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

101–110 of 229 posts

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

#101

Post by infecto »

mritchie712 wrote: post #89
infecto wrote: post #63

Earlier quoted context omitted.

These all-or-nothing takes on LLMs are getting tiresome. 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. I’ve been writing Python and Java professionally…

my stance is the opposite of all-or-nothing. The note above is one example. How much value you get out of CURSOR specifically is going to vary based on person & problem. The Python dev in my example might immediately get value out of o3 in ChatGPT. It's not all or nothing. What you get value out of immediately will vary based on circumstance.

You say your stance isn’t all-or-nothing, but your original comment drew a pretty hard line, junior devs who start from scratch and have a high tolerance for bugs get 10x productivity, while experienced devs with high standards and mature setups will likely be slowed down. That framing is exactly the kind of binary thinking that’s making these conversations so unproductive.

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

#102

Post by jrvarela56 »

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-…

You can use the LLm to decompose tasks. As you said, tasks that are simple and have solutions in the trainning data can save you time.

Most code out there is glue. So there’s a lot of trainning data on integrating/composing stuff.

If you take this as a whole, you could do that 30-60 min into 5 min for most dev work.

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

#103

Post by tasuki »

> but I was optimizing for speed and I hadn’t actually sat down just to review the code

There, there's your problem. The problem is not LLMs, the problem is people not using their brain. Can't we use LLMs and our brains as well? Both are amazing tools!

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

#104

Post by alpaca128 »

withinboredom wrote: post #3

I've come to mostly use ai to bounce ideas off of. Even that has gotten less useful these last few months for some reason. Now it either wants to do the work for me or just spit out a complete agreement without being any bit critical.

It's known that OpenAI tweaked ChatGPT output so it's very agreeable and flattering no matter what the input is. Which turns out to be a problem because even the most schizophrenic paranoid rant will get an enthusiastic response praising how the user isn't a sheep and doesn't blindly conform to societal norms etc.

And why did they make this change? Because it makes users spend more time on the platform. ChatGPT wasn't just one of the fastest-growing web services ever, it's now also speedrunning enshittification.

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

#105

Post by exiguus »

Over the past few months, I have read numerous articles on this topic. Some are in favor, some are against, and others fall somewhere in between. However, they all share a common shortcoming: the absence of code. There are no codebases, no commit histories—nothing that allows readers to track how the codebase evolves, gets refactored, or how new features are integrated.

Without access to the code, it's challenging to verify the authors' claims and form an independent opinion. In my view, we should be cautious about trusting articles that lack examples or sources. As someone wiser than me once said:

> Articles without sources are merely the opinions of the author.

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

#106

Post by tasuki »

rco8786 wrote: post #40
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?

(Usually) Yes. The LLM can generate three functions, over 100 lines of code, and I spend perhaps 15 minutes rearranging it so it pleases me aesthetically. It would've taken me an hour or two to write.

I find most benefit in writing tests for a yet-inexistent function I need, then giving the LLM the function signature, and having it implement the function. TDD in the age of LLMs is great!

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

#107

Post by arctek »

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-…

Similar to my experience, it works well for small tasks, replacing search (most of the time) and doing alot of boilerplate work.

I have one project that is very complex and for this I can't and don't use LLMs for.

I've also found it's better if you can get it code generate everything in the one session, if you try other LLMs or sessions it will quickly degrade. That's when you will see duplicate functions and dead end code.

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

#108

Post by ghufran_syed »

infecto wrote: post #101
mritchie712 wrote: post #89

Earlier quoted context omitted.

my stance is the opposite of all-or-nothing. The note above is one example. How much value you get out of CURSOR specifically is going to vary based on person & problem. The Python dev in my example might immediately get value out of o3 in ChatGPT. It's not all or nothing. What you get value out of immediately will vary based on circumstance.

You say your stance isn’t all-or-nothing, but your original comment drew a pretty hard line, junior devs who start from scratch and have a high tolerance for bugs get 10x productivity, while experienced devs with high standards and mature setups will likely be slowed down. That framing is exactly the kind of binary thinking that’s making these conversations so unproductive.

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?

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

#109

Post by infecto »

ghufran_syed wrote: post #108
infecto wrote: post #101

Earlier quoted context omitted.

You say your stance isn’t all-or-nothing, but your original comment drew a pretty hard line, junior devs who start from scratch and have a high tolerance for bugs get 10x productivity, while experienced devs with high standards and mature setups will likely be slowed down. That framing is exactly the kind of binary thinking that’s making these conversations so unproductive.

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 they drew boundaries with very specific conditions that lead the reader. It’s a common theme in these AI discussions.

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

#110

Post by anonzzzies »

ekidd wrote: post #92
anonzzzies wrote: post #68

Earlier quoted context omitted.

> until you've learned to use it You have the copilot mode which takes no learning at all which might give you some speedup, especially if you are doing repetitive stuff, it might even 10x+ you. You have cmdk mode which you need to prompt and seems to he a lobotomized version of chat. I find putting comments and waiting for the copilot mode to kick in better as then the way we got there is saved. Then there is agenti…

> You have the copilot mode which takes no learning at all which might give you some speedup, especially if you are doing repetitive stuff, it might even 10x+ you. I have some grey hair and I've been programming since I was a kid. Using CoPilot autocompletion roughly doubles my productivity while cutting my code quality by 10%. This happens because I can see issues in autocompleted code far faster than I can type, th…

I get very good results with very little effort, but that is because I have written code for 40 years fulltime. Not because I know the tool better.
Post reply on HN