I'm dialing back my LLM usage • Hacker News Board

Re: I'm dialing back my LLM usage

#41

Post by generalizations » Wed, Jul 02, 2025, 3:41 PM UTC

x187463 wrote: post #11

Am I spending too much time on HN or is every post/comment section filled with this same narrative? Basically, LLMs are exciting but they produce messy code for which the dev feels no ownership. Managing a codebase written by an LLM is difficult because you have not cognitively loaded the entire thing into your head as you do with code written yourself. They're okay for one-off scripts or projects you do not intend t…

It feels like a bell curve:

- one big set of users who don't like it because it generates a lot of code and uses its own style of algorithms, and it's a whole lot of unfamiliar code that the user has to load up in their mind - as you said. Too much to comprehend, and quickly overwhelming.

And then to either side

- it unblocks users who simply couldn't have written the code on their own, who aren't even trying to load it into their head. They are now able to make working programs!

- it accelerates users who could have written it on their own, given enough time, but have figured out how to treat it as an army of junior coders, and learned to only maintain the high level algorithm in their head. They are now able to build far larger projects, fast!

Re: I'm dialing back my LLM usage

#42

Post by haiku2077 » Wed, Jul 02, 2025, 3:43 PM UTC

solomonb wrote: post #25

seanw444 wrote: post #4

This is pretty much the conclusion I've come to as well. It's not good at being an autocomplete for entire chunks of your codebase. You lose the mental model of what is doing what, and exactly where. I prefer to use it as a personalized, faster-iterating StackOverflow. I'll ask it to give me a rundown of a concept I'm not familiar with, or for a general direction to point me in if I'm uncertain of what a good solutio…

I use it the same way but cursor is constantly insisting on making code changes. Is there a trick to get it to introspect on the codebase without wanting to modify it?

In Zed you can toggle between read-only and write modes at any point when using the agent. You can also create custom modes that allow the use of specific tools, editing only specific files, etc. Does cursor have a similar feature?

Re: I'm dialing back my LLM usage

#43

Post by remram » Wed, Jul 02, 2025, 3:43 PM UTC

_flux wrote: post #14

quaintdev wrote: post #6

LLMs have limits. They are super powerful but they can't make the kind of leap humans can. For example, I asked both Claude and Gemini below problem. "I want to run webserver on Android but it does not allow binding on ports lower than 1000. What are my options?" Both responded with below solutions 1. Use reverse proxy 2. Root the phone 3. Run on higher port Even after asking them to rethink they couldn't come up wit…

TIL. I knew about the SRV reconds—which almost nobody uses I think?—but this was news to me. I guess it's also actually supported, unlike SRV that are more like supported only by some applications? Matrix migrated from SRV to .well-known files for providing the data. (Or I maybe it supports both.)

Re: I'm dialing back my LLM usage

#44

Post by yard2010 » Wed, Jul 02, 2025, 3:44 PM UTC

atonse wrote: post #9

These seem like good checkpoints (and valid criticisms) on the road to progress. But it's also not crazy to think that with LLMs getting smarter (and considerable resources put into making them better at coding), that future versions would clean up and refactor code written by past versions. Correct?

LLM doesn't get smarter. An LLM is just a statistical tool for text generation, not a form of an AI. Since language is so inherent to intelligence and knowledge, it correlates. But LLM is just a tool for predicting what the average internet person would say.

Re: I'm dialing back my LLM usage

#45

Post by ookblah » Wed, Jul 02, 2025, 3:44 PM UTC

x187463 wrote: post #11

Am I spending too much time on HN or is every post/comment section filled with this same narrative? Basically, LLMs are exciting but they produce messy code for which the dev feels no ownership. Managing a codebase written by an LLM is difficult because you have not cognitively loaded the entire thing into your head as you do with code written yourself. They're okay for one-off scripts or projects you do not intend t…

honestly my theory is part of it is people who are very caught up in the "craft" part of it and now hate these LLMs for producing shit that pretty much works but isn't like this "perfect specimen" of coding architecture that they now have to pour over.

honestly, the vast majority of basically CRUD apps out there we are inflating our skills a bit too much here. even if the code is junk you can adapt your mindset to accept what LLMs produce, clean it up a bit, and come out with something maintainable.

like do these people ever have to review code from other people or juniors? the feedback loop here is tighter (although the drawback is your LLM doesn't "learn").

i wouldn't use it for anything super novel or cutting edge i guess, but i don't know, i guess everyone on HN might be coding some super secret advanced project that an LLM can't handle....?

Re: I'm dialing back my LLM usage

#46

Post by pimlottc » Wed, Jul 02, 2025, 3:44 PM UTC

quaintdev wrote: post #6

LLMs have limits. They are super powerful but they can't make the kind of leap humans can. For example, I asked both Claude and Gemini below problem. "I want to run webserver on Android but it does not allow binding on ports lower than 1000. What are my options?" Both responded with below solutions 1. Use reverse proxy 2. Root the phone 3. Run on higher port Even after asking them to rethink they couldn't come up wit…

To be fair, the question implies the port number of the local service is the problem, when it's more about making sure users can access it without needing to specify a port number in the URL.

Yes, an experienced person might be able to suss out what the real problem was, but it's not really the LLMs fault for answering the specific question it was asked. Maybe you just wanted to run a server for testing and didn't realize that you can add a non-standard port to the URL.

Re: I'm dialing back my LLM usage

#47

Post by nico » Wed, Jul 02, 2025, 3:45 PM UTC

x187463 wrote: post #11

Am I spending too much time on HN or is every post/comment section filled with this same narrative? Basically, LLMs are exciting but they produce messy code for which the dev feels no ownership. Managing a codebase written by an LLM is difficult because you have not cognitively loaded the entire thing into your head as you do with code written yourself. They're okay for one-off scripts or projects you do not intend t…

> Managing a codebase written by an LLM is difficult because you have not cognitively loaded the entire thing into your head as you do with code written yourself

This happens with any sufficiently big/old codebase. We can never remember everything, even if we wrote it ourselves

I do agree with the sentiment and insight about the 2 branches of topics frequently seen lately on HN about AI-assisted coding

Would really like to see a live/video demo of semi-autonomous agents running in parallel and executing actual useful tasks on a decently complex codebase, ideally one that was entirely “manually” written by devs before agents are involved - and that actually runs a production system with either lots of users or paid customers

Re: I'm dialing back my LLM usage

#48

Post by kadhirvelm » Wed, Jul 02, 2025, 3:45 PM UTC

I wonder if this is as good as LLMs can get, or if this is a transition period between LLM as an assistant, and LLM as a compiler. Where in the latter world we don’t need to care about the code because we just care about the features. We let the LLM deal with the code and we deal with the context, treating code more like a binary. In that world, I’d bet code gets the same treatment as memory management today, where only a small percent of people need to manage it directly and most of us assume it happens correctly enough to not worry about it.

Re: I'm dialing back my LLM usage

#49

Post by cornfieldlabs » Wed, Jul 02, 2025, 3:47 PM UTC

alexvitkov wrote: post #10

I've found the Cursor autocomplete to be nice, but I've learned to only accept a completion if it's byte for byte what I would've written. With the context of surrounding code it guesses that often enough to be worth the money for me. The chatbot portion of the software is useless.

For me it's the opposite. Autocomplete suggests the lines I just deleted and also suggests completely useless stuff. I have a shortcut to snooze (it's possible!) it. It interrupts flow my flow a lot. I would rather those stuff myself.

Chat mode on the other hand follows my rules really well.

I mostly use o3 - it seems to be the only model that has "common sense" in my experience

Re: I'm dialing back my LLM usage

#50

Post by xpe » Wed, Jul 02, 2025, 3:47 PM UTC

jimbokun wrote: post #33

x187463 wrote: post #11

Am I spending too much time on HN or is every post/comment section filled with this same narrative? Basically, LLMs are exciting but they produce messy code for which the dev feels no ownership. Managing a codebase written by an LLM is difficult because you have not cognitively loaded the entire thing into your head as you do with code written yourself. They're okay for one-off scripts or projects you do not intend t…

Of course it's the main topic because it's an existential question for almost all our careers.

And AI in general* poses existence-level questions (that could go either way: good or bad) regarding military applications, medical research, economic benefits, quality of life, human thriving, etc.

The idea that the future is going to “more or less be predictable” and “within the realm of normal” is a pretty bold claim when you look at history! Paradigm shifts happen. And many people think we’re in the middle of one — people that don’t necessarily have an economic interest in saying so.

* I’m not taking a position here about predicting what particular AI technologies will come next, for what price, with what efficiency and capabilities, and when. Lots of things could happen we can’t predict — like economic cycles, overinvestment, energy constraints, war, popular pushback, policy choices, etc. But I would probably bet that LLMs are just the beginning.