The vibecoders are becoming sentient
-
I do the same, I am not sure if it saves time. Some times not. Other times if it is a task I really don’t want to work on this helps me to get started and break through procreation
Lol, work as your coitus interruptus.
I know you meant procrastination btw.
-
Vibe coding is useful for super basic bash scripting and that's about it. Even that it will mess up but usually in a suler easily fixed way
I don't think it has much to do with how "complex or not" it is, but rather how common it is.
It can completely fail on very simple things that are just a bit obscure, so it has too little training data.
And it can do very complex things if there's enough training data on those things.
-
Nah I'm on that guy's side. His experience lines up with my own, namely that vibe coding is not useful for people who don't know how to program, but it can be useful for people who do know how to program, and simply aren't familiar with the specific syntax used in a language they're not an expert in.
In that case, the queries to the AI model aren't, "write me a program that can do X", it's more like "write me a function in this language that can take A, B, and C as inputs, do operation Y with them, and return Z", or "what's the best way to find all of the unique elements in an array and sort it alphabetically in this language". Then the programmer can take those pieces and build up a proper application with them. The AI isn't actually writing the program for you, it's more like a customized Stack Overflow generator, without having to wade through a decade of people arguing back and forth in the comments about inane bullshit.
Does it save a ton of time? No, but it's still helpful, and can get you up and running in a new language much faster than the alternative.
I'm just using AI to get me the damn standard library function I want to use but can't remember. Way faster than clicking through a couple links of a search result for it.
-
This post did not contain any content.
Like trying to write a book just using auto complete
-
This post did not contain any content.
Vibe coding tools are very useful when you want to make a tech movie but the
hollywoodcommand just does not cut it. -
Nah I'm on that guy's side. His experience lines up with my own, namely that vibe coding is not useful for people who don't know how to program, but it can be useful for people who do know how to program, and simply aren't familiar with the specific syntax used in a language they're not an expert in.
In that case, the queries to the AI model aren't, "write me a program that can do X", it's more like "write me a function in this language that can take A, B, and C as inputs, do operation Y with them, and return Z", or "what's the best way to find all of the unique elements in an array and sort it alphabetically in this language". Then the programmer can take those pieces and build up a proper application with them. The AI isn't actually writing the program for you, it's more like a customized Stack Overflow generator, without having to wade through a decade of people arguing back and forth in the comments about inane bullshit.
Does it save a ton of time? No, but it's still helpful, and can get you up and running in a new language much faster than the alternative.
I really like the description of AI coding as 'custom stack overflow generator' because it really sells the flaws as well, to an experienced dev. We go to stack overflow for help with some weird quirk of a language or find an obscure library that solves our specific need.
I think vibe coding is cobbling together a project from a bunch of stack overflow posts -- and they only use the question part of the post.
-
Vibe coding is useful for super basic bash scripting and that's about it. Even that it will mess up but usually in a suler easily fixed way
When I want to be lazy and make some simple excel macros is about the most iv trusted it with that it manages to do with out fucking up and taking more time then just doing it my self.
-
I don't want to dismiss your point overall, but I see that example so often and it irks me so much.
Unit tests are your specification. So, 1) ideally you should write the specification before you implement the functionality. But also, 2) this is the one part where you really should be putting in your critical thinking to work out what the code needs to be doing.
An AI chatbot or autocomplete can aid you in putting down some of the boilerplate to have the specification automatically checked against the implementation. Or you could try to formulate the specification in plaintext and have an AI translate it into code. But an AI without knowledge of the context nor critical thinking cannot write the specification for you.
wrote last edited by [email protected]Unit tests become the specification once they are written. ChatGPT can easily write unit tests from whatever your specification is before that -- such as documentation, a bunch of comments and stubs, or even a first draft of the function itself, given enough context from the rest of the project.
Unit tests are too klunky to think in. You don't prototype the specification by implementing unit tests. And you really only lay down a few critical paths even if you "write the tests first" because code paths always come up during implementation that demand more test coverage anyway.
-
This post did not contain any content.wrote last edited by [email protected]
No way. Youtube ad told me a different story the other day. Could that be a... lie?
(shocked_face.jpg) -
This post did not contain any content.
God bless vibe coders, because of them I'm buying a new PC build this week AND I've decided to get a PS5.
Thank you Vibe Coders, your laziness and and sheer idiocy are padding my wallet nicely.
-
The argument was "AI helps when starting up new projects by making unit tests etc."
Also for not 20, but even building 10 year old libraries using AI is unhelpful. It just keeps hallucinating non-existent packages and functions.
At this point just drive yourself crazy while promising to become goose farmer and commenting every single line in your own words like god intended for programmers to do.
wrote last edited by [email protected]You read "new projects" in, actually. And the whole unit test thing was just an example demonstrating how AI use has to be tightly bounded to be arguably useful.
-
A buddy of mine is into vibe coding, but he actually does know how to code as well. He will reiterate through the code with the llm until he thinks it will work. I can believe it saves time, but you still have to know what you are doing.
I don't see how it would save time as someone whose job is to currently undo what "time" it "saves". You can give Claude Code the most fantastic and accurate prompt in the world but you're still going to have to explain to it how something actually works when it gets to the point, and it will, that it starts contradicting itself and over complicating things.
