After two years of vibecoding, I'm back to writing by hand

I feel like the vast majority of articles on this are little more than the following:

"AI can be good -- very good -- at building parts. For now, it's very bad at the big picture."

Great engagement-building post for the author’s startup, blog, etc. Contrarian and just plausible enough.

I disagree though. There’s no good reason that careful use of this new form of tooling can’t fully respect the whole, respect structural integrity, and respect neighboring patterns.

As always, it’s not the tool.

False dichotomy. There is a happy medium where you can orchestrate the agent to give you the code you want even when the spec changes

I hear a lot of "I am not a good enough coder..." "It has all the sum of human knowledge..."

That's a very bad way to look at these tools. They legit know nothing, they hallucinate APIs all the time.

The only value they have at least in my book is they type super fast.

Process and plumbing become very important when using ai for coding. Yes, you need good prompts. But as the code base gets more complex, you also need to spend significant time developing test guides, standardization documents, custom linters, etc, to manage the agents over time.

I haven't been vibe coding for more than a few months.

It's just a tool with a high level of automation. That becomes clear when you have to guide it to use more sane practices, simple things like don't overuse HTTP headers when you don't need them.

I don't get what everyone sees in this post. It is just a sloppy rant. It just talks in generalities. There is no coherent argument, there are no examples, and we don't even know the problem space in which the author had bad coding assistant experience.

AI is a good tutor, helping you understand what's going on with the codebase, and also helps with minor autocomplete tasks.

You should never just let AI "figure it out." It's the assistant, not the driver.

I don't know whether I would go that extreme, but I also often find myself faster writing code manually; for some tasks though and contextually, AI-assisted coding is pretty useful, but you still must be in the driving seat, at all times.

Good take though.

unless someone shows their threads of prompts or an unedited stream of them working, it's pointless to put any weight into their opinions.

this is such an individualized technology that two people at the same starting point two years ago, could've developed wildly different workflows.

The part that most resonates with me is the lingering feeling of “oh but it must be my fault for underspecifying” which blocks the outright belief that models are just still sloppy at certain things

Little to no evidence was presented.

This is vibe argumenting.

This is not my experience at all. Claude will ask me follow up questions if it has some. The claim that it goes full steam ahead on its original plan is false.

An excellent example of the political utility of AI, and how long it takes to figure out that it isn't as useful as the hype might make you think.

Previous discussion on the video: https://news.ycombinator.com/item?id=46744572

Taking crazy pills here too.

I just bootstrapped a 500k loc MVP with AI Generator, Community and Zapier integration.

www.clases.community

And is my 3rd project that size, fully vibe coded

You just give up before AI overpass human

It still feels like gambling to me when I use AI code assistants to generate large chunks of code. Sometimes, it will surprise me with how well it does. Other times, it infuriatingly doesn't follow very precise instructions for small changes. This is even when I use it in the way that I often ask for multiple options for solutions and implementations and then choose between them after the AI tool does the course rating.

There are many instances where I get to the final part of the feature and realize I spent far more time coercing AI to do the right thing than it would have taken me to do it myself.

It is also sometimes really enjoyable and sometimes a horrible experience. Programming prior to it could also be frustrating at times, but not in the same way. Maybe it is the expectation of increased efficiency that is now demanded in the face of AI tools.

I do think AI tools are consistently great for small POCs or where very standard simple patterns are used. Outside of that, it is a crapshoot or slot machine.

a lot of AI assisted development goes into project management and system design.

I have been tolerably successful. However, I have almost 30 years of coding experience, and have the judgement on how big a component should be - when I push that myself _or_ with AI, things go hairy.

ymmv.

AI can be good under the right circumstances but only if reviewed 100% of the time by a human.

Homelab is my hobby where I run Proxmox, Debian VM, DNS, K8s, etc, all managed via Ansible.

