The problem with vibe coding is more behavioral I think: the person more likely to jump in the bandwagon to avoid writing some code themselves is probably not the one thinking about long term architecture and craftsmanship. It’s a laziness enhancer.
Reading "couldn't" as, you would technically not be able to do it because of the complexity or intricacy of the problem, how did you guarantee that the change offered by the AI made proper sense and didn't leave out critical patterns that were too complex for you to detect ?
Your comment makes it sound like you're now dependent on AI to refactor again if dire consequences are detected way down the line (in a few months for instance), and the problem space is already just not graspable by a mere human. Which sounds really bad if that's the case.
There's a difference between not intellectually understanding something and not being able to refactor something because if you start pulling on a thread, you are not sure what will unravel!
And often there just isn't time allocated in a budget to begin an unlimited game of bug testing whack-a-mole!
My confidence in LLMs is not that high and I use Claude a lot. The limitations are very apparent very quickly. They're great for simple refactors and doing some busy work, but if you're refactoring something you're too afraid to do by hand then I fear you've simply deferred responsibility to the LLM - assuming it will understand the code better than you do, which seems foolhardy.
A lot of repetitive slight variations on the same easy to describe change sounds pretty good to ask an LLM to do quickly.
But if someone else were to do it for me I would gratefully review the merge request.
For me personally, the activation energy is higher when reviewing: it’s fun to come up with the solution that ends up being used, not so fun to come up with a solution that just serves as a reference point for evaluation and then gets immediately thrown away. Plus, I know in advance that a lot of cycles will be wasted on trying to understand how someone else’s vision maps onto my solution, especially when that vision is muddy.
Submitting LLM barf for review and not reviewing it should be grounds for termination. The only way I can envision LLM barf being sustainable, or plausible, is if you removed code review altogether.
What does it mean to have to review your own code as a separate activity? Do many people contribute code that they wrote but… never read?
> Submitting LLM barf
Oh right…
The concept and design were by that point iterated on, so it doesn’t happen that I need to rewrite a significant amount of code.
If you need an example, it's easy to add a debugging/logging statement like `console.log`, but if the coder committed and submitted the log statement, then they clearly didn't review the code at all, and there are probably much bigger code issues at stake. This is a problem even without LLMs.
If person A committed code that looks bad to person B, it just means person A commits bad code by the standard of person B, not that person A “does not review own code”.
Maybe it’s a subjective difference, same as you could call someone “rude” or you could say the same person “didn’t think before saying”.
If you can do it using an LLM in a few hours however, suddenly making your life, and the lives of everyone that comes after you, easier becomes a pretty simple decision.
AI is a sharp tool, use it well and it cuts. Use it poorly and it'll cut you.
Helping you overcome the activation barrier to make that redactor is great if that truly is what it is. That is probably still worth billions in the aggregate given git is considered billion dollar software.
But slop piled on top of slop piled on top of slop is only going to compound all the bad things we already knew about bad software. I have always enjoyed the anecdote that in China, Tencent had over 6k mediocre engineers servicing QQ then hired fewer than 30 great ones to build the core of WeChat...
AI isn't exactly free and software maintenance doesn't scale linearly
While that is true, AI isn’t going to make the big difference here. Whether the slop is written by AI or 6000 mediocre engineers is of no matter to the end result. One might argue that if it were written by AI at least those engineers could do something useful with their lives.
I’m very much able to understand the result and test for consequences, I wouldn’t think of putting code I don’t understand in production.
Not necessarily. It may have refactored the codebase in a way that is more organized and easier to follow.
> how did you guarantee that the change offered by the AI made proper sense and didn't leave out critical patterns that were too complex for you to detect ?
Perhaps extensive testing? Or a prayer.
Theres some fidelity loss but it works for text, because there's quite often so much redundancy.
However, I'm not sure this technique could work on code.
It only looks effective if you remove learning from the equation.
It's the wrong tool for the job, that's what it is.
I kind of view this use case as enhanced code linters
I quit my last very good job because I became so fed up with this situation. It was bad enough before the CTO started using LLMs. It was ABSURD after.
(This was a YC company that sold quickly after I quit, at a loss, presumably because they didn't know what else to do)
someone holding a hammer by the head and failing at getting the nail in doesnt mean a hammer is a bad tool for nailing
No part of what I said suggested the tool wasn't capable of being a useful tool.
It's effective on things that would take months/years to learn, if someone could reasonably learn it on their own at all. I tried vibe coding a Java program as if I was pair programming with an AI, and I encountered some very "Java" issues that I would not have even had the opportunity to get experience in unless I was lucky enough to work on a Fortune 500 Java codebase.
AI doesn't work in a waterfall environment. You have to be able to rapidly iterate, sometimes in a matter of hours, without bias and/or emotional attachment.
What do you mean? There is no difference between waterfall or agile in what you do during a few hours.
Are you being ironic?
Throw a big context window model like Gemini at it to document the architecture unless good documentation exists. Then use modify that document to drive development of new or modified code.
Many big waterfall projects already have a process for this - use the AI instead of marginally capable offshore developers.
Do you expect an incoming collapse of modern society?
That's the only case where LLM would be "not there anymore." Even if this current hype train dies completely, there will still businesses providing LLM interference, just far less new models. Thinking LLM would be "not there anymore" is even more delusional than thinking programmer as a job would cease to exist due to LLM.
Trying to get some third party hardware working with raspi
The hardware provider provides 2 separate code bases with separate documentation but only supports the latest one.
I literally had to force feed the newer code base into ChatGPT, and then feed in working example code to get it going, else it constantly reference the wrong methods.
If I just kept going Code / output / repeat it would maybe have stumbled on the answer but it was way off.
> Counterpoint: AI has help me refactor things where I normally couldn’t. Things like extracting some common structure that’s present in a slightly different way in 30 places, where cursor detects it, or suggesting potential for a certain pattern.
Recently, I was listening to a podcast about realistic real world uses for an LLM. One of them was a law firm trying to review details of a case to determine a strategy. One of podcasters (sp?) recoiled in horror: "An LLM is writing your briefs?" They replied: "No, no. We use it generate ideas. Then, we select best." It was experts (lawyers, in this case) using an LLM as a tool.
"Technology acts as an amplifier of human intentions"
...so, if someone is just doing a sloppy job, AI-assisted vibe coding will enable them to do it faster.
In any case a very rare and specific corner case you mention, a dev can go on a decade or two (or lifetime or two) without ever experiencing similar requirement. If it should be a convincing argument for almighty llm it certainly isnt.
You can have AI almost generated anything, but even AI has limited to understanding requirements, if you cannot articulate what you want very precisely, it's difficult to get "AI" to help you with that.
And it’s better in the long run.
Part of the reason is that the reporters are themselves not in the trenches coding to be skeptical of the claims they hear.