Hello programmers! I’ve been making a living for a couple of decades figuring out stuff for people and coding whatever will make them happy. It’s fun. I’ve grown to prefer the people to the coding but I still get a kick out of the whole thing.
The problem is: at the job we’re being asked to pivot to vibe coding. At this point the order is to use it for all code, read the slop carefully, argue with the machine for way too long and only then open that PR. Massive productivity gains are expected. I’m appalled from an ethical, philosophical and professional standpoint. We’re a non-profit ngo ffs. My colleagues are fine with it. If I get even slightly critical the group goes awkwardly silent and I get comments on how all the programmers they know from other places don’t code anymore.
If this is how it goes from now on, I’m out. Is it really though? Are all businesses switching to vibe coding? Have some of you started switching career? I think I want to go to meatspace. Hand-made coding could make a cute hobby.
No, vibe coding is what happens when a new technology spawns, and everyone is in a gold rush to find out what they can use it for.
LLM assisted software development is probably here to stay though. I’m also learning the ropes of this agentic stuff, where it works and where it falls flat as I always try to fully understand and take ownership of the code I put in my commits. At the end of the day, it needs to look like I coded it.
On an aside, I’m hopeful we can figure out an ethical way to do model training that respects licensing, such as only training on MIT licensed code. Such a rabbit hole the ethics are.
I write code. There is skill to being able to read documentation. I love tools like predictive IDE’s. Search engines augmented my ability to code with sites like stackoverflow. LLM’s are a continuation of that trend. Often the output is broad strokes that I need to refine. At my workplace, humans are required even with the tool improvements.
I read a geography meme book last week. Non-ai users have wrinklier brains. Don’t worry.
Just don’t do it, if you don’t want. Noone can pull the plug on your will. Only you can.
I’m already branded as practicing the cardinal sin of resisting change. They can’t make me vibe code, but they can absolutely fire me. I’d rather leave on my own terms.
Not to fire you up… better leave yesterday. It got rather quiet due to LLM usage, but when the shit hit’s the fan who’s going to beg on their knees? The more you use it the more you also train it. Most people think they are using a product, but again they fooled everyone into becoming the product.
Professional coder turned vibe coder here. My approach has been to lean in really heavy on creating deterministic harnesses and guardrails, that can also be templated for bootstrapping new slop projects quickly and easily.
Then I end up just getting paid to press button make feature go brrrr, and on my other monitor I work on personal projects that I actually care about, while simultaneously being paid because I press button make feature go brrrr.
Spending the time curating my harnesses and workflows, including pretty rigorous automated testing of what Claude shits out, is what keeps it all together. You can’t just set it and forget it. Something about that is fun to me, though, because I am masochistic devops man.
That’s pretty great actually!
I’ve so far managed to avoid being mandated vibe coding at work since I have some pull at the company, so I don’t have a ton of experience working with it.
How long does each brrrr take? Does it give you a reasonable amount of time to sink into a personal project before it completes?
I have hand-rolled agents/skills that run through a standardized process:
- investigate
- plan
- execute
- self-review
- open PR
I leverage bash and python scripts whenever possible within harnesses, to try to avoid Claude injecting flair where steps and processes should be as repeatable as possible. I also write a lot of supplementary skills for it to use, with least-privilege scoping (important!), to give it access to do things like read work request tickets, run staging smoke tests, etc.
You can get to a point where you can basically say something like, “Investigate and plan SWE-1773” and it’ll do all the shit, spit out a human-readable markdown plan complete with mermaid diagrams. You then okay to execute it, and at the end do an earnest PR review, and some manual tests.
Each brrr is gonna depend on how thorough you need to be, feature sizes, and if it shits the bed during planning. But honestly, the likelihood of your LLM shitting the bed is heavily dependent on how good of a harness engineer you want to become. If you shape and mold the environment and workflow like someone who say, works in developer tooling, then output quality can become surprisingly reliable.
You said you work on personal projects while it brrrrs. Of course it depends, but are we talking personal projects 30s at a time, 10 min at a time, or an hour?
Thanks for sharing your workflow. I’m already pretty fed up on how tech just keeps on adding layers upon layers of complexity. I love understanding what goes on. You can imagine I’m not thrilled.
These people are the ones causing the problems. They tell you they’ve got it all figured out make it sound great but they’re the ones shitting out garbage faster than you can fix it.
If you’re gonna talk shit about my skills you could at least @ me. I’ve worked decades in the industry, with a lot of that time knee-deep in dev tooling and devops. It’s a cake walk keeping an LLM on guard rails producing well-tested code if you’re a seasoned and sane architect, compared to say, humans. Sorry you can’t seem to wrap your head around it.
Lol
Wow, you sound insufferable.
Congratulations on giving up your career, though. I’m sure the “architect” will take care of you.
I’ve worked decades in the industry
That doesn’t mean anything. I have seen senior developers who built up “street cred” for decades fall into the vibecoding trap and deskill themselves rapidly.
What you described is not vibe coding. Vibe coding is when you don’t read the code.
Vibe coding is fart coding whether you checked it or not. You still cheated and you didn’t use your own cognitive utilities…
OK what game am I playing, and who wrote the rules that say I cheated?
That was more of a royal “you” because I think we’ve all been guilty of it by now.
I don’t know who wrote the rules but I don’t think we should not be calling people vibe coders just because they reviewed it. That’s resetting us under a dystopian playbook.
I think your initial criticism is too easy to refute. If someone wants to criticize me for using LLMs because they’re bad for the environment or because they’re built on stolen IP, sure we can have that more nuanced discussion.
But telling me that I’m “cheating and I didn’t use my own cognitive utilities” – you have no idea how I use LLMs. You’re just assuming that I’m putting zero critical thought into the code I’m submitting. I review every line of code I submit, regardless of whether it was generated by LLM, written by hand, or a combination of both. And it is a laborious task; but my labor is more focused on decision making and designing tests than typing and fighting a compiler.
I haven’t measured my productivity in any meaningful way, so I won’t try to argue that LLMs are strictly more productive. That’s a separate discussion. All I can say is that I prefer the workflow where I can describe my thoughts in natural language and then review generated code more than writing the code myself.
Lmao the last line in this comment is literally you admitting you prefer avoiding to use your brain to code.
AI slop mfers will literally write a book in defense of their AI use and then go “but yeah, I actually do suck” at the end.
deleted by creator
It is heavily normalized in industry now.
I quit a job that added AI use to performance reviews super early. That was pure bureaucratic cancer and most of my good coworkers burned out and left. I don’t think I’ll ever work for a big corp again, I actually like my work so much more now.
At work I’m expected to use it, our clients want it, my boss likes that he can feel technical when writing tickets (they’re mostly wrong though, and the tickets solution instead of report and request). It genuinely can do some useful tasks that make sense to use it for.
There are real pros and cons, but there’s no putting this back in the bottle. Philosophically I do hate it and everything it stands for, but practically it has allowed me to do a lot that I couldn’t (and wouldn’t) before.
The only good solution I’ve found is that you have to get your hands dirty and stay in the weeds. You cannot let it run off and do what it wants, you have to drive and then tag it in. When you vibe code something you’ll find yourself in three weeks resolving an issue and going “wait, it does what?!”, and of course, arguing with the gibberish Claude or GPT claims is English but is actually the first stage of model collapse as the models reinforcement train on ever more distilled data. Plus, skill atrophy is real. Decide which skills to allow to atrophy carefully.
AI code review is good and useful. I used to use it as a first wave for obvious stuff, but it is actually decent and high trust now. Saves me some time on that.
It’s good at finding bugs and security issues, and one thing I actually really like is having it model a system as a state machine and enumerate all the possible states to find bugs — especially concurrency bugs. I don’t work in a provable language, so this is hugely helpful.
I would be very hesitant to take a role where they push vibe coding or “agentic fleets” or loops or whatever. If you’re babysitting 6 Claude code sessions you aren’t working and you’re not in the loop on any of them. That will accumulate as tech debt and bog you down over time. It’ll suck your soul dry. It’s miserable.
Reading the slop and reviewing it “software factory” style is a very bad sign to me.
Some code is throwaway or disposable, vibing that makes sense to me. But the core work is more important than ever. Maybe the disposable code is the new part, I look at it like installing an IKEA kitchen, it’s slop, but it looks nice, the important part is the foundation and level flooring that enables the slop to stand up.
arguing with the gibberish Claude or GPT claims is English
You’re right to push back on that – I’ve been using Claudish the whole time and this actually changes everything. If we use English instead, each one of these comments could be a single, concise line. One thing worth knowing: This is not a minor boost to understanding, but a complete game changer. Understanding my bullshit has been gated behind speaking LLMese.
Nah, really, I’ve been able to get fairly decent code out of the newer models since I work with a very popular language. Not one-shotted of course, but after some change requests or manual changes. But the language these models speak (including the Chinese ones, it seems) is infuriating and they seem to insist on tons of super long comments in places where the code itself feels self-explanatory. My philosophy is to write “why” comments, not “how” comments, but not a single model seems to agree with me.
I look at it like installing an IKEA kitchen, it’s slop, but it looks nice
Are IKEA kitchens really that bad? I’ve been looking to remodel my ancient kitchen and it comes to 5-6k EUR, appliances included (minus the fridge, I upgraded that a while ago), from IKEA. If I ask a carpenter to do a proper one, that’s going to be more like 10-20k and I don’t wanna spend that kinda money lol
I think IKEA has different price points
The ones installed when I moved in were those cheap particle board counter tops and cabinets, so when my dishwasher leaked everything expanded and cracked and can never be fixed. A real wood or high quality MDF would have been okay with a one time water event (if dried properly)
It stood up for years, worked fine, wasn’t awful. Just was cheap and not resilient.
I think I’ll use this answer to reflect. So first, vibe coding means, to me anyway, taking w/e the ai spits at you without checking/understanding. Aside from that, like okay, check the code send the PR. But anyway, at one point in my life, I thought, hey it would be great to go from writing code to reviewing code by others. I thought that would be a stepping stone for me. After a carefully thought, that’s what ai code gen is in the end. One of those careful what you wish for kind of thing.
I do think LLM is here to stay, one way or another. Might be like the next compiler like a comment suggested. I also do think that any software developer/engineer is stronger candidate with AI than one who rejects it.
Vibe coding means giving an LLM access to the entire repository and blindly accepting the very large pull requests it makes after you tell it what you want.
That is an insane way to do development and any company who does it will suffer.
What is becoming normal is AI assisted programming. The developer retains understanding of the codebase and uses an LLM to generate small boilerplate sections because it’s quicker than writing everything by hand.
Using LLMs to write code is perfectly acceptable as long as there is a human understands exactly what the code does. Do not give agency to the AI and you’ll be fine. Let it make decisions for you and you’ll be out of the job pretty quickly.
