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

141–150 of 229 posts

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

#141

Post by dfxm12 »

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.

They are being marketed a virtual assistants that will literally do all the work for you. If they become marketed truthfully, however, people will probably realize that they aren't worth the cost and it's largely more beneficial to search the web and/or crowdsource answers.

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

#142

Post by acureau »

jfim wrote: post #60
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…

One thing you can do is to define the classes and methods that you want to have, and have the LLM implement them. For tricky things, you can leave additional notes in the empty method body as to how things should be implemented. This way you're doing the big picture thinking while having the LLM do what's it's good at, generating code within the limits of its context window and ability to reason about larger software…

I've found a lot of value in this approach as well, I don't delegate any architecture decisions to LLMs. I build out the high-level and I see if the LLM can fill the gaps. I've found they are good at writing pure functions, and am good at composing them and managing state.

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

#143

Post by pizzathyme »

nicodjimenez wrote: post #10

I tend to agree with this. These days I usually use LLMs to learn about something new or to help me generate client code for common APIs (especially boto3 these days). I tried Windsurf to help me make basic changes to my docker compose files, but when it couldn't even do that correctly, I lost a little enthusiasm. I'm sure it can build a working prototype of a small web app but that's not enough for me. For me LLMs a…

I had a similar experience as the author. I've found found that cursor / copilot are FANTASTIC at "smart autocomplete", or "write a (small function that does this)" and quick viral prototypes.

But after I got a week into my LLM-led code base, it became clear it was all spaghetti code and progress ground to a halt.

This article is a perfect snapshot of the state of the art. It might improve in the future, but this is where it is in May 2025.

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

#144

Post by Izkata »

rco8786 wrote: post #19

> So I do a “coding review” session. And the horror ensues. Yup. I've spoken about this on here before. I was a Cursor user for a few months. Whatever efficiency gains I "achieved" were instantly erased in review, as we uncovered all the subtle and not-so-subtle bugs it produced. Went back to vanilla VSCode and still use copilot but only when I prompt it to do something specific (scaffold a test, write a migration wi…

> Cursor's tab complete feels like magic at first, but the shine wore off for me.

My favorite thing here watching a co-worker is when Cursor tries to tab complete what he just removed, and sometimes he does it by reflex.

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

#145

Post by bluecheese452 »

infecto wrote: post #127
mritchie712 wrote: post #122

Earlier quoted context omitted.

no, those are two examples of many many possible circumstances. I intentionally made it two very specific examples so that was clear. Seems it wasn't so clear.

Fair enough but if you have to show up in the comments clarifying that your clearly delineated “IF this THEN that” post wasn’t meant to be read as a hard divide, maybe the examples weren’t doing the work you thought they were. You can’t sketch a two-point graph and then be surprised people assume it’s linear. Again I think the high level premise is correct as I already said, the delivery falls flat though. Your more…

I and others understood it perfectly well. Maybe the problem wasn’t with the post.

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

#146

Post by donatj »

I kind of miss figuring things out by myself. I am unwilling to use anything it generates that I don't completely understand so often I spend just as much time figuring out why the code it created works as I would have just writing it myself.

My job has changed from writing code to code reviewing a psychopathic baby.

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

#147

Post by kartoffelsaft »

stevepotter wrote: post #53
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 do a variety of things, including iOS and web. Like you mentioned, LLM results between the two are very different. I can't trust LLM output to even compile, much less work. Just last night, it told me to use an API called `CMVideoFormatDescriptionGetCameraIntrinsicMatrix`. That API is very interesting because it doesn't exist. It also did a great job of digging some deep holes when dealing with some tricky Swift 6…

Honestly, with a lot of HN debating the merits of LLMs for generating code, I wish it were an unwritten rule that everyone states the stack they're using with it. It seems that the people who rave about it creating a whole product line in a weekend are asking it to write them a web iterface using [popular js framework] that connects to [ubiquitous database], and their app is a step or two away from being CRUD. Meanwhile, the people who say it's done nothing for them are writing against [proprietary in-house library from 2005].

The worst is the middleground of stacks that are popular enough to be known but not enough for an LLM to know them. I say worst because in these cases the facade that the LLM understands how to create your product will fall before you the software's lifecycle ends (at least, if you're vibe-coding).

For what it's worth, I've mostly been a hobbyist but I'm getting close to graduating with a CS degree. I've avoided using LLMs for classwork because I don't want to rob myself of an education, but I've occasionally used them for personal, weird projects (or tried to at least). I always give up with it because I tend to like trying out niche languages that the LLM will just start to assume work like python (ex: most LLMs struggle with zig in my experience).

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

#148

Post by flanked-evergl »

psim1 wrote: post #133

"Using [your] brain" is key. And your brain has to understand software engineering in the first place, before you can use it. In my project, the product manager has recently tried his hand at vibe coding. LLM produces what you would expect it to produce and as described in the article: ok but not robust code, and fast. So now he thinks he knows how fast coding should be and has gone light speed on the product, expect…

You should quit, with people like that running things it's going to get run into the ground. Problem is that most product managers don't get that their position is the fail upwards position, the position you get when you literally can't do anything useful.

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

#149

Post by bwfan123 »

This [1] is an old and brilliant article titled "On the foolishness of natural language programming" by Dijkstra relevant to this debate.

The argument is that the precision allowed by formal languages for programming, math etc were the key enabler for all of the progress made in information processing.

ie, Vibe-coding with LLMs will make coding into a black-art known only to the shamans who can prompt well.

[1] https://www.cs.utexas.edu/~EWD/transcriptions/EWD06xx/EWD667...

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

#150

Post by aqme28 »

emseetech wrote: post #49
mritchie712 wrote: post #37

Earlier quoted context omitted.

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 produ…

Agreed but the 1 year JS dev should know they're making a deal with the devil in terms of building their skillset long term.

Maybe. But I also think that ignoring AI tools will hamper your long-term skillsets, as our profession adapts to these new tools.
Post reply on HN