For what it is worth, I hate docker :)

I wanted to setup a private tracker torrent that should include:

1) Jackett: For the authentication

2) Radarr: The inhouse browser

3) qBitorrent: which receives the torrent files automatically from Radarr

4) Jellyfin: Of course :)

I used ChatGPT to assist me into getting the above done as simple as possible and all done via Ansible:

1) Ansible playbook to setup a Debian LXC Proxmox container

2) Jackett + Radarr + qBitorrent all in one for simplicity

3) Wireguard VPN + Proton VPN: If the VPN ever go down, the entire container network must stop (IPTables) so my home IP isn't leaked.

After 3 nights I got everything working and running 24/7, but it required a lot of review so it can be managed 10 years down the road instead of WTF is this???

There were silly mistakes that make you question "Why am I even using this tool??" but then I remember, Google and search engines are dead. It would have taken me weeks to get this done otherwise, AI tools speed that process by fetching the info I need so I can put them together.

I use AI purely to replace the broken state of search engines, even Brave and DuckDuckGo, I know what I am asking it, not just copy/paste and hope it works.

I have colleagues also into IT field whose the company where they work are fully AI, full access to their environment, they no longer do the thinking, they just press the button. These people are cooked, not just because of the state of AI, if they ever go look for another job, all they did for years was press a button!!

OK. Top AI labs have people using llms for 100% of their code. Enjoy writing by hand tho

I am still fascinated by how convincing the AI slop can be. I saw way too much code and documentation which made no sense. But it's often not obvious. I read it, I don't get it, I read it again, am I just stupid? I can grab some threads from it, but overall, it just doesn't make sense, it doesn't click for me. And that's when I often realize, it doesn't click, because it's a slop. It's obvious in pictures (e.g., generate a picture of a bike with labels). But in code? It requires more time to look at it than to actually write it. So it just slips reviews, it sometimes even works as it should, but it's damn hard to understand and fix it in the future. Until eventually, nothing can fix it.

For the record, I use AI to generate code but not for "vibecoding". I don't believe when people tell me "you just prompt it badly". I saw enough to lose faith.

I feel vindicated by this article, but I shouldn't. I have to admit that I never developed the optimism to do this for two years, but have increasingly been trying to view this as a personal failing of closed-mindedness, brought on by an increasing number of commentators and colleagues coming around to "vibe-coding" as each "next big thing" in it dropped.

I think the most I can say I've dove in was in the last week. I wrangled some resources to build myself a setup with a completely self-hosted and agentic workflow and used several open-weight models that people around me had specifically recommended, and I had a work project that was self-contained and small enough to work from scratch. There were a few moving pieces but the models gave me what looked like a working solution within a few iterations, and I was duly impressed until I realized that it wasn't quite working as expected.

As I reviewed and iterated on it more with the agents, eventually this rube-goldberg machine started filling in gaps with print statements designed to trick me and sneaky block comments that mentioned that it was placeholder code not meant for production in oblique terms three lines into a boring description of what the output was supposed to be. This should have been obvious, but even at this point four days in I was finding myself missing more things, not understanding the code because I wasn't writing it. This is basically the automation blindness I feared from proprietary workflows that could be changed or taken away at any time, but much faster than I had assumed, and the promise of being able to work through it at this higher level, this new way of working, seemed less and less plausible the more I iterated, even starting over with chunks of the problem in new contexts as many suggest didn't really help.

I had deadlines, so I gave up and spent about half of my weekend fixing this by hand, and found it incredibly satisfying when it worked, but all-in this took more time and effort and perhaps more importantly caused more stress than just writing it in the first place probably would have

My background is in ML research, and this makes it perhaps easier to predict the failure modes of these things (though surprisingly many don't seem to), but also makes me want to be optimistic, to believe this can work, but I also have done a lot of work as a software engineer and I think my intuition remains that doing precision knowledge work of any kind at scale with a generative model remains A Very Suspect Idea that comes more from the dreams of the wealthy executive class than a real grounding in what generative models are capable of and how they're best employed.

