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

121–130 of 229 posts

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

#121

Post by mrweasel »

CuriouslyC wrote: post #86
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…

16 year python dev who's done all that, lead multiple projects from inception to success, and I rarely manually code anymore. I can specify precisely what I want, and how I want it built (this is the key part), stub out a few files and create a few directories, and let an agent run wild but configured for static analysis tools/test suite to run after every iteration with the instructions to fix their mistakes before…

Assuming that your workflow works, and the rest of us just need to learn to use LLMs equally effective, won't that plateau us at the current level of programming?

The LLMs learn from examples, but if everyone uses LLMs to generate code, there's no new code to learn new features, libraries or methods from. The next generation of models are just going to be trained on the code generated by it's predecessors with now new inputs.

Being an LLM maximalist is basically freeze development in the present, now and forever.

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

#122

Post by mritchie712 »

infecto wrote: post #109
ghufran_syed wrote: post #108

Earlier quoted context omitted.

I wouldn’t classify this as binary thinking - isnt the comment you are replying just defining boundary conditions? Then those two points don’t define the entire space, but the output there does at least let us infer (but not prove) something about the nature of the “function” between those two points? Where the function f is something like f: experience -> productivity increase?

You’re right that it’s possible to read the original comment as just laying out two boundary conditions—but I think we have to acknowledge how narrative framing shapes the takeaway. The way it’s written leads the reader toward a conclusion: “LLMs are great for junior, fast-shipping devs; less so for experienced, meticulous engineers.” Even if that wasn’t the intent, that’s the message most will walk away with. But th…

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.

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

#123

Post by VMG »

meander_water wrote: post #65

The thing most LLM maximalists don't realize is that the bottleneck for most people is not code generation, it's code understanding. You may have doubled the speed at which you created something, but you need to pay double that time back in code review, testing and building a mental model of the codebase in your head. And you _need_ to do this if you want to have any chance of maintaining the codebase (i.e. bugfixes,…

This is not true.

It may be bad practice, but consider that the median developer does not care at all about the internals of the dependencies that they are using.

They care about the interface and about whether they work or not.

They usually do not care about the implementation.

Code generated by LLM is not that different than pulling in a random npm package or rust crate. We all understand the downsides, but there is a reason that practice is so popular.

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

#124

Post by UncleEntity »

voidhorse wrote: post #87
mexicocitinluez wrote: post #81

Earlier quoted context omitted.

> I get the point you’re trying to make, LLMs can be a force multiplier for less experienced devs, but the sweeping generalizations don’t hold up. If you’re okay with a higher tolerance for bugs or loose guardrails, sure, LLMs can feel magical. But that doesn’t mean they’re less valuable to experienced developers. Amen. Seriously. They're tools. Sometimes they work wonderfully. Sometimes, not so much. But I have DEFI…

> Amen. Seriously. They're tools. Sometimes they work wonderfully. Sometimes, not so much. But I have DEFINITELY found value. And I've been building stuff for over 15 years as well. Yes, but these lax expectation s are what I don't understand. What other tools in software sometimes work and sometimes don't that you find remotely acceptable? Sure all tools have bugs, but if your compiler had the same failure rate and…

Hell, AI is probably -1x for me because I refuse to give up and do it myself instead of trying to get the robots to do it. I mean, writing code is for the monkeys, right?

Anyhoo... I find that there are times where you have to really get in there and question the robot's assumptions as they will keep making the same mistake over and over until you truly understand what it is they are actually trying to accomplish. A lot of times the desired goal and their goal are different enough to cause extreme frustration as one tends to think the robot's goal should perfectly align with the prompt. Once it fails a couple times then the interrogation begins since we're not making any further progress, obviously.

Case in point, I have this "Operational Semantics" document, which is correct, and a peg VM, which is tested to be correct, but if you combine the two one of the operators was being compiled incorrectly due to the way backtracking works in the VM. After Claude's many failed attempts we had a long discussion and finally tracked down the problem to be something outside of its creative boundaries and it needed one of those "why don't you do it this way..." moments. Sure, I shouldn't have to do this but that's the reality of the tools and, like they say, "a good craftsman never blames his tools".

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

#125

Post by skydhash »

geraneum wrote: post #57
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…

> Writing down the architecture and guidelines more explicitly? Yes, very explicit like “if (condition) do (action)” and get more explicit when… oh wait!

