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

The current state of LLM-driven development

blog.tolki.dev

Post reply on HN
Print view View original

191–200 of 244 posts

Re: The current state of LLM-driven development

#191

Post by enraged_camel »

tptacek wrote: post #8

Learning how to use LLMs in a coding workflow is trivial. There is no learning curve. You can safely ignore them if they don’t fit your workflows at the moment. I have never heard anybody successfully using LLMs say this before. Most of what I've learned from talking to people about their workflows is counterintuitive and subtle. It's a really weird way to open up an article concluding that LLMs make one a worse prog…

Agreed. This is an astonishingly bad article. It's clear that the only reason it made it to the front page is because people who view AI with disdain or hatred upvoted it. Because as you say: how can anyone make authoritative claims about a set of tools not just without taking the time to learn to use them properly, but also believing that they don't even need to bother?

Re: The current state of LLM-driven development

#192

Post by memorylane »

throwawaybob420 wrote: post #140

Judging from all the comments here, it’s going to be amazing seeing the fallout of all the LLM generated code in a year or so. The amount of people who seemingly relish the ability to stop thinking and let the model generate giant chunks of their code base, is uh, something else lol.

Dunno about you, but I find thinking hard… when I offload boilerplate code to Claude, I have more cycles left over to hold the problem in my head and effectively direct the agent in detail.

Re: The current state of LLM-driven development

#193

Post by credit_guy »

otabdeveloper4 wrote: post #181
credit_guy wrote: post #101

Earlier quoted context omitted.

Fully agree. It takes months to learn how to use LLMs properly. There is an initial honeymoon where the LLMs blow your mind out. Then you get some disappointments. But then you start realizing that there are some things that LLMs are good at and some that they are bad at. You start creating a feel for what you can expect them to do. And more importantly, you get into the habit of splitting problems into smaller probl…

I dunno, man. I think you could have spent that time, you know, learning to code instead.

Sure. But it happens that I have 20 years of experience, and I know quite well how to code. Everything the LLM does for me I can do myself. But the LLM does that 100 times faster than me. Most of the days nowadays I push thousands of lines of code. And it's not garbage code, the LLMs write quite high quality code. Of course, I still have to go through the code and make sure it all makes sense. So I am still the bottleneck. At some point I will probably grown to trust the LLM, but I'm not quite there yet.

Re: The current state of LLM-driven development

#194

Post by 8note »

credit_guy wrote: post #193
otabdeveloper4 wrote: post #181

Earlier quoted context omitted.

I dunno, man. I think you could have spent that time, you know, learning to code instead.

Sure. But it happens that I have 20 years of experience, and I know quite well how to code. Everything the LLM does for me I can do myself. But the LLM does that 100 times faster than me. Most of the days nowadays I push thousands of lines of code. And it's not garbage code, the LLMs write quite high quality code. Of course, I still have to go through the code and make sure it all makes sense. So I am still the bottl…

it is, mind you, exactly the same experience as working on a team with lots of junior engineers, and delegating work to them

Re: The current state of LLM-driven development

#195

Post by credit_guy »

8note wrote: post #194
credit_guy wrote: post #193

Earlier quoted context omitted.

Sure. But it happens that I have 20 years of experience, and I know quite well how to code. Everything the LLM does for me I can do myself. But the LLM does that 100 times faster than me. Most of the days nowadays I push thousands of lines of code. And it's not garbage code, the LLMs write quite high quality code. Of course, I still have to go through the code and make sure it all makes sense. So I am still the bottl…

it is, mind you, exactly the same experience as working on a team with lots of junior engineers, and delegating work to them

Yes and no. With junior developers you need to educate them. You need to do that with LLMs too. Maybe you need to break down the problem in smaller chunks, but you get to this after a while. But once the LLM understands the task, you get a few hundred lines of code in a mater of minutes. With a junior developer you are lucky if they come back the same day. The iteration speed with AI is simply in a different league.

Edit: it is Sunday. As I am relaxing, and spending time writing answers on HN, I keep a lazy eye on the progress of an LLM at work too. I got stuff done that would have taken me a few days of work by just clicking a "Continue" button now and then.

Re: The current state of LLM-driven development

#196

Post by gexla »

physPop wrote: post #107
credit_guy wrote: post #101

Earlier quoted context omitted.

