The vibecoders are becoming sentient
-
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
I suspect it's a bit of both. With agents the review size can be pretty small and easier to digest which leads to more people reviewing, but I suspect it is still more surface level.
-
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.
Answer is probably the same as before AI: build a portfolio on GitHub
You really think that using GitHub falls in the usual vibecoding toolbox? As in: would they even know where/how to look?
-
Answer is probably the same as before AI: build a portfolio on GitHub
You really think that using GitHub falls in the usual vibecoding toolbox? As in: would they even know where/how to look?
You think vibe coders don’t love the smell of their own shit enough to show it to the world?
-
It makes me so mad that there are CS grads who can't find work at the same time as companies are exploiting the H1B process saying "there aren't enough applicants". When are these companies going to be held accountable?
Never, they donate to get the politicians reelected.
-
It's kind of hard for me to tell on this one. Maybe the boomer lead is seeping into my brain.
Nah, it's the microplastics.
-
My path was working for a consulting firm (Accenture) for a few years, making friends with my clients, and then jumping to freelance work a few years later when I can get paid my contract rate directly rather than letting Accenture take a big chunk of it.
Working with Accenture
I am so sorry..
-
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?
No idea, but I am not sure your family member is qualified. I would estimate that a coding LLM can code as well as a fresh CS grad. The big advantage that fresh grads have is that after you give them a piece of advice once or twice, they stop making that same mistake.
-
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?
No idea, but I am not sure your family member is qualified. I would estimate that a coding LLM can code as well as a fresh CS grad. The big advantage that fresh grads have is that after you give them a piece of advice once or twice, they stop making that same mistake.
-
Working with Accenture
I am so sorry..
It was a wild ride
-
No idea, but I am not sure your family member is qualified. I would estimate that a coding LLM can code as well as a fresh CS grad. The big advantage that fresh grads have is that after you give them a piece of advice once or twice, they stop making that same mistake.
a coding LLM can code as well as a fresh CS grad.
For a couple of hundred lines of code, they might even be above average. When you split that into a couple of files or start branching out, they usually start to struggle.
after you give them a piece of advice once or twice, they stop making that same mistake.
That's a damn good observation. Learning only happens with re-training and that's wayyy cheaper when done in meat.
-
It makes me so mad that there are CS grads who can't find work at the same time as companies are exploiting the H1B process saying "there aren't enough applicants". When are these companies going to be held accountable?
After they fill up on H1B workers and find out that only 1/10 is a good investment.
H1B development work has been a thing for decades, but there's a reason why there are still high-paying development jobs in the US.
-
Has he tried being a senior developer? He should really try being a senior developer.
He needs at least a decade of industry experience. That helps me find jobs.
-
It makes me so mad that there are CS grads who can't find work at the same time as companies are exploiting the H1B process saying "there aren't enough applicants". When are these companies going to be held accountable?
This is in no way new. 20 years ago I used to refer to some job postings as H1Bait because they'd have requirements that were physically impossible (like having 5 years experience with a piece of software <2 years old) specifically so they could claim they couldn't find anyone qualified (because anyone claiming to be qualified was definitely lying) to justify an H1B for which they would be suddenly way less thorough about checking qualifications.
-
I have never used an AI to code and don't care about being able to do it to the point that I have disabled the buttons that Microsoft crammed into VS Code.
That said, I do think a better use of AI might be to prepare PRs in logical and reasonable sizes for submission that have coherent contextualization and scope. That way when some dingbat vibe codes their way into a circle jerk that simultaneously crashes from dual memory access and doxxes the entire user base, finding issues is easier to spread out and easier to educate them on why vibe coding is boneheaded.
I developed for the VFX industry and I see the whole vibe coding thing as akin to storyboards or previs. Those are fast and (often) sloppy representations of the final production which can be used to quickly communicate a concept without massive investment. I see the similarities in this, a vibe code job is sloppy, sometimes incomprehensible, but the finished product could give someone who knew what the fuck they are doing a springboard to write it correctly. So do what the film industry does: keep your previs guys in the basement, feed them occasionally, and tell them to go home when the real work starts. (No shade to previs/SB artists, it is a real craft and vital for the film industry as a whole. I am being flippant about you for commedic effect. Love you guys.)
