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

I'm dialing back my LLM usage

zed.dev

Post reply on HN
Print view View original

51–60 of 252 posts

Re: I'm dialing back my LLM usage

#51

Post by pier25 »

skeeter2020 wrote: post #38
pier25 wrote: post #31

Earlier quoted context omitted.

> 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. I don't think that's the main reason. Well written code is easier to follow even when you haven't written it yourself (or maybe you did but forgot about it).

I argue you still need to cognitively load the solution, it's just that well written code allows you to (a) segment the code base effectively and (b) hold it at a higher level of abstraction.

Absolutely. The comment I was responding to argued the difficulty was that LLM code wasn't loaded cognitively. I'm arguing the problem is actually the code produced by LLMs tends to be messy and hard to follow beyond trivial examples.

Re: I'm dialing back my LLM usage

#52

Post by nsingh2 »

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 Cursor, there is an 'ask' mode that isn't as over-eager to make edits as the default agent mode.

Re: I'm dialing back my LLM usage

#53

Post by furyofantares »

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?

I say something like "without making any code changes right now, investigate blah blah blah" and if I want more than just info "and propose a direction that I can look at", or sometimes give it a file to write a proposal into.

Re: I'm dialing back my LLM usage

#54

Post by lcnPylGDnU4H9OF »

pimlottc wrote: post #46
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 re…

It's not really an LLM being "faulty" in that we kinda know they have these limitations. I think they're pointing out that these models have a hard time "thinking outside the box" which is generally a lauded skill, especially for the problem-solving/planning that agents are expected to do.

Re: I'm dialing back my LLM usage

#55

Post by emilecantin »

chasing wrote: post #12

LLMs save me a lot of time as a software engineer because they save me a ton of time doing either boilerplate work or mundane tasks that are relatively conceptually easy but annoying to actually have to do/type/whatever in an IDE. But I still more-or-less have to think like a software engineer. That's not going to go away. I have to make sure the code remains clean and well-organized -- which, for example, LLMs can h…

I'm in a similar boat. I've only started using it more very recently, and it's really helping my "white-page syndrome" when I'm starting a new feature. I still have to fix a bunch of stuff, but I think it's easier for me to fix, tweak and refactor existing code than it is to write a new file from scratch.

Often times there's a lot of repetition in the app I'm working on, and there's a lot of it that's already been abstracted away, but we still have to import the component, its dependencies, and setup the whole thing which is indeed pretty boring. It really helps to tell the LLM to implement something and point it to an example of the style I want.

Re: I'm dialing back my LLM usage

#56

Post by dkubb »

noodletheworld wrote: post #18
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…

> want to tell you how awesome their workflow is Or, often, sell you something.

A lot of the time they are selling themselves as influencers on the subject. It’s often a way to get views or attention that they can use in the future.

Re: I'm dialing back my LLM usage

#57

Post by bwfan123 »

totalperspectiv wrote: post #20
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…

I think you hit the nail on the head with the mental model part. I really like this method of thinking about programming "Programming as Theory Building" https://gist.github.com/onlurking/fc5c81d18cfce9ff81bc968a7f... I don't mind when other programmers use AI, and use it myself. What I mind is the abdication of responsibility for the code or result. I don't think that we should be issuing a disclaimer when we use AI…

Thanks for sharing this beautiful essay which I have never come across. The essay and its citations are thought-provoking reading.

IMO, LLMs of today are not capable of building theories (https://news.ycombinator.com/item?id=44427757#44435126). And, if we view programming as theory building, then LLMs are really not capable of coding. They will remain useful tools.

Re: I'm dialing back my LLM usage

#58

Post by nsingh2 »

Nedomas wrote: post #3

two weeks ago I started heavily using Codex (I have 20y+ dev xp). At first I was very enthusiastic and thought Codex is helping me multiplex myself. But you actually spend so much time trying to explain Codex the most obvious things and it gets them wrong all the time in some kind of nuanced way that in the end you spend more time doing things via Codex than by hand. So I also dialed back Codex usage and got back to…

Same experience, these "background agents" are powered by models that aren't yet capable enough to handle large, tangled or legacy codebases without human guidance. So the background part ends up being functionally useless in my experience.

Re: I'm dialing back my LLM usage

#59

Post by tempodox »

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…

> … encountered many times per day.

I suspect that's at least partially because all of that doesn't stop the hype from being pushed on and on without mercy. Which in turn is probably because the perverse amounts of investment that went into this have to be reclaimed somehow with monetization. Imagine all those VCs having to realize that hundreds of billions of $$$ are lost to wishful hallucinations. Before they concede that there will of course be much astroturfing in the vein of your last paragraph.

Re: I'm dialing back my LLM usage

#60

Post by baq »

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…

> workflow is without actually showing any code.

an argument can be made that the code doesn't matter as long as the product works as it's supposed to (big asterisk here)

Post reply on HN