AI doesn't generate working products, that's still your job

I'm about to throw away multiple months of LLM generated code for one of my side projects. I was really careful writing design specs and it wasn't even a new code base the LLM worked on, but still after several months of AI changes I feel my code degraded more and more into a subtle mess. Hard to explain, each individual change looked good and logical and on the surface the codebase looks fine, but looking at the whole picture everything is subtly wrong in multiple ways. The same goes for where I used AI for existing commercial code bases. I would love to have AI write production ready software for me, but it's just not there yet, there simply are things that good programmers and architects do that cannot be captured by the training loop of current generation LLMs.

I notice the same pattern when using LLMs to write longer text like reports or scientific papers, individually each section they write makes sense but overall the whole document feels off in a hard to describe way. I think it's where you can see the difference between human intelligence and whatever it is LLMs have, it's not the same thing. We are much slower and less able on the small scale but seems we can do some higher level reasoning that is still impossible for LLMs. That always becomes clear when you point an LLM at an obvious flaw it produced and it goes "You are absolutely right!" as if it's obvious in hindsight but when running multiple "Please look for issues" iterations it would never have spotted the issue by itself.

That said I think it will be absolutely fine writing a simple CRUD app for you e.g. using some popular JS framework, Tailwind for styling and a regular ORM, there's more than enough training data available for these things. But then again such software could be purchased before already e.g. as a SaaS template, I don't think LLMs are so revolutionary here, they just replace the template (but to be honest a good hand-written SaaS boilerplate is probably still better than a vibe coded one).

The test is simple: have we seen great new products or improvements in the products we use over the past 12,24,36 months?

The only great new product I’ve used is my LLM of choice, and those labs seem to be hiring more humans than ever.

Maybe it’s true that Claude only just got good enough and that 12 months from now our day to day lives will be way better thanks to LLM-driven product improvements/breakthroughs.

My bet is that 12 months from now we will still have no great improvements and the claim will be “LLMs only got good enough in Feb 2027 so you can’t judge anything yet!”

I have two different experiences with LLMs.

First one is that I have vibe coded two different projects for work, one is a slack plugin which basically pushes alerts to a channel based on a people roaster and another one is a gmeet plugin to add a talking timer for each participant in the meeting. I used Opuse 4.6 and both were written with a node backend and I actually don't have a good understanding on how it works, but both works without any issue and are deployed in gcp. However, it was not a one shot prompt, but a very detailed step by step plan created for both apps and then executed including adding tests. Both of these apps are used for as internal team tools and we used to pay 20$ per person (back then the team was 5 people, but now it has grown) for the slack plugin before and after we built our own version of it, now it's just 0.07$ per month and that's the gcp infra cost.

Second one in using LLMs more like a coding monkey for work. I design the architecture, discuss it with my teammates, we nitpick and refine the approach and agree on how it should be implemented and then we create detailed JIRA tickets and feed these tickets to LLM (in this case again Opus). However, again first it must create a detailed implementation plan and only after it was reviewed and approved by an engineer it is being implemented.

If someone wants a quick working MVP, then I think the first option is the best to even test if it's possible to have a proof of concept. However, if someone wants to build a long lasting product, then throwaway that MVP and do a proper plan thinking about scalability and clean architecture from the start and use LLM as a code monkey. In my experience LLMs are still pretty bad at making better architecture and clean code decisions that is maintainable by humans in the long run.

When you have built your working product try this prompt:

- Review the codebase is it production ready? I'm selling it for $1million dollars can it meet that standard.

Then cry as the ai reveals that it didn't actually do anything close to what it said it did. I call this my million dollar prompt, as in it teaches you just how much you are being fooled.

I find the base logic of this post flawed - it can make a prototype, but what about everything after the prototype? Well, um, then you work on those things too? It seems like the premise of articles like this assume that using AI means whatever you can one-shot from a four line prompt. There are obviously a lot of issues with it, but this just sounds like uncritical self-justification rather than any fundamental insight.

The litmus test is this: do you enjoy consuming AI-generated stuff?

I don’t. Whether it’s written text, or video, audio, restaurant menus, clothing pictures, documentation, airport control, ads…

I do think there’s value in LLMs but as a sort of better search engines and q/a machines.

There's going to be plenty of work helping other companies make some sense of their vibe coded efforts. The value of individual projects might decrease, but there will be a lot more of them. And without help they won't actually work out all that well.

I talked to a company that does not employ software engineers that were doing some things with Claude Code a few weeks ago. Insightful comment: I want that person to do what I hired them to do, not mess around with code. What they were trying to do was a bit out of their comfort zone and they were smart enough to realize it.

There is going to be a lot more of this. What's very real is that companies selling one size fits all products to others are going to have a much harder time selling because everybody is going to expect a thing tailored to them because they now can. Delivering those things is still going to be work that needs to be done. A lot of work actually. People with experience building things with their own hands have an advantage. And if those people also understand the domain in which they are trying to do stuff, that's a double advantage.

Like always, most people haven't got a clue about what they actually need. Figuring out what people need (consulting) and then delivering it has always been the job. But you might be able to take on a few more customers now. There won't be a shortage of those once people figure out software just got cheaper.

For some strange reason, most of the software I use is getting worse, not better.

I think we have played this game long time ago. If products were a question of a single request then outsourcing companies would dominate over product ones.

I think a lot of product development happens in the itearations after the intial prototype/MVP and so on. It is not only the technical aspect to it, you need to spend time on a problem deeply understand what are the root causes of pains and address them in your product, both from UX and also from technical perspective.

People were able to "prompt" a product even before to an outsourcing company, but they'd rather pay the fee to a product company because of the expertese they have gained through out the years and all the users they've spoken to.

I am very product focused with my projects. I have Claude write 100% of the code but I challenge its suggestions and make damn sure there are ways for it to verify functionality and correctness. I don't read much of the generated code but am adamant that there are tests: unit, integration and (if possible) against other implementations. And I care a LOT about performance.

So far (last 6-7 months) I've built tons of stuff in my spare time: A pdf generator lib, a scheme implementation (R5RS and R7RS) with AOT compilation, a screenplay editor, a code editor, a ripgrep-like lib/engine/cli tool for fast search in a workspace, a markdown parser, a Fountain (screenplay) parser, a lib for dealing with updating apps, tooling for finding duplicate code and generating codemaps - and much more.

It's been an absolute ride.

The fear in most people is not of losing the job, but of losing their value in the market as ai raises the floor of capabilities of other people competing for the same job.

I think this is intuitively true, and I've noticed this even as someone who doesn’t have an engineering background.

In my LLM coding experience, I’ve had this happen numerous times, for instance when building a card game.

The LLM does a great job for a while, but adding special event cards becomes impossible because it imported a standard 52 card deck library instead of having a flexible data model with card objects.

I suppose this is knowable and you could tell an LLM to do this from the beginning. It's just that when you view making a game (or any piece of software) as just a throwaway thing and don't start with deep thought about the implementation as an experienced engineer might, you don't think about this.

I think part of the issue with AI-generated writing, code, or anything else, is that it robs us of the thinking that used to be baked into the process of making stuff.

For my game, if I had to build it from scratch, I surely would've sketched out the kind of data model it requires to not waste my time.

I do think some of this stuff is overblown though. It's true that LLMs don't create production-grade stuff, but not all software needs to be scalable, fast, and easily maintainable.

This might be required for infrastructure or apps designed to (hopefully eventually) be used by millions.

But it's not true for a minor utility, like if I want to build a meal-planning app for my family. I don't care if the app is the fastest it can be or if the data model could eventually support a feature to configure dietary preferences and allergies or to plan the meals for Google's tens of thousands of employees.

There was a viral article a few years ago around how software could be like a home-cooked meal. And AI enables exactly that. A home-cooked meal doesn't require culinary perfection, but to feed the family and, maybe more importantly, be a gift of labor to the other person.

A half-hearted and timid post. It’s very obvious it was written to avoid criticism.

I think the author started writing this on a whim and couldnt bring it to a proper conclusion. What i cant understand is how it managed to get such a high points on hn. Because the piece is completely stale—neither praise nor criticism. The author’s own thoughts are so generic that we hear them every single day in our daily lives, and especially on Hacker News, in the back-and-forth between the “Coddites” and the “Vibers” crowd.

My indirect take is that, since AI coding is already shrouded in uncertainty, there’s no need for it to remain in this kind of fog—this article will lose all relevance within five years and end up proving the author wrong.

I think of it this way. If AI could build the product alone, then why would it ever be worth more than the tokens you spent on it? I think this would hold true 99% of the time. It's literally like asking someone "Can you pay me $1m for new gadget? I hired this other dude for $20p/h and he made it in a week". It simply doesn't add up.

The 80/20 rule still stands.

I agree that the people who vibe code driven by the fear of being left behind are in a sort of self fulfilling loop.

The more code is generated without understanding, the less likely it will be maintained and it will be left behind the audited code in quality and in usefulness.

It's so easy to get into AI that the only thing we can be left behind is personal experience or learning. But jumping in and spending on claude to vibe up a SaaS...pretty much anyone can do that now.

AI only does what it is instructed to do. Without deep domain knowledge, results produced from simple prompts alone cannot be turned into production-ready products. In reality, creating detailed prompts, conducting continuous reviews, and providing iterative feedback after the prototype stage often takes even more time than building the prototype itself.

I build reai.no, an accounting system in Norway. I can say with 100% certainty that if you don't know what you're doing. Then it will still be a mess. I throw away 90% of the code that other devs come with and also from my own prompts.

I also tend to close PRs if I'm not sure it is the best solution and just ask them to start from scratch since the second time you implement something (unless you do it completely blindly) probably made you realise how you could make it simpler :)

I also focus a lot on teaching devs domain knowledge. Actually learning accounting so they can more independently understand how to build something "correctly".

Anyone who thinks this way has completely lost sight of what it means to use generative AI for software projects, namely, the concept of a tool, however sophisticated it may be, but still just a tool. The goal of a project can be anything from a prototype to a finished product, and using AI tools does not change what you want to achieve as the final result.

I’ll add that you still need the will and the care to drive it towards an useful product. AI still not magically generate useful products if you don’t ask it to do it and prune the results until it approaches what you desired to create.

"AI has dramatically accelerated the path to a first working version. It has not shortened the distance between a first working version and something production-grade." - Anuradha Weeraman

I like that one “ They understand what they're asking the model to produce. They review generated code with the same critical eye they'd apply to a junior engineer's pull request. They bring architectural thinking to the conversation, not just feature descriptions. They know when to push back on what the model suggests.” I use AI randomly recently and more and more see it as fantastic poc tool , also it’s really good at comparison existing tools and making some raw material for analysis

This begs the question of what the fundamentals really are. There are a bajillion bootcamps and learn-x-in-a-weekend books out there, most of which seem to focus on getting you familiar with basic syntax rather than teaching the how and why.

If memorising syntax and a standard library are no longer differentiators, then what exactly are you supposed to learn?

I wrote something very related to this: https://pgaleone.eu/ai/2026/07/26/use-your-brain/

I'm tired of this "X was never the hard part" meme when in fact X (this time: prototyping) was in fact difficult.

Human doesn't write blog post, that's still Claude's job...

Agentic Engineer: "How'd you solve the icing problem?" Vibe Coder: "Icing problem?"

It's funny this post was AI generated.

Most of this piece reads like the Claude output I have to read after every prompt, cleaned up with an /elegant-writing skill or something. I'm so used to skimming text in this voice, it's hard to pay attention to this.

I honestly do not understand why people do this for writing that carries their signature, essentially. Do you want people to associate your name with skimmable fluff? We can talk to each other directly, please. The machine is helpful but it doesn't have to mediate every human interaction ever.

Before: most code programmers write is thrown away. Most products fail.

Now: most code LLMs write is thrown away. Most products fail.

Knowing what to build and how at the high level (architecture and algorithms) has always been the most important part of programming, not banging out code. A 2X to 10X programmer isn’t that way because they bang code faster. They’re that way because they throw away less. Now that programmer wastes less LLM tokens.

A big part of LLM appeal is that most code is not artisan craft designed to work beautifully and last forever to be part of something that will also last like a compiler for a popular language or a kernel. Most code is speculative and/or ephemeral. Much of it is also very boring.

Yeah but back then we need 10 engineer, now we need only maybe 2 - 4

I’ve been a Lead Engineer in a prior life, and also led many offshore teams that executives and product managers thought were “bad”

I have great results with AI assisted code bases and development

I am the harness

Can we please not share things that are 100% AI written here, at least without attribution? This one struck me as such, and Pangram (which I believe has a pretty low false positive rate) calls it at literally 100%.

If you can’t write your own words, it’s no wonder you can’t get the software past prototype phase.

Clear, useful, done

Blah blah. Software engineering is now prompt engineering. I'm not sure what the point of this article is.

> Why this matters

AI doesn't write articles, that's still your job.

I've seen too many similar posts on Hacker News. From 2025 to 2026, I've seen countless articles with titles like 'The Prototype Isn't the Product.'

I think these are defensive mechanisms, a kind of lullaby for the Gen AI era.

Why is this discourse endlessly reproduced? In my view, it's because the industry is still searching for a new methodology to control the waterfall of Gen AI code. The cognitive dissonance that results is being resolved by relying on vague personal virtues like 'craftsmanship,' 'fundamentals of computer science,' and 'human judgment.'

If the goal is to review Gen AI code in its entirety, the way an engineer would review a PR, then honestly, I don't see the point of using Gen AI in the first place.

Yes, models lack judgment and only do pattern matching. But lately, I've noticed that in closed systems, Gen AI often produces more logically coherent code than humans do. If that's the case, maybe programmers should shift toward designing closed systems where algebraic data types ensure the program works correctly.

Because using Gen AI means you're committing to codebases that go beyond individual cognitive limits. Once you start using Gen AI code, there's a subtle mismatch with human written code, a fundamental impedance mismatch, like the one between ORM and SQL.

In that sense, I honestly don't know.

The arguments that have been repeated for nearly a year all sound basically the same. But when I look closer, this isn't Gen AI era coding. It's just old era methodology with 'human' swapped out for 'AI.' If the subject changes, the methodology should change too.

Looking at the countless repetitive posts on HN, it shows what HN programmers are afraid of. They're afraid of the destruction of their overall meta-methodology.

All the arguments being made now are about how to become a good senior engineer in the old days.

But is that analogy really appropriate for the volume of code AI is generating?

The amount of code being generated is exploding. The amount of complexity is exploding. Responsibility is becoming unclear. These aren't issues of individual skill. Saying that drivers just need to be more careful when traffic increases is bad road policy. The core is that the roads and signaling systems need to change.

A new subject requires a new methodology.

In that sense, I think the recent post from Jane Street is more like a new solution. Of course, ADT doesn't guarantee that modeling always holds either.

So honestly, I don't know. When I look at HN, it seems like all I see is what social signals people are most anxious about.

Another take . If a (my) product is easy for AI to work with - I call it LLMable - that’s good metric or sign I move in the right direction . AI just guidelines me in that sense …

Someone please tell this to my clients.

> An experienced engineer using modern AI tools can move at a pace that would have been unimaginable five years ago.

I dunno sometimes I think I should have sticked with a simpler solution coded by hand with more tradeoffs, than trying doing more and spend days back and forth in an endless feedback loop. Or fighting back the Agent that is more than happy to over produce.

IMO the problem is not the single developer using more agentic tooling, it's the whole work chain, who reviews your changes use agentic tooling assistance and over produce a lot of feedback and you're back with the clanker making many decisions that just drains you at the end of the day. I miss the times where we released many more simple things sith many more tradeoffs and business decisions

This is a greatly written article. Thanks

I have always said with AI there will always be new jobs.

This is becoming more and more true every day.

I have 3+ years of experience working on projects that integrate LLMs into the "old" approach to building software. Overall, whenever clients used LLM to analyse inputs without expecting them to be accurate, we were getting decent results. Not so much on the generative side, where LLMs are still producing crap output. This is on projects where humans wrote most of the code.

Things look way worse when working with vibed code. Over the last twelve months or so I encountered a number of issues with code and tests given to me by people with little or no coding experience claiming that this is a finished product and expecting me to "productionise it" (their words, not mine). Because they believe in LLMs like religious zealots and have no idea what programmers with actual experience of writing code are talking about there is a breakdown of communication and a lot of misunderstanding. On my latest project I was given a zip archive and asked to "make it work" by someone who calls themselves a "software architect" but has no idea how software development works. That person was surprised when we asked for a git repository, requirements, and design. None were given and we were told to use Claude to explain what the code is supposed to do. When we pressed for requirements the "architect" sent us a 4-page list of requirements based on the LLMs analysis of the contents of the zip file. It was so vague that it could apply to any project. Similarly, the architect vibed tickets in Jira and we had to clean them up as well, because of their vaugness and repetition or generic requirements. The three of us spent two months turning this turd into a piece of software with working tests and working implementation before we were told a PM will be assigned to our team and we will have to explain to him how the software works and what the requirements are. I am no longer on that project. I have had enough.

Another client forced addition on an AI PR reviewer. After initial excitement every dev on a 200+ team started ignoring it, because the fixes it suggests actually break code.

The marketing around LLMs convinced idiots that they are capable of producing software and that the greatest enemy of delivery are actual software developers with experience of delivering working software. The lowest point must be the recent series of ads I keep seeing on YouTube in which one character gets overly excited because he vibed a to do app... Every OS comes with one and if you don't like them, there are plenty of free and paid alternatives that cost less and work better than "your" vibed app.

I can't wait for the VC money to run out and the LLM madness to go to hell.

I can't tell if this is insightful or copium.

AI doesn’t do shit, be honest.

[flagged]

[flagged]

[dead]