I think storyboards is a great example of how it could be used properly.
Storyboards are a great way for someone to communicate "this is how I want it to look" in a rough way. But, a storyboard will never show up in the final movie (except maybe fun clips during the credits or something). It's something that helps you on your way, but along the way 100% of it is replaced.
Similarly, the way I think of generative AI is that it's basically a really good props department.
In the past, if a props / graphics / FX department had to generate some text on a computer screen that looked like someone was Hacking the Planet they'd need to come up with something that looked completely realistic. But, it would either be something hand-crafted, or they'd just go grab some open-source file and spew it out on the screen. What generative AI does is that it digests vast amounts of data to be able to come up with something that looks realistic for the prompt it was given. For something like a hacking scene, an LLM can probably generate something that's actually much better than what the humans would make given the time and effort required. A hacking scene that a computer security professional would think is realistic is normally way beyond the required scope. But, an LLM can probably do one that is actually plausible for a computer security professional because of what that LLM has been trained on. But, it's still a prop. If there are any IP addresses or email addresses in the LLM-generated output they may or may not work. And, for a movie prop, it might actually be worse if they do work.
When you're asking an AI something like "What does a selection sort algorithm look like in Rust?", what you're really doing is asking "What does a realistic answer to that question look like?" You're basically asking for a prop.
Now, some props can be extremely realistic looking. Think of the cockpit of an airplane in a serious aviation drama. The props people will probably either build a very realistic cockpit, or maybe even buy one from a junkyard and fix it up. The prop will be realistic enough that even a pilot will look at it and say that it's correctly laid out and accurate. Similarly, if you ask an LLM to produce code for you, sometimes it will give you something that is realistic enough that it actually works.
Having said that, fundamentally, there's a difference between "What is the answer to this question?" and "What would a realistic answer to this question look like?" And that's the fundamental flaw of LLMs. Answering a question requires understanding the question. Simulating an answer just requires pattern matching.
-
This is in no way new. 20 years ago I used to refer to some job postings as H1Bait because they'd have requirements that were physically impossible (like having 5 years experience with a piece of software <2 years old) specifically so they could claim they couldn't find anyone qualified (because anyone claiming to be qualified was definitely lying) to justify an H1B for which they would be suddenly way less thorough about checking qualifications.
Yeah companies have always been abusing H1B, but it seems like only recently is it so hard for CS grads to find jobs. I didn't have much trouble in 2010 and it was easy to hop jobs for me the last 10 years.
Now, not so much.
-
Yeah, this is my nightmare scenario. Code reviews are always the worst part of a programming gig, and they must get exponentially worse when the junior devs can crank out 100s of lines of code per commit with an LLM.
Also, LLMs are essentially designed to produce code that will pass a code review. It's output that is designed to look as realistic as possible. So, not only do you have to look through the code for flaws, any error is basically "camouflaged".
With a junior dev, sometimes their lack of experience is visible in the code. You can tell what to look at more closely based on where it looks like they're out of their comfort zone. Whereas an LLM is always 100% in its comfort zone, but has no clue what it's actually doing.
-
Nah, it's the microplastics.
Why not both
? -
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.
Tests are probably both the best and worst things to use LLMs for.
They're the best because of all the boilerplate. Unit tests tend to have so much of that, setting things up and tearing it down. You want that to be as consistent as possible so that someone looking at it immediately understands what they're seeing.
OTOH, tests are also where you figure out how to attack your code from multiple angles. You really need to understand your code to think of all the ways it could fail. LLMs don't understand anything, so I'd never trust one to come up with a good set of things to test.
-
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.
Not me, I'd rather work on a clean code base without any slop, even if it pays a little less. QoL > TC
-
Can someone tell me what vibe coding is?
From what I understand, it's using an LLM for coding, but taken to an extreme. Like, a regular programmer might use an LLM to help them with something, but they'll read through the code the LLM produces, make sure they understand it, tweak it wherever it's necessary, etc. A vibe coder might not even be a programmer, they just get the LLM to generate some code and they run the code to see if it does what they want. If it doesn't, they talk to the LLM some more and generate some more code. At no point do they actually read through the code and try to understand it. They just run the program and see if it does what they want.
