I don’t really care about vibe coders but as a dev with just under 2 decades in the field:
- Your vibe coding shit will not go to prod until humans fully review it
- You better review it yourself first before offloading that massive mental drain to someone else (which means you still need to have some semblance of programming skills). Don’t open a PR with 250 files in it and then tell someone else to validate it.
- Use more context. Don’t give it vague ass prompts.
- Don’t use auto-accept. That’s just lazy asshole shit.
I can’t stress this enough: if you give me a PR with tons of new files and expect me to review it when you didn’t even review it yourself, I will 100% reject it and make you do it. If it’s all dumped into a single commit, I will whip your computer into the nearest body of water and tell you to go fish it out.
I don’t care what AI tool wrote your code. You’re still responsible for it and I will blame you.
When I see a sloppy PR I remind people “AI didn’t write that. You wrote it. Your name is on the git blame.”
I like this mentality. I might start telling people the same thing
Love it, I have a vibe coding colleague I will use this with.
If it’s all dumped into a single commit, I will whip your computer into the nearest body of water and tell you to go fish it out.
I’m going to steal this for an update to an internal guidance document for my dev team. Thank you.
Lmao glad I could help! I hate those big commits. They’re so much harder to traverse and know what’s going on. Developer experience has been big on my mind lately. Working 5 days a week is already hard, but there are moments when we can make tiny bits easier for each other.
My entire IT career has been funded by morons like this. This is just the latest moronic idea that is going to pay my bills. Cleaning up after vibe coders has guaranteed my income until I die. You see, posts like this focus on the code that is broken and requires another dev to fix it enough to get it going. There is a long road from “finally working” to “production ready” to “optimized”, and we get paid along every inch of the way.
Removed by mod
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.
Removed by mod
Oh man, I love ChatGPT for one thing in particular: “Hey chatbot, is there some library or standard library function for that very specific, yet still kinda generic thing I’m trying to do, so that I don’t have to write it myself?”
It does frequently give a helpful answer. That is, it doesn’t give me working code, but a helpful pointer to some manual where I can find good instructions for how to use the thing to solve my problem.
It’s like the nerd version of Synthol body ‘builders’.
Well
That’s horrifying. I thought it was way cooler that I could make my own muscles bigger by diet and exercise but maybe cool is different in different parts of the world
That’s horrifying.
I have no empirical evidence… but I’m fully convinced there’s at least 1 idiot with a synthol pp
I would not be a slight bit surprised if all of those guys tried to have a synthol pp.
Removed by mod
Best erotic story ever on !DevsGoneWild@lemmynsfw.com <3
I’m sure it’s fun to see a series of text prompts turn into an app, but if you don’t understand the code and can’t fix it when it doesn’t work without starting over, you’re going to have a bad time. Sure, it takes time and effort to learn to program, but it pays off in the end.
Like trying to write a book just using auto complete
Its just funny that it ends up costing more time
But I thought armies of teenagers were starting tech businesses?!
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
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.
Agree, my spouse and I do the same. You need to know how to code and understand the basic principles otherwise it’s a bit like the Chinese room thing where you may or may not operate currently not have no actual clue of what you’re doing. You need to be about to see when llms follow their hobby and blow three lines of code unnecessarily out of proportion by adding 60 lines of unneeded shit that opens the door to more bugs.
Bruh yer not doing it right. Are you stupid, bruh? You gotta work on yer promps, bruh. You gotta watch some tiktoks on it, bruh. Bruh, go watch @demisets4, bruh. Learn to prompt, bruh. Your not good at it, bruh. Bruh, you should try something else if you can’t figure it out that’s a you problem, bruh.
deleted by creator
As a programmer I’ve found it infinitely times more useful for troubleshooting and setting up things than for programming. When my Arch Linux nukes itself again I know I’ll use an LLM, when I find a random old device or game at the thrift store and want to get it to work I’ll use an LLM, etc. For programming I only use the IntelliJ line completion models since they’re smart enough to see patterns for the dumb busywork, but don’t try to outsmart me most of the time which would only cost more time.
deleted by creator
I refuse to believe this post isn’t satire, because holy shit.
