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

Coding agents have replaced every framework I used

blog.alaindichiappari.dev

Post reply on HN
Print view View original

191–200 of 611 posts

Re: Coding agents have replaced every framework I used

#191

Post by verdverm »

hakunin wrote: post #181
cheema33 wrote: post #159

Earlier quoted context omitted.

“Of all the points the other side makes, this one seems the most incoherent. Code is deterministic, AI isn’t. We don’t have to look at assembly, because a compiler produces the same result every time.” This is a valid argument. However, if you create test harnesses using multiple LLMs validating each other’s work, you can get very close to compiler-like deterministic behavior today. And this process will improve over…

It helps, but it doesn't make it deterministic. LLMs could all be misled together. A different story would be if we had deterministic models, where the exact same input always results in the exact same output. I'm not sure why we don't try this tbh.

I've been wondering if there are better random seeds, like how there are people who hunt for good seeds in Minecraft

Re: Coding agents have replaced every framework I used

#192

Post by TideAd »

Ocha wrote: post #100
jatora wrote: post #93

Earlier quoted context omitted.

I dont really understand how this is possible. I've built some very large applications, and even a full LLM data curation,tokenizer, pretrain, posttrain SFT/DPO pipeline with LLM's and it most certainly took far less time than if i had done it manually. Sure it isnt all optimal...but it most certainly isnt subpar, and it is fully functional

So you skipped the code review and just checked that it does what you needed it to do?

GPT-5 codex variants with xhigh reasoning make great code reviewers.

Re: Coding agents have replaced every framework I used

#193

Post by verdverm »

scrame wrote: post #86
dvfjsdhgfv wrote: post #62

Earlier quoted context omitted.

> if I had written it completely by myself from the start, I would have finished the project in the same amount of time but I’d understand the details far better. I believe the argument from the other camp is that you don't need to understand the code anymore, just like you don't need to understand the assembly language.

quite a bit of software you would need to understand the assembly. not everything is web-services.

I've only needed assembly once in more than 20 years of programming, not a webdev

It was during university to get access to CPU counters for better instrumenting, like 15 years ago. Havent needed it since

Re: Coding agents have replaced every framework I used

#194

Post by alexalx666 »

peteforde wrote: post #83

I have been using Cursor w/ Opus 4.x to do extensive embedded development work over the past six months in particular. My own take on this topic is that for all of the chatter about LLMs in software engineering, I think a lot of folks are missing the opportunity to pull back and talk about LLMs in the context of engineering writ large. [I'm not capitalizing engineering because I'm using the HN lens of product develop…

In my experience, often the libs provided by manufacturers are thin wrappers over physical interface setup and communication in the form of a single header and cpp file. Isnt it easier to just use them instead of generating differently phrased copies of them?

Re: Coding agents have replaced every framework I used

#195

Post by notpachet »

thwarted wrote: post #102
wtetzner wrote: post #34

Earlier quoted context omitted.

> It's strange to me when articles like this describe the 'pain of writing code'. I find it strange to compare the comment sections for AI articles with those about vim/emacs etc. In the vim/emacs comments, people always state that typing in code hardly takes any time, and thinking hard is where they spend their time, so it's not worth learning to type fast. Then in the AI comments, they say that with AI writing the…

At first I thought you were referring to the debates over using vim or using emacs, but I think you mean to refer to the discussions about learning to use/switching to powerful editors like vim or emacs. If you learn and use a sharp, powerful editor and learn to type fast, the "burden" of editing and typing goes away.

I wonder how many vibecoding/automatic programming zealots are fluent in a multimodal editor.

Re: Coding agents have replaced every framework I used

#196

Post by exe34 »

hakunin wrote: post #181
cheema33 wrote: post #159

Earlier quoted context omitted.

“Of all the points the other side makes, this one seems the most incoherent. Code is deterministic, AI isn’t. We don’t have to look at assembly, because a compiler produces the same result every time.” This is a valid argument. However, if you create test harnesses using multiple LLMs validating each other’s work, you can get very close to compiler-like deterministic behavior today. And this process will improve over…

It helps, but it doesn't make it deterministic. LLMs could all be misled together. A different story would be if we had deterministic models, where the exact same input always results in the exact same output. I'm not sure why we don't try this tbh.

it's literally just setting T=0. except they are not as creative then. they don't explore alternative ideas from the mean.

Re: Coding agents have replaced every framework I used

#197

Post by woeirua »

HighGoldstein wrote: post #179
FeteCommuniste wrote: post #164

Earlier quoted context omitted.

I don't think there's going to be any catastrophic collapse but I predict de-slopping will grow to occupy more and more developer time. Who knows, maybe soon enough we'll have specially trained de-slopper bots, too.

> Who knows, maybe soon enough we'll have specially trained de-slopper bots, too. Fire, meet oil.

The naysayers said we’d never even get to this point. It’s far more plausible to me that AI will advance enough to de-slopify our code than it is to me that there will be some karmic reckoning in which the graybeards emerge on top again.

Re: Coding agents have replaced every framework I used

#198

Post by exe34 »

AstroBen wrote: post #144
dvfjsdhgfv wrote: post #62

Earlier quoted context omitted.

> if I had written it completely by myself from the start, I would have finished the project in the same amount of time but I’d understand the details far better. I believe the argument from the other camp is that you don't need to understand the code anymore, just like you don't need to understand the assembly language.

That will never happen unless we figure out a far simpler way to prove the system does what it should. If you've ever had bugs crop up with a full test suite you should know this is incredibly hard to do LLMs can't read your mind. In the end they're always taking the english prompt and making a bunch of fill in the blank assumptions around it. This is inevitable if we're to get any productivity improvements out of th…

we can do both. we can write code for the parts where it matters and let the LLM code the parts that aren't as critical.

Re: Coding agents have replaced every framework I used

#199

Post by verdverm »

simonw wrote: post #118
abcde666777 wrote: post #25

It's strange to me when articles like this describe the 'pain of writing code'. I've always found that the easy part. Anyway, this stuff makes me think of what it would be like if you had Tolkein around today using AI to assist him in his writing. 'Claude, generate me a paragraph describing Frodo and Sam having an argument over the trustworthiness of Gollum. Frodo should be defending Gollum and Sam should be on his s…

Have you really never found writing code painful? CI is failing. It passed yesterday. Is there a flaky API being called somewhere? Did a recent commit introduce a breaking change? Maybe one of my third-party dependencies shipped a breaking change? I was going to work on new code, but now I have to spend between 5 minutes and an hour+ - impossible to predict - solving this new frustration that just cropped up. I love…

You have a solution, I've seen them recommend some pretty terrible bug fixes, especially in the ci realm because they get rather clueless as the perspective gets higher or broader

Re: Coding agents have replaced every framework I used

#200

Post by exe34 »

SoftTalker wrote: post #190
exe34 wrote: post #180

Earlier quoted context omitted.

my problem with frameworks has always been that the moment I want to do something the framework writers aren't interested in, I now have three problems: my problem, how to implement it in the underlying platform and how to work around the framework to not break my feature.

Yes this happens in every framework I've ever used. My approach used to be to try to work around it, but now I've got these local exceptions to what the framework does and that is inevitably where problems/bugs pop up. Now I simply say "we can't implement the feature that way in this framework, we need to rework the specification." I no longer try to work against the framework, it's just a massive time sink and creat…

I'm so glad software engineering isn't my job. I love solving problems, and I'm somewhat better at using code to do it than my peers (fellow scientists), but I would hate to have a boss/client that says "it needs to do X" and the framework writer (or SDK, ala Android/Xcode) say "no, that hurts my profits/privacy busting".
Post reply on HN