I do remain optimistic that LLMs will continue to find use cases that better fit a niche of state-of-the-art natural language processing that is nonetheless probabilistic in nature. Many such use cases exist. Taking human job descriptions and trying to pretend they can do them entirely seems like a poorly-thought-out one, and we've to my mind poured enough money and effort into it that I think we can say it at the very least needs radically new breakthroughs to stand a chance of working as (optimistically) advertised

> It was pure, unadulterated slop. I was bewildered. Had I not reviewed every line of code before admitting it? Where did all this...gunk..come from?

I chuckled at this. This describes pretty much every large piece of software I've ever worked on. You don't need an LLM to create a giant piece of slop. To avoid it takes tons of planning, refinement, and diligence whether it's LLM's or humans writing it.

Looking for solo devs testing AI continuation tool - DM me

Opus 4.5 is maybe 10% better than GPT 3.5. It's a total joke and these AI lab CEOs should literally be put in prison with Bernie Maddoff

The author makes it sound like such a binary choice, but there's a happy middle where you are having AI generate large blocks of code and then you closely supervise it. My experience so far with AI is to treat it like you're a low-level manager delegating drudgework. I will regularly rewrite or reorganize parts of the code and give it back to the AI to reset the baseline and expectations.

AI is far from perfect, but the same is true about any work you may have to entrust to another person. Shipping slop because someone never checked the code was literally something that happened several times at startups I have worked at - no AI necessary!

Vibecoding is an interesting dynamic for a lot of coders specifically because you can be good or bad at vibecoding - but the skill to determine your success isn't necessarily your coding knowledge but your management and delegation soft skills.

Google Maps completely and utterly obliterated my ability to navigate. I no longer actively navigated. I passively navigated.

This is no different. And I'm not talking about vibe coding. I just mean having an llm browser window open.

When you're losing your abilities, it's easy to think you're getting smarter. You feel pretty smart when you're pasting that code

But you'll know when you start asking "do me that thingy again". You'll know from your own prompts. You'll know when you look at older code you wrote with fear and awe. That "coding" has shifted from an activity like weaving cloth to one more like watching YouTube.

Active coding vs passive coding

Good luck finding an employer that lets you do this moving forward. The new reality is that no one can give the estimates they previously gave for tasks. \

"Amazingly, I’m faster, more accurate, more creative, more productive, and more efficient than AI, when you price everything in, and not just code tokens per hour."

For 99.99% of developers this just won't be true.

I read that people just allow Claude Code free rein but after using it for a few months and seeing what it does I wonder how much of that is in front of users. CC is incredible as much as it is frustrating and a lot of what it churns out is utter rubbish.

I also keep seeing that writing more detailed specs is the answer and retorts from those saying we’re back to waterfall.

That isn’t true. I think more of the iteration has moved to the spec. Writing the code is so quick now so can make spec changes you wouldn’t dare before.

You also need gates like tests and you need very regular commits.

I’m gradually moving towards more detailed specs in the form of use cases and scenarios along with solid tests and a constantly tuned agent file + guidelines.

Through this I’m slowly moving back to letting Claude lose on implementation knowing I can do scan of the git diffs versus dealing with a thousand ask before edits and slowing things down.

When this works you start to see the magic.

I wish more critics would start to showcase examples of code slop. I'm not saying this because I defend the use of AI-coding, but rather because many junior devs. that read these types articles/blog posts may not know what slop is, or what it looks like. Simply put, you don't know what you don't know.

You can do both. It's not binary.

You'll never find a programming language that frees you from the burden of clarifying your ideas.

Relevant xkcd: https://xkcd.com/568/

Even if we reach the point where it's as good as a good senior dev. We will still have to explain what we want it to do.

That's how I find it most helpful too. I give it a task and work out the spec based on the bad assumptions it makes and manually fix it.

