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

Eight years of wanting, three months of building with AI

lalitm.com

Post reply on HN
Print view View original

131–140 of 349 posts

Re: Eight years of wanting, three months of building with AI

#131

Post by klabb3 »

zozbot234 wrote: post #92
sharperguy wrote: post #81

Earlier quoted context omitted.

It's actually common for human-written projects to go through an initial R&D phase where the first prototypes turn into spaghetti code and require a full rewrite. I haven't been through this myself with LLMs, but I wonder to what extent they could analyse the codebase, propose and then implement a better architecture based on the initial version.

If you write that first prototype in Rust, with the idiomatic style of "Rust exploratory code" (lots of defensive .clone()ing to avoid borrowck trouble; pervasive interior mutability; gratuitous use of Rc or Arc to simplify handling of the objects' lifecycle) that can often be incrementally refactored into a proper implementation. Very hard to do in other languages where you have no fixed boilerplate marking "this is…

Rust is a language for fast prototyping? That’s the one thing Rust is absolutely terrible at imo, and I really like the production/quality/safety aspects of Rust.

Re: Eight years of wanting, three months of building with AI

#132

Post by throwatdem12311 »

0xbadcafebee wrote: post #118
throwatdem12311 wrote: post #100

Earlier quoted context omitted.

For me it’s just a matter of “does this actually save me time at all?” If it generates the slop version in a week but it takes me 3 more weeks to clean it up, could I have I just done it right the first time myself in 4 weeks instead? How much money have I wasted in tokens?

A car saves you time in getting to and from the store. But if you don't learn to drive, and just hop in the car and press things, you're going to crash, and that definitely won't save you time. Cars are also more expensive than walking or a bike, yet people still buy them.

I already know how to drive stick (trad coding), I don’t feel like I’m gaining much by switching to automatic transmission.

Re: Eight years of wanting, three months of building with AI

#133

Post by wiether »

vaylian wrote: post #125
throwaway47001 wrote: post #111

I appreciate these kind of fact-based posts. Thank you for this. Unfortunately, AI seems to be divisive. I hope we will find our way back eventually. I believe the lessons from this era will reverberate for a long time and all sides stand to learn something. As for me, I can’t help but notice there is a distinct group of developers that does not get it. I know because they are my colleagues. They are good people and…

> because they are such laggards I am a technologist. But I am seriously concerned about the ecological consequences of the training and usage of AI. To me, the true laggards are those, who have not understood yet, that climate change requires a prudent use of our resources. I don't mind people having fun or being productive with AI. But I do mind it when AI is presented as the only way of doing things.

Don't waste time thinking about the comment you replied to.

Only an AI would bother to create a throwaway account to post such a shallow comment that is mostly fearmongering to push people to use AI.

Re: Eight years of wanting, three months of building with AI

#134

Post by stepan_l »

I had the same experience, been working on my project for a few months and it started very easy and then I lost control of the code base. Had to rewrite a lot of things. The code AI writes does not look bad, but there is something wrong about it. It just does not feel right. You still need to steer it a lot. But I am very happy that I could write a quite complex project with almost no dependencies at all. Only used Electron. I don't even use npm. That is very promising how far you can get without relying on any libraries/frameworks. You can check it here https://github.com/AgentWFY/AgentWFY MIT license.

Re: Eight years of wanting, three months of building with AI

#136

Post by zozbot234 »

klabb3 wrote: post #131
zozbot234 wrote: post #92

Earlier quoted context omitted.

If you write that first prototype in Rust, with the idiomatic style of "Rust exploratory code" (lots of defensive .clone()ing to avoid borrowck trouble; pervasive interior mutability; gratuitous use