AI Prototypes Are Easy, But Building Real Products Is Still Your Job
AI doesn't generate working products, that's still your job
I argue that while AI accelerates creating working prototypes, the hard work of building production-grade software remains unchanged. The real challenge is not writing syntax but exercising judgment on system design, security, and scalability. Relying solely on AI without a foundation in computer science leaves you unable to fix failures or scale systems. True engineering now means using AI as a force multiplier for deep knowledge rather than a replacement for understanding.
The engineers who will be left behind are not those who lack AI skills. They're the ones who use AI as a substitute for understanding, who vibe-code their way through systems they can't reason about, and then find themselves unable to fix what breaks.
- ThePhysicist
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 i […]
- HarHarVeryFunny
I prefer the article's own "The Prototype Isn't the Product" title, since that seems to better capture what's being discussed.
With AI, it can be ridiculously quick to vibe code throwaway prototypes and personal use apps where "seems to mostly work" is the quality criteria, but what remains harder and slower is software engineering - building things where quality and maintainability are critical.
There is much less discussion of this - we mostly see people wanting to show off some flashy demo they just vibe coded, not discussion of how useful AI was, or wasn't, in working on some large legacy codebase or whatever non-sexy non-trivial task their day-to-day professional work consists of.
You are not going to get a 6am sunday call at home because your vibe-coded 3-D game prototype stopped working, but you surely will if there's a bug in the 24x7 production system that was just updated.
- jaccola
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!”
- tim-projects
When you have built your working product try this prompt:
- Review the codebase is it production ready? I'm selling it for $1million dollars can it meet that standard.
Then cry as the ai reveals that it didn't actually do anything close to what it said it did. I call this my million dollar prompt, as in it teaches you just how much you are being fooled.
- sajithdilshan
I have two different experiences with LLMs.
First one is that I have vibe coded two different projects for work, one is a slack plugin which basically pushes alerts to a channel based on a people roaster and another one is a gmeet plugin to add a talking timer for each participant in the meeting. I used Opuse 4.6 and both were written with a node backend and I actually don't have a good understanding on how it works, but both works without any issue and are deployed in gcp. However, it was not a one shot prompt, but a very detailed step by step plan created for both apps and then executed including adding tests. Both of these apps are used for as internal team tools and we used to pay 20$ 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 wa […]
- kouunji
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.
- sdevonoes
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.
- FinnLobsien
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 s […]