The impression I get from the article is of a need to develop better prompts and/or break them down more

It took me about two weeks to realise this. I still use LLMs, but it's just a tool. Sometimes it's the right tool, but often it isn't. I don't use an SDS drill to smooth down a wall. I use sandpaper and do it by hand.

One thing that's consistent with AI negative/doesn't work/is slop posts: they don't tell you want models they are using.

On the one hand, I created vibe coded a large-ish (100k LOC) C#, Python, Powershell project over the holidays. The whole thing was more than I could ever complete on my own in the 5 days it took to vibe code using three agents. I wrote countless markdown 'spec' files, etc.

The result stunned everyone I work with. I would never in a million years put this code on Github for others. It's terrible code for a myriad reasons.

My lived experience was... the task was accomplished but not in a sustainable way over the course of perhaps 80 individual sessions with the longest being multiple solid 45 minute refactors...(codex-max)

About those. One of things I spotted fairly quickly was the tendency of models to duplicate effort or take convoluted approaches to patch in behaviors. To get around this, I would every so often take the entire codebase, send it to Gemini-3 Pro and ask it for improvements. Comically, every time, Gemini-3-Pro responds with "well this code is hot garbage, you need to refactor these 20 things". Meanwhile, I'm side-eying like.. dude you wrote this. Never fails to amuse me.

So, in the end, the project was delivered, was pretty cool, had 5x more features than I would have implemented myself and once I got into a groove -- I was able to reduce the garbage through constant refactors from large code reviews. Net Positive experience on a project that had zero commercial value and zero risk to customers.

But on the other hand...

I spend a week troubleshooting a subtle resource leak (C#) on a commercial project that was introduced during a vibe-coding session where a new animation system was added and somehow added a bug that caused a hard crash on re-entering a planet scene.

The bug caused an all-stop and a week of lost effort. Countless AI Agent sessions circularly trying to review and resolve it. Countless human hours of testing and banging heads against monitors.

In the end, on the maybe random 10th pass using Gemini-3-Pro it provided a hint that was enough to find the issue.

This was a monumental fail and if game studios are using LLMs, good god, the future of buggy mess releases is only going to get worse.

I would summarize this experience as lots of amazement and new feature velocity. A little too loose with commits (too much entanglement to easily unwind later) and ultimately a negative experience.

A classic Agentic AI experience. 50% Amazing, 50% WTF.

The title alone reads like the "digging for diamonds" meme.

2006: "If I can just write the specs so that the engineer understands them it will write me code that works."

2026: "If I can just write the specs so that the machine understands them it will write me code that works."

Rants like this are - entirely correct in describing frustration - reasonable in their conclusions with respect to how and when to work with contemporary tools - entirely incorrect in intuition about whether "writing by hand" is a viable path or career going forward

Like it not, as a friend observed, we are N months away a world where most engineers never looks at source code; and the spectrum of reasons one would want to will inexorably narrow.

It will never be zero.

But people who haven't yet typed a word of code never will.

He might be coding by hand again, but the article itself is AI slop

Claude Code slOpus user. No surprise this is their conclusion.

two years of vibecoding experience already?

his points about why he stopped using AI: these are the things us reluctant AI adopters have been saying since this all started.

Good luck. I haven't written a single line of code since 6 month ago

k

This bubble is going to crash so much harder than any other bubble in history. It's almost impossible to overstate the level of hype. LLMs are functionally useless in any context. It's a total and absolute scam.

I vibe coded for a while (about a year) it was just so terrible for my ability to do anything, it started becoming recurring that I couldn't control my timelines because I would get into a loop where I would keep asking AI to "fix" things I didn't actually understand and had no mental capacity to actually read 50k lines of LLM generated code compared to if I had done it from scratch so I would keep and keep going.

Or how I would start spamming SQL scripts and randomly at some point nuke all my work (happened more than once)... luckily at least I had backups regularly but... yeah.

I'm sorry but no, LLMs can't replace software engineers.

[dead]

[dead]