You said yourself he has to reiterate through the code with the LLM to get something that works. If he already knows it, he could just write it. Having to explain to something HOW to write what you ALREADY know can't possibly be saving time. it's Coding with extra steps.
-
This post did not contain any content.
So there are multiple people in this thread who state their job is to unfuck what the LLMs are doing. I have a family member who graduated in CS a year ago and is having a hell of a time finding work, how would he go about getting one of these "clean up after the model" jobs?
-
I watched a bit out of curiosity and even vibe-coding aside, he is annoying as fuck. Couldn't stand him 20 seconds.
That's an issue on its own. He's just a typical streamer. I already had enough from looking at thumbnails.
-
Nah I'm on that guy's side. His experience lines up with my own, namely that vibe coding is not useful for people who don't know how to program, but it can be useful for people who do know how to program, and simply aren't familiar with the specific syntax used in a language they're not an expert in.
In that case, the queries to the AI model aren't, "write me a program that can do X", it's more like "write me a function in this language that can take A, B, and C as inputs, do operation Y with them, and return Z", or "what's the best way to find all of the unique elements in an array and sort it alphabetically in this language". Then the programmer can take those pieces and build up a proper application with them. The AI isn't actually writing the program for you, it's more like a customized Stack Overflow generator, without having to wade through a decade of people arguing back and forth in the comments about inane bullshit.
Does it save a ton of time? No, but it's still helpful, and can get you up and running in a new language much faster than the alternative.
wrote last edited by [email protected]My company is doing a big push for LLM/codegen/“everyday ‘AI’”
Sorry - threw up in my mouth a little bit there
And pretty much the only thing I acquiesce to using is the “better autocomplete” feature. Most of the other stuff it seems to offer is essentially useless on a day-to-day basis for me.
And moreover, it’s actively harmful to the entire practice of engineering, because management and execs see it as this magical oracle/panopticon that can magically make people more productive and churn out 10x more bullshit products that they didn’t consult with engineers on than before. It can’t and it doesn’t. But that doesn’t stop them from thinking it can.
And then they stop hiring junior levels because “codegen can do that”. And then you have a generational gap in the entire fucking discipline of coding as an art, because the entire fucking tech industry is doing this. And we haven’t even touched on the ecological and infrastructural (as in: water and power, not “which cloud or bare metal do we put this on”) implications and how they’re being blatantly ignored and hand-waved away, or the comical license and usage violations that are perfectly fine when large companies do but you’ve been a naughty boy if you torrent a fucking movie. But I digress.
-
So there are multiple people in this thread who state their job is to unfuck what the LLMs are doing. I have a family member who graduated in CS a year ago and is having a hell of a time finding work, how would he go about getting one of these "clean up after the model" jobs?
Answer is probably the same as before AI: build a portfolio on GitHub. These days maybe try to find repos that have vibe code in them and make commits that fix the AI garbage.
-
So there are multiple people in this thread who state their job is to unfuck what the LLMs are doing. I have a family member who graduated in CS a year ago and is having a hell of a time finding work, how would he go about getting one of these "clean up after the model" jobs?
The difficult part is going to be that new engineers are not generally who people think about to unfuck code. Even before the LLMs junior engineers are generally the people that fuck things up.
It’s through fucking lots of stuff up and unfucking that stuff up and learning how not to fuck things up in the first place that you go from being a junior engineer to a more senior engineer. Until you land in a lofty position like staff engineer and your job is mostly to listen to how people want to fuck everything up and go “maybe let’s try this other way that won’t fuck everything up instead”
Tell your family member to network, that’s the best way to get a job. There are discord servers for every programming language and most projects. Contribute to open source projects and get to know the people.
Build things, write code, open source it on GitHub.
Drill on leet code questions, they aren’t super useful, but in any interview at least part of the assessment is going to be how well they can do on those.
There are still plenty of places hiring. AI has just made it so that most senior engineers have access to a junior engineer level programmer that they can give tasks to at all time, the AI. So anything you can do to stand out is an advantage.
-
A buddy of mine is into vibe coding, but he actually does know how to code as well. He will reiterate through the code with the llm until he thinks it will work. I can believe it saves time, but you still have to know what you are doing.
The most amazing thing about vibe coding is that in my 20 odd years of professional programming the thing I’ve had to beg and plead for the most was code reviews.
Everyone loves writing code, no one it seems much enjoyed reading other people’s code.
Somehow though vibe coding (and the other LLM guided coding) has made people go “I’ll skip the part where I write code, let an LLM generate a bunch of code that I’ll review”
Either people have fundamentally changed, unlikely, or there’s just a lot more people that are willing to skim over a pile of autogenerated code and go “yea, I’m sure it’s fine” and open a PR
-
This post did not contain any content.
Clearly satire
-
This post did not contain any content.
It is not useless. You should absolutely continue to vibes code. Don't let a professional get involved at the ground floor. Don't inhouse a professional staff.
Please continue paying me $200/hr for months on end debugging your Baby's First Web App tier coding project long after anyone else can salvage it.
And don't forget to tell your investors how smart you are by Vibes Coding! That's the most important part. Secure! That! Series! B! Go public! Get yourself a billion dollar valuation on these projects!
Keep me in the good wine and the nice car! I love vibes coding.
