Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

“Vibe Coding” vs. Reality

cendyne.dev

Post reply on HN
Print view View original

141–150 of 312 posts

Re: “Vibe Coding” vs. Reality

#141

Post by jocoda »

falkensmaize wrote: post #98
jocoda wrote: post #80

My, very limited experience with LLM assisted coding is that it depends... For basic frameworks done in something like Python it is very good, but not perfect, yet. But the iteration cycle to get to where you want to be is still faster than doing the whole job manually and I see this as a big win. For more esoteric fast changing languages/frameworks it has me chasing my tail in a chain of code updates where each fix…

"But it will get better, a lot better." I see statements like this a lot when talking about AI in general. People seem to think it is a foregone conclusion that no limit to LLM model improvement and capability exists. What causes you to believe this and what evidence do you have to back it up?

Really? Opinion, based on the fact that there are basic improvements that can be implemented on what we have now, using the skills that we have now. If you don't agree, that's ok.

Now, about your comprehension skills, where is there any mention on my part of there being 'no limit'? In fact I go as far as to speculate on at least one.

Re: “Vibe Coding” vs. Reality

#142

Post by DonHopkins »

musicale wrote: post #7

"ever since I started to share how I built my SaaS using Cursor" random thing are happening, maxed out usage on api keys, people bypassing the subscription, creating random shit on db as you know I'm not technical so this is taking me longer that usual to figure out - (leo, 2025)

What does "I'm not technical" actually mean?

It sounds like a euphemism for:

I don't want to work hard.

I don't care about the details.

I don't want to learn new things.

I want somebody else to do my homework.

I don't want to put in the effort it takes to succeed.

I cheated my way through school instead of learning from classes.

I've always had everything handed to me on a silver platter, and I expect that to continue.

I want to put more effort into yapping on Twitter and getting followers that actually doing any work.

Re: “Vibe Coding” vs. Reality

#143

Post by oblio »

id00 wrote: post #132
jxjnskkzxxhx wrote: post #95

Making the arguing that these tools have flaws seem like a losing battle. Soon those flaws will be fixed[1] and youll have to find new flaws to complain about. Eventually hopefully you'll realize that you just don't like feeling displaced. [1] it's unbelievable what a difference in quality 1 year made for chat gpt

Why are you so certain that flaws will be fixed? Seems like there is a giant leap between a machine spewing words based on probability and actual deep understanding of the code it's suppose to write

Until this knowledge is widespread, a lot of devs better hold on to their current good jobs.

Re: “Vibe Coding” vs. Reality

#144

Post by bobxmax »

pton_xd wrote: post #12
bobxmax wrote: post #4

Earlier quoted context omitted.

I work at a company relatively well-known in Startup-land and I've replaced a product team which had 9 devs 2 years ago with 2 devs with AI. Devs are just coping so hard around LLMs its hard to watch. OTOH the few engineers who have embraced it are excelling.

You likely should have replaced those devs years ago. Kudos to LLMs helping you figure that out though.

Nope. They were talented devs who all (well, most) landed in great companies after.

We just didn't need them anymore because LLMs and tools like cursor are insanely good.

Re: “Vibe Coding” vs. Reality

#145

Post by FpUser »

TeMPOraL wrote: post #103
matsemann wrote: post #75

Earlier quoted context omitted.

The market where I live is far larger than it was 15-20 years ago. So both have grown, the outsourcing didn't kill local as predicted.

The growth of demand for software development is absurd and heavily skews people's expectations. It won't last forever.

>" It won't last forever."

And who cares if it is true? So far programming is one of very few professions when person can set themselves for life in a relatively short period of time. When / if it is gone there will be something else. I have few friends who'd switched to be a handyman. They are doing great from what I see.

Re: “Vibe Coding” vs. Reality

#146

Post by TeMPOraL »

jmull wrote: post #126
MarkMarine wrote: post #92

This is the go community saying a computer will never best human go players. We already have examples of a model finding more performant sorts [0], given the right incentives and time, and the right system for optimizing (LLMs trained on “average code” probably aren’t it) the computer will best us at creating things for the computer. Is “vibe coding” real today? Not in my experience, with even Claude code. My hand ha…

Well… to be frank, this is someone not reading TFA. The article is pointing out real limitations of vibe coding today (which you appear to agree with). It does suggest AI coding won’t be viable in the future. You should probably update your comment to say something like, “spot on”.

Nah, the article is generalizing from a single sample of current state, ignoring the larger trajectory (that, for AI coding, went from sci-fi to reality in two years).

Sure, the tools aren't perfect, so there's some art to using them now - which the author of TFA seems to be unaware of. Take for example:

> You cannot ask these tools today to develop a performant React application. You cannot ask these tools to implement a secure user registration flow. It will choose to execute functions like is user registered on the client instead of the server.

Of course you can ask them to do it. You can literally ask them to "write better code" (yes, with this exact phrase; see [0]), and you'll get better code. More performant, or more secure - it depends on specifics of the case. Or, you can ask them specifically to focus on security or performance, and you will typically get improvements on those axis.

That's today. Next year, people will know how to prompt the models away from most common failure modes, and the models themselves will be further trained to avoid those same failure modes. In bringing specific problems up, TFA isn't making a convincing argument against future of "vibe coding" - it's literally helping in making it happen.

--

[0] - https://minimaxir.com/2025/01/write-better-code/

Re: “Vibe Coding” vs. Reality

#147

Post by the_snooze »

tokioyoyo wrote: post #140
falkensmaize wrote: post #98

Earlier quoted context omitted.

"But it will get better, a lot better." I see statements like this a lot when talking about AI in general. People seem to think it is a foregone conclusion that no limit to LLM model improvement and capability exists. What causes you to believe this and what evidence do you have to back it up?

Because compared to a year ago, it's much better. Compared to two years ago, it almost didn't exist. Compared to three years ago, nobody was actually talking about it.

https://xkcd.com/605/

Re: “Vibe Coding” vs. Reality

#148

Post by arrowsmith »

margalabargala wrote: post #120
MarkMarine wrote: post #92

This is the go community saying a computer will never best human go players. We already have examples of a model finding more performant sorts [0], given the right incentives and time, and the right system for optimizing (LLMs trained on “average code” probably aren’t it) the computer will best us at creating things for the computer. Is “vibe coding” real today? Not in my experience, with even Claude code. My hand ha…

Where we are now, I wonder if is similar to the early days of compiled languages existing, back when people still somewhat commonly wrote assembly by hand and didn't trust compilers. Sure, things like Roller Coaster Tycoon exist, but but writing in a compiled language is so much faster, easier, and more broadly accessible than writing in assembly that compilers took over.

TIL that Rollercoaster Tycoon was written in Assembly.

“[Developer Chris] Sawyer wrote 99% of the code for RollerCoaster Tycoon in x86 assembly language for the Microsoft Macro Assembler, with the remaining one percent written in C.” - Wikipedia

What a lunatic.

Re: “Vibe Coding” vs. Reality

#150

Post by loloquwowndueo »

dr_dshiv wrote: post #131
MarkMarine wrote: post #92

This is the go community saying a computer will never best human go players. We already have examples of a model finding more performant sorts [0], given the right incentives and time, and the right system for optimizing (LLMs trained on “average code” probably aren’t it) the computer will best us at creating things for the computer. Is “vibe coding” real today? Not in my experience, with even Claude code. My hand ha…

Vibe coding is 100% real. Or maybe we should call it code vibing when there is no coding ability. But I just taught 18 professionals with no coding ability to build functional software. Their minds were blown

Wait until they have to maintain, debug or secure that software. You’ll see things really blow at that point.
Post reply on HN