Fully agree. It takes months to learn how to use LLMs properly. There is an initial honeymoon where the LLMs blow your mind out. Then you get some disappointments. But then you start realizing that there are some things that LLMs are good at and some that they are bad at. You start creating a feel for what you can expect them to do. And more importantly, you get into the habit of splitting problems into smaller probl…

it really doesn't take that long. Maybe if you're super junior and never coded before? In that case I'm glad its helping you get into the field. Also, if its taking you months there are whole new models that will get released and you need to learn those quirks again.

No, it's a practice. You're not necessarily building technical knowledge, rather you're building up an intuition. It's for sure not like learning a programming language. It's more like feeling your way along and figuring out how to inhabit a dwelling in the dark. We would just have to agree to disagree on this. I feel exactly as the parent commenter felt. But it's not easy to explain (or to understand from someones explanation.)

Re: The current state of LLM-driven development

#197

Post by gexla »

credit_guy wrote: post #101
tptacek wrote: post #8

Learning how to use LLMs in a coding workflow is trivial. There is no learning curve. You can safely ignore them if they don’t fit your workflows at the moment. I have never heard anybody successfully using LLMs say this before. Most of what I've learned from talking to people about their workflows is counterintuitive and subtle. It's a really weird way to open up an article concluding that LLMs make one a worse prog…

Fully agree. It takes months to learn how to use LLMs properly. There is an initial honeymoon where the LLMs blow your mind out. Then you get some disappointments. But then you start realizing that there are some things that LLMs are good at and some that they are bad at. You start creating a feel for what you can expect them to do. And more importantly, you get into the habit of splitting problems into smaller probl…

Love this, and it's so true. A lot of people don't get this, because it's so nuanced. It's not something that's slowing you down. It's not learning a technical skill. Rather, it's building an intuition.

I find it funny when people ask me if it's true that they can build an app using an LLM without knowing how to code. I think of this... that it took me months before I started feeling like I "got it" with fitting LLMs into my coding process. So, not only do you need to learn how to code, but getting to the point that the LLM feels like a natural extension of you has its own timeline on top.

Re: The current state of LLM-driven development

#198

Post by gexla »

8note wrote: post #194
credit_guy wrote: post #193

Earlier quoted context omitted.

Sure. But it happens that I have 20 years of experience, and I know quite well how to code. Everything the LLM does for me I can do myself. But the LLM does that 100 times faster than me. Most of the days nowadays I push thousands of lines of code. And it's not garbage code, the LLMs write quite high quality code. Of course, I still have to go through the code and make sure it all makes sense. So I am still the bottl…

it is, mind you, exactly the same experience as working on a team with lots of junior engineers, and delegating work to them

Wait a minute, you didn't just claim that we have reached AGI, right? I mean, that's what it would mean to delegate work to junior engineers, right? You're delegating work to human level intelligence. That's not what we have with LLMs.

Re: The current state of LLM-driven development

#199

Post by skajzbxbbj »

johnisgood wrote: post #98
misja111 wrote: post #96

Earlier quoted context omitted.

> My dad doesn't need to know how to do algebra to get his taxes done, he just has an accountant. This is not quite the same thing. The AI is not perfect, it frequently makes mistakes or suboptimal code. As a software engineer, you are responsible for finding and fixing those. This means you have to review and fully understand everything that the AI has written. Quite a different situation than your dad and his accou…

> This means you have to review and fully understand everything that the AI has written. Yes, and people who care and is knowledgeable do this already. I do this, for one.

But there’s no way one is giving as thorough a review as if one had written code to solve the problem themselves. Writing is understanding. You’re trading thoroughness and integrity for chance.

Writing code should never have been a bottle neck. And since it wasn’t, any massive gains are due to being ok with trusting the AI.

Re: The current state of LLM-driven development

#200

Post by mockingloris »

memorylane wrote: post #192
throwawaybob420 wrote: post #140

Judging from all the comments here, it’s going to be amazing seeing the fallout of all the LLM generated code in a year or so. The amount of people who seemingly relish the ability to stop thinking and let the model generate giant chunks of their code base, is uh, something else lol.

Dunno about you, but I find thinking hard… when I offload boilerplate code to Claude, I have more cycles left over to hold the problem in my head and effectively direct the agent in detail.

This makes sense. I find that after 15 to 20 iterations, I get better understanding of what is being done and possible simplifications.

I then manually declare some functions, JSDoc comments for the return types, imports and stop halfway. By then the agent is able to think, ha!, you plan to replace all the api calls to this composable under the so and so namespace.

It's iterations and context. I don't use them for everything but I find that they help when my brain bandwidth begins to lag or I just need a boilerplate code before engineering specific use cases.

└── Dey well

Post reply on HN