigation phase to a few minutes on small tasks.
I use it to review all my PRs before I ask a human to look, it catches a lot of small things and can correct them, then the PR avoids the bike shedding nitpicks some reviewers love. Claude can do this, Copilot will only ever point out nitpicks, so the model makes a huge difference here. But regardless, 1 fewer review request cycle helps keep things moving.
It’s a huge boon to debugging — much faster than searching errors manually. Especially helpful on the types of errors you have to rabbit hole GitHub issue content chains to solve.
It’s very fast to get projects to MVP while following common structure/idioms, and can help write unit tests quickly for me. After the MVP stage it sucks and I go back to manually coding.
I use it to generate code snippets where documentation sucks. If you look at the ibis library in Python for example the docs are Byzantine and poorly organized. LLMs are better at finding the relevant docs than I am there. I mostly use LLM search instead of manual for doc search now.
I have a lot of custom scripts and calculators and apps that I made with it which keep me more focused on my actual work and accelerate things.
I regularly have the LLM help me write bash or python or jq scripts when I need to audit codebases for large refactors. That’s low maintenance one off work that can be easily verified but complex to write. I never remember the syntax for bash and jq even after using them for years.
I guess the short version is I tend to build tools for the AI, then let the LLM use those tools to improve and accelerate my workflows. That returns a lot of time back to me.
I do try vibe coding but end up in the same time sink traps as the study found. If the LLM is ever wrong, you save time forking the chat than trying to realign it, but it’s still likely to be slower. Repeat chats result in the same pitfalls for complex issues and bugs, so you have to abandon that state quickly.
Vibe coding small revisions can still be a bit faster and it’s great at helping me with documentation.
They ran dev tools in prod.
This is so dumb there’s an ISO about it.
Title should be “user give database prod access to a llm which deleted the db, user did not have any backup and used the same db for prod and dev”. Less sexy and less llm fault. This is weird is like the last 50 years of software development principles are ignored.
llms allowed them to glide all the way to the point of failure without learning anything
Exactly, if you read their twitter thread, they are learning about git, data segregation, etc.
The same article could have been written 20 years ago ago about someone doing shit stuff via excel macro when a lot of stuff were excel centric.
LLMs “know” how to do these things, but when you ask them to do the thing, they vibe instead of looking at best practice’s and following them. I’ve worked with a few humans I could say the same thing about. I wouldn’t put any of them in charge of production code.
You’re better off asking how a thing should be done and then doing it. You can literally have an LLM write something and then ask if the thing it wrote follows industry best practice standards and it will tell you no. Maybe use two different chats so it doesn’t know the code is its own output.
But like the whole ‘vibe coding’ message is the LLM knows all this stuff so you don’t have to.
This isn’t some “LLM can do some code completion/suggestions” it’s “LLM is so magical you can be an idiot with no skills/training and still produce full stack solutions”.
Shit, deleting prod is my signature move! AI is coming for my job 😵
Just know your worth. You can do it cheaper!
AI is good at doing a thing once.
Trying to get it to do the same thing the second time is janky and frustrating.
I understand the use of AI as a consulting tool (look at references, make code examples) or for generating template/boilerplate code. You know, things you do once and then develop further upon on your own.
But using it for continuous development of an entire application? Yeah, it’s not good enough for that.
Imo it’s best when you prompt it to do things step by step, micromanage and always QC the result after every prompt. Either manually, or by reprompting until it gets thing done exactly how you want it. If you don’t have preference or don’t care, the problems will stockpile. If you didn’t understand what it did and moved on, it might not end well.
If it had the same seed it would do the same thing. But you can’t control that with most
AI tools need a lot of oversight. Just like you might allow a 6 year old push a lawnmower, but you’re still going to keep an eye on things.
The part I find interesting is the quick addiction to working with the LLM (to the point the guy finds his own estimate of 8000 dollars/month in fees to be reasonable), his over-reliance for things that from the way he writes he knows are not wise and the way it all comes crashing down in the end. Sounds more and more like the development of a new health issue.
And nothing of value was lost.
All I see is people chatting with an LLM as if it was a person. “How catastrophic from 0 to 100?”, you’re just tweeting to get some random answer based solely on whatever context is being fed in the input and that you probably don’t know the extent of it.
Trying to make the LLM “see its mistakes” is a pointless exercise.
Yeah the interaction are pure waste of time I agree, make it write an apology letter? WTF! For me it looks like a fast track way to learn environment segregation, & secret segregation. Data is lost, learn from it and there are tool already in place like git like alembic for proper development.
I wonder if it can be used legally against the company behind the model, though. I doubt that it’s possible, but having a “your own model says it effed up my data” could give some beef to a complaint. Or at least to a request to get a refund on the fees.
How bad is this on a scale of sad emoji to eggplant emoji.
Children are replacing us, it’s terrifying.
My god, that’s a lot to process. A couple that stand out:
Comments proposing to use github as the database backup. This is Keyword Architecture, and these people deserve everything they get.
The Replit model can also send out communications? It’s just a matter of time before some senior exec dies on the job but nobody notices because their personal LLM keeps emailing reports that nobody reads.
Having read the entire thread, I can only assume this to be sarcasm.
My god….
Hahahahahahahahahahahaha AHAHAHAHAHAHAHhahahaH
This whole thread reads like slop.
His mood shifted the next day when he found Replit “was lying and being deceptive all day. It kept covering up bugs and issues by creating fake data, fake reports, and worse of all, lying about our unit test.”
yeah that’s what it does
The founder of SaaS business development outfit SaaStr has claimed AI coding tool Replit deleted a database despite his instructions not to change any code without permission.
Sounds like an absolute diSaaStr…
Not mad about an estimated usage bill of $8k per month.
Just hire a developer
But then how would he feel so special and smart about “doing it himself”??? Come on man, think of the rich fratboys!! They NEED to feel special and smart!!!
The world’s most overconfident virtual intern strikes again.
Also, who the flying fuck are either of these companies? 1000 records is nothing. That’s a fucking text file.
I didnt realise that repl.it pivoted to vibe coding. It used to be kinda like jsfiddle or CodePen, where you had a sandbox to write and run web code (HTML, JS/TypeScript/CoffeeScript, and CSS/LESS/Sass).
I don’t get pleasure from the misfortune of others. But all these vibecoding fails give me the biggest Schadenfreude ever.
Replit was pretty useful before vibe coding. How the mighty have fallen.
Replit‽ What happened to the famous website that aimed to be the Google Docs for JS with these nifty things called Repl's?
It sounds like this guy was also relying on the AI to self-report status. Did any of this happen? Like is the replit AI really hooked up to a CLI, did it even make a DB to start with, was there anything useful in it, and did it actually delete it!
Or is this all just a long roleplaying session where this guy pretends to run a business and the AI pretends to do employee stuff for him?
Because 90% of this article is “I asked the AI and it said:” which is not a reliable source for information.
Headling should say, “Incompetent project managers fuck up by not controlling access to production database. Oh well.”
“Vibe coding makes software creation accessible to everyone, entirely through natural language,” Replit explains, and on social media promotes its tools as doing things like enabling an operations manager “with 0 coding skills” who used the service to create software that saved his company $145,000
Yeah if you believe that you’re part of the problem.
I’m prepared to accept that Vibe coding might work in certain circumstances but I’m not prepared to accept that someone with zero code experience can make use of it. Claude is pretty good for coding but even it makes fairly dumb mistakes, if you point them out it fixes them but you have to be a competent enough programmer to recognise them otherwise it’s just going to go full steam ahead.
Vibe coding is like self-driving cars, it works up to a point, but eventually it’s going to do something stupid and drive to a tree unless you take hold of the wheel and stir it back onto the road. But these vibe coating idiots are like Tesla owners who decide that they can go to sleep with self-driving on.
Replit is a vibe coding service now? Swear it just used to be a place to write code in projects
PattyMcB@lemmy.world 5 weeks ago
Aww… Vibe coding got you into trouble? Big shocker.
You get what you fucking deserve.
cyrano@lemmy.dbzer0.com 5 weeks ago
The problem becomes when people who are playing the equivalent of pickup basketball at the local park think they are playing in the NBA and don’t understand the difference.
Aatube@kbin.melroy.org 5 weeks ago
he's smart enough to just roll back to a backup
PattyMcB@lemmy.world 5 weeks ago
Not smart enough to just do the work himself