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

261–270 of 611 posts

Re: Coding agents have replaced every framework I used

#261

Post by andoando »

capyba wrote: post #29
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…

Your last sentence describes my thoughts exactly. I try to incorporate Claude into my workflow, just to see what it can do, and the best I’ve ended up with is - 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. Even just some AI-assisted development in the trickier parts of my code bases completely robs me o…

Are you giving it huge todos in one prompt or working modularly?

Claude set up account creation / login with SSO login, OTP and email notifications in like 5 mins and told me exactly what to do on the provider side. Theres no way that wouldn't have taken me few hours to figure out

There is no way its not faster at a large breadth of the work, unless youre maybe a fanatic with reviewing and nitpicking every line of code to the extreme

Re: Coding agents have replaced every framework I used

#262

Post by philipswood »

hakunin wrote: post #129
danny_codes wrote: post #120

Earlier quoted context omitted.

GCC is, I imagine, several orders of magnitude mor deterministic than an LLM.

It’s not _more_ deterministic. It’s deterministic, period. The LLMs we use today are simply not.

Build systems may be deterministic in the narrow sense you use, but significant extra effort is required to make them reproducible.

Engineering in the broader sense often deals with managing the outputs of variable systems to get known good outcomes to acceptable tolerances.

Edit: added second paragraph

Re: Coding agents have replaced every framework I used

#263

Post by nottorp »

redleggedfrog wrote: post #208
rglover wrote: post #139

A significant number of developers and businesses are going to have an absolutely brutal rude awakening in the not too distant future. You can build things this way, and they may work for a time, but you don't know what you don't know (and experience teaches you that you only find most stuff by building/struggling; not sipping a soda while the AI blurts out potentially secure/stable code). The hubris around AI is goi…

The future is already here. Been working a few years at a subsidiary of a large corporation where the entire hierarchy of companies is pushing AI hard, at different levels of complexity, from office work up through software development. Regular company meetings across companies and divisions to discuss methods and progress. Overall not a bad strategy and it's paying dividends. A experiment was tried on a large and ve…

I've noticed this in my small scale tests. Basically the larger the prompt gets (and it includes all the previously generated code because that's what you want to add features to), the more likely is that the LLM will go off the rails. Or forget the beginning of the context. Or go into a loop.

Now if you're using a lot of separate prompts where you draw from whatever the network was trained on and not from code that's in the prompt, you can get usable stuff out of it. But that won't build you the whole application.

Re: Coding agents have replaced every framework I used

#264

Post by smashed »

skybrian wrote: post #230
pragmatic wrote: post #221

Earlier quoted context omitted.

Now run that loop 1000 times. What does the code /system look like. It is going to be more like evolution (fit to environment) than engineering (fit to purpose). It will be fascinating to watch nonetheless.

Sure, if all you ask it to do is fix bugs. You can also ask it to work on code health things like better organization, better testing, finding interesting invariants and enforcing them, and so on. It's up to you what you want to prioritize.

I have some healthy skepticism on this claim though. Maybe, but there will be a point of diminishing returns where these refactors introduce more problems than they solve and just cause more AI spending.

Code is always a liability. More code just means more problems. There has never been a code generating tool that was any good. If you can have a tool generate the code, it means you can write something on a higher level of abstraction that would not need that code to begin with.

AI can be used to write this better quality / higher level code. That's the interesting part to me. Not churning out massive amounts of code, that's a mistake.

Re: Coding agents have replaced every framework I used

#265

Post by LunaSea »

pawelduda wrote: post #201
HighGoldstein wrote: post #184

Earlier quoted context omitted.

> Correct. Those who wave away AI and refuse to engrain it into their workflows are going to be left behind in the dust. Similar to those who waved away crypto and are now left behind in the dust, yes?

I think Bitcoin and major cryptos outperformed a lot of assets over the last decade, so you could say it left some people behind in the dust, yes

Like being ratioed with a 50% price crash?

Re: Coding agents have replaced every framework I used

#267

Post by pengaru »

omnicognate wrote: post #241
woeirua wrote: post #197

Earlier quoted context omitted.

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.

What point have we reached? All I see is HN drowning in insufferable, identical-sounding posts about how everything has changed forever. Meanwhile at work, in a high stakes environment where software not working as intended has actual consequences, there are... a few new tools some people like using and think they may be a bit more productive with. And the jury's still out even on that. The initial excitement of LLMs…

It's no coincidence HN is hosted by a VC. VC-backed tech is all about boom-bust hype cycles analogous to the lever pull of a giant slot machine.

Re: Coding agents have replaced every framework I used

#268

Post by MrDarcy »

goostavos wrote: post #228
MrDarcy wrote: post #187

Earlier quoted context omitted.

This comment ignores the key insight of the article. Design is what matters most now. Design is the difference between vibe coding and software engineering. Given a good design, software engineers today are 100x more productive. What they produce is high quality due to the design. Production is fast and cheap due to the agents. You are correct, there will be a reckoning for large scale systems which are vibe coded. T…

>software engineers today are 100x more productive Somebody needs to explain to my lying eyes where these 100xers are hiding. They seem to live in comments on the internet, but I'm not seeing the teams around me increase their output by two orders of magnitude.

They are the people who have the design sense of someone like Rob Pike but lack his coding skill. These people are now 100x more capable than they were previously.

Re: Coding agents have replaced every framework I used

#270

Post by tenthirtyam »

rglover wrote: post #139

A significant number of developers and businesses are going to have an absolutely brutal rude awakening in the not too distant future. You can build things this way, and they may work for a time, but you don't know what you don't know (and experience teaches you that you only find most stuff by building/struggling; not sipping a soda while the AI blurts out potentially secure/stable code). The hubris around AI is goi…

My expectation is that there'll never be a single bust-up moment, no line-in-the-sand beyond which we'll be able to say "it doesn't work anymore."

Instead agent written code will get more and more complex, requiring more and more tokens (& NPU/GPU/RAM) to create/review/debug/modify, and will rapidly pass beyond any hope of a human understanding even for relatively simple projects (e.g. such as a banking app on your phone).

I wonder, however, whether the complexity will grow slower or faster than Moore's law and our collective ability to feed the AIs.

Post reply on HN