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

After months of coding with LLMs, I'm going back to using my brain

albertofortin.com

Post reply on HN
Print view View original

31–40 of 229 posts

Re: After months of coding with LLMs, I'm going back to using my brain

#31

Post by a7fort »

dev_l1x_be wrote: post #26

I think LLMs are great for generating the structure of your code. The only issue is that these models are amazing when you are navigating in very well documented, talked about, etc. subjects, and start to go off the rail when you are using somewhat esoteric things. The speed boost I get by generating Terraform and HTML, CSS, JS with Deepseek and Grok (sometimes asking one to review the others code) is pretty signific…

You're right and I will still use it, but only for more limited scopes. I've also cancelled my Claude subscription recently, but for different reasons - it doesn't have the "memory" feature that makes ChatGPT so much more worth it at the moment.

Re: After months of coding with LLMs, I'm going back to using my brain

#34

Post by JimDabell »

> I’ve never used Go or Clickhouse before

> I have no concept of Go or Clickhouse best practices.

> One morning, I decide to actually inspect closely what’s all this code that Cursor has been writing. It’s not like I was blindly prompting without looking at the end result, but I was optimizing for speed and I hadn’t actually sat down just to review the code.

> I’m defaulting to coding the first draft of that function on my own.

I feel like he’s learnt the wrong lesson from this. There is a vast gulf between letting an LLM loose without oversight in a language you don’t know and starting from scratch yourself. There’s absolutely nothing wrong with having AI do the first draft. But it actually has to be a first draft, not something you blindly commit without review.

> “Vibe coding”, or whatever “coding with AI without knowing how to code” is called, is as of today a recipe for disaster, if you’re building anything that’s not a quick prototype.

But that’s what vibe coding is. It’s explicitly about quick throwaway prototypes. If you care about the code, you are not vibe coding.

> There's a new kind of coding I call "vibe coding", where you fully give in to the vibes, embrace exponentials, and forget that the code even exists. […] It's not too bad for throwaway weekend projects, but still quite amusing. I'm building a project or webapp, but it's not really coding - I just see stuff, say stuff, run stuff, and copy paste stuff, and it mostly works.

— https://x.com/karpathy/status/1886192184808149383

He’s basically saying that vibe coding is a disaster after his experience doing something that is not vibe coding.

Re: After months of coding with LLMs, I'm going back to using my brain

#35

Post by llm_nerd »

jclardy wrote: post #8

I don't get the whole "all-in" mentality around LLMs. I'm an iOS dev by trade, I continue to do that as I always have. The difference now is I'll use an LLM to quickly generate a one-off view based on a design. This isn't a core view of an app, the core functionality, or really anything of importance. It's a view that promotes a new feature, or how to install widgets, or random things. This would normally take me 30-…

>I don't get the whole "all-in" mentality around LLMs

To be uncharitable and cynical for a moment (and talking generally rather than about this specific post), it yields content. It gives people something to talk about. Defining their personality by their absolutes, when in reality the world is an infinite shades of gradients.

Go "all in" on something and write about how amazing it is. In a month you can write your "why I'm giving up" the thing you went all in on and write about how relieved/better it is. It's such an incredibly tired gimmick.

"Why I dumped SQL for NoSQL and am never looking back" "Why NoSQL failed me"

"Why we at FlakeyCo are all in on this new JavaScript framework!" "Why we dumped that new JavaScript framework"

This same incredibly boring cycle is seen on here over and over and over again, and somehow people fall for it. Like, it's a huge indicator that the writer more than likely has bad judgment and probably shouldn't be the person to listen to about much.

Like most rational people that use decent judgement (rather than feeling I need to "all in" on something, as if the more I commit the more real the thing I'm committing to is), I leverage LLMs many, many times in my day to day. Yet somehow it has authored approximately zero percentage of my actual code, yet is still a spectacular resource.

Re: After months of coding with LLMs, I'm going back to using my brain

#36

Post by jacob019 »

VMG wrote: post #11

I get it and I see the same problems as the author. I'm working on a few toy projects and I am using LLM for 90% of it. The result is 10x faster than if I coded it "by hand", but the architecture is worse and somewhat alien. I'm still keeping at it, because I'm convinced that LLM driven code is where things are headed, inevitably. These tools are just crazy powerful, but we will have to learn how to use them in a way…

This is where they shine, for prototyping greenfield projects, but as the project gets closer to production that 10x erodes. You have to be really intentional about the architecture, fixing core design issues later can turn 10x into 0.1x.

Re: After months of coding with LLMs, I'm going back to using my brain

#37

Post by mritchie712 »

jclardy wrote: post #8

I don't get the whole "all-in" mentality around LLMs. I'm an iOS dev by trade, I continue to do that as I always have. The difference now is I'll use an LLM to quickly generate a one-off view based on a design. This isn't a core view of an app, the core functionality, or really anything of importance. It's a view that promotes a new feature, or how to install widgets, or random things. This would normally take me 30-…

How useful the various tools will be depends on the person and the problem. Take two hypothetical people working on different problems and consider if, for example, Cursor would be useful.

IF you're a:

* 10 year python dev

* work almost entirely on a very large, complex python code base

* have a pycharm IDE fine tuned over many years to work perfectly on that code base

* have very low tolerance for bugs (stable product, no room for move fast, break things)

THEN: LLMs aren't going to 10x you. An IDE like Cursor will likely make you slower for a very long time until you've learned to use it.

IF you're a:

* 1 year JS (react, nextjs, etc.) dev

* start mostly from scratch on new ideas

* have little prior IDE preference

* have high tolerance for bugs and just want to ship and try stuff

THEN: LLMs will to 10x you. An IDE like Cursor will immediately make you way faster.

Re: After months of coding with LLMs, I'm going back to using my brain

#39

Post by a7fort »

reconnecting wrote: post #5

Off-topic: may I ask, why PHP + MySQL is no longer considered suitable to you? It's hard to say without specifics, but simply upgrading from MySQL to PostgreSQL without rewriting the PHP codebase in Go might resolve most of the potential issues.

It's two separate issues:

1) I do a lot of scraping, and Go concurrency + Colly has better performance

2) My DB size is exploding and I have limited budget, and it looks like CH is so much better at compressing data. I recently did a test and for the same table with same exact data, MySQL was using 11GB, ClickHouse 500MB

Re: After months of coding with LLMs, I'm going back to using my brain

#40

Post by rco8786 »

dmazin wrote: post #2

This rings true to me. I still use LLMs heavily . However, I now follow two rules: * Do not delegate any deep thought to them. For example, when thinking through a difficult design problem, I do it myself. * Deeply review and modify any code they generate. I go through it line-by-line and edit it thoroughly. I have to do this because I find that much of what they generate is verbose, overly defensive, etc. I don't ca…

> Deeply review and modify any code they generate. I go through it line-by-line and edit it thoroughly

This is the issue, right? If you have to do this, are you saving any time?

Post reply on HN