Yeah. I never understood where people are coming with “you need guardrails, extensive architecture docs, coding rules,…”. For every software and features I wrote, I already have a good idea of the objectives before I even start to code. I do the specific part with code, going back to the whiteboard when I need to think.

It’s an iterative process, not a linear one. And the only hige commits are the scaffolding and the refactorings. It’s more like sculpture than 3d printing, a perpetual refinement of the code instead of adding huge lines of code.

This is the reason I switched to Vim, then Emacs. They allow for fast navigation, and faster editing. And so easy to add your own tool as the code is a repetitive structure. The rare cases I needed to add 10s of lines of code is with a code generator, or copy-pasting from some other file.

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

#126

Post by skydhash »

VMG wrote: post #123
meander_water wrote: post #65

The thing most LLM maximalists don't realize is that the bottleneck for most people is not code generation, it's code understanding. You may have doubled the speed at which you created something, but you need to pay double that time back in code review, testing and building a mental model of the codebase in your head. And you _need_ to do this if you want to have any chance of maintaining the codebase (i.e. bugfixes,…

This is not true. It may be bad practice, but consider that the median developer does not care at all about the internals of the dependencies that they are using. They care about the interface and about whether they work or not. They usually do not care about the implementation. Code generated by LLM is not that different than pulling in a random npm package or rust crate. We all understand the downsides, but there i…

Everything compounds. Good architecture makes it easy to maintain things later. Bad code will slow you down to a snail pace and will result in 1000s of bug tickets.

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

#127

Post by infecto »

mritchie712 wrote: post #122
infecto wrote: post #109

Earlier quoted context omitted.

You’re right that it’s possible to read the original comment as just laying out two boundary conditions—but I think we have to acknowledge how narrative framing shapes the takeaway. The way it’s written leads the reader toward a conclusion: “LLMs are great for junior, fast-shipping devs; less so for experienced, meticulous engineers.” Even if that wasn’t the intent, that’s the message most will walk away with. But th…

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 junior devs have larger opportunity of extracting value.

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

#128

Post by qudat »

VMG wrote: post #123
meander_water wrote: post #65

The thing most LLM maximalists don't realize is that the bottleneck for most people is not code generation, it's code understanding. You may have doubled the speed at which you created something, but you need to pay double that time back in code review, testing and building a mental model of the codebase in your head. And you _need_ to do this if you want to have any chance of maintaining the codebase (i.e. bugfixes,…

This is not true. It may be bad practice, but consider that the median developer does not care at all about the internals of the dependencies that they are using. They care about the interface and about whether they work or not. They usually do not care about the implementation. Code generated by LLM is not that different than pulling in a random npm package or rust crate. We all understand the downsides, but there i…

> They usually do not care about the implementation.

[citation needed]

> Code generated by LLM is not that different than pulling in a random npm package or rust crate

It's not random, there's an algorithm for picking "good" packages and it's much simpler than reviewing every single line of LLM code.

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

#129

Post by VMG »

qudat wrote: post #128
VMG wrote: post #123

Earlier quoted context omitted.

This is not true. It may be bad practice, but consider that the median developer does not care at all about the internals of the dependencies that they are using. They care about the interface and about whether they work or not. They usually do not care about the implementation. Code generated by LLM is not that different than pulling in a random npm package or rust crate. We all understand the downsides, but there i…

> They usually do not care about the implementation. [citation needed] > Code generated by LLM is not that different than pulling in a random npm package or rust crate It's not random, there's an algorithm for picking "good" packages and it's much simpler than reviewing every single line of LLM code.

>> They usually do not care about the implementation. > [citation needed]

Everybody agrees that e.g. `make` and autotools is a pile of garbage. It doesn't matter, it works and people use it.

> It's not random, there's an algorithm for picking "good" packages and it's much simpler than reviewing every single line of LLM code.

But you don't need to review every single line of LLM code just as you don't need to review every single line of dependency code. If it works, it works.

Why does it matter who wrote it?

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

#130

Post by jwblackwell »

> the current PHP+MySQL combo was not fit for purpose anymore

He lost me here. Sounds like he tried to change from a boring stack he understood, to Go and Clickhouse because it's cooler.

You're asking for trouble. LLMs are great and getting better, but you can't expect them to handle something like this right now

Post reply on HN