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.
One question I have for the slop advocates in this thread is this - do you not like programming? Did you fall for the „learn to code“ meme and just learned the bare minimum to get a paycheque working on web dashboards?
Like why would you voluntarily cut out the most enjoyable part of the job, and go around scoffing at people who don’t want to do that?
Productivity is my boss’s problem, not mine, and I’d rather go and try and farm geese (I hate geese) than spend my whole day reading LLM generated code.
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.
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.
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.
Lol
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?
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.
it’s not gonna last. if you tune out of the hype and actually look at some hard data, vibecoding stops looking so hot: https://codemanship.wordpress.com/2026/08/12/ai-software-development-what-does-the-data-say/
the current token costs are unsustainable also. the only ones making bank right now are the shovel sellers: https://isaiprofitable.com/
personally i’m working on hand-rewriting several projects vibecoded out by a non-dev in a small shop. not only is a lot of this straight up broken nonsense, the amount of tech debt is staggering. previous job wasn’t better, i had to spend more time fixing slop from former coworkers than actually introducing new features. keep your skills sharp and persevere. we’ll get through this.
tl;dr: this, too, shall pass. but holy shit.
It’s absolutely going to last. IMO until Astra the models were not good enough to really be worth bothering with, but we’ve reached a tipping point.
And while I still do read the code they make and then fix things (or tell them to do things differently), it’s still waaaay quicker than doing it “by hand”.
Sorry but if you’re expecting this to be a temporary thing you’re going to be very disappointed.
IMO until Astra the models were not good enough to really be worth bothering with, but we’ve reached a tipping point.
People said the same about older models.
Yep. Every. Single. One.
But being able to ship small, mildly broken, internal tools for my non-technical coworkers quickly is actually amazing.
Nobody cares if the internal tool code is nice, but when it shaves 50% of the work off of sales the sales team gets excited. So if I vibe up a shitty UI it’s still a net gain.
I’ve probably automated away like 60% of the ad hoc work I used to get into internal tools, and that has helped a ton with workload and budget.
Careful. You know how it goes with temporary workarounds? Suddenly, you find yourself maintaining slightly broken load-bearing slop.
It’s normalized now but I don’t see it lasting. I’m retiring at the end of this year cause I’ve had enough of it and I don’t want to wait anymore for companies to finally figure it out. I’ve told so many what needs to change, what they need to do in order to fix their builds (mainly consisting of rebuild it, rehire the devs you laid off, use AI as a rubber duck only) and none of them listen. They thank me for my time, cut a cheque, and send me on my way. I had the idiotic notion of trying to change things, hopefully make some people see the light but they’ve all drunk the kool-aid and have all pushed all their poker chips in and are currently hoping it works out. it won’t.
Any dev worth their salt can look at what’s been produced and everything is garbage. everything. I’ve yet to meet a single developer of any level that has looked at something that’s been vibe coded and said “hey, that’s not bad!” It’s all crap. the ONLY things that would ever work is if the AI somehow managed to churn something out to be 100% complete and working on the first attempt. something that will never need to be upgraded or scaled or something that would never interact with the user space. Name me something that does that.
The issue as it stands right now is it’s taking too long to fail. it will fail, I guarantee you that, but it’s taking too long. Developers and programmers and engineers can’t wait anymore. They’re not keeping their skills up because many just don’t see a point. Many have been unemployed from the field for so long now they’ve taken different career paths. We’re simply losing developers due to time.
It should have happened by now, should have happened months ago. the gaps in training data are increasing. you get way more hallucinations than solutions. the tool is absolutely worthless but the problem is the people utilizing the tool don’t know any of this. thus token use increases.
What are your thoughts for using AI to colour in & do the tedious bits? So you plan out the structure of what you’re trying to do, work out the individual pieces and get the AI to do a bunch of the (well specified) leg work. I’ve found it fairly reliable like this, especially for things that involve looking up function parameters in unfamiliar APIs. But this does depend on a thorough look over what comes out as well. No doubt there’s still issues that can pop up but generally have found it to be useful overall
If the API is unfamiliar how do you know what it puts out is the best way to use the API without going and reading the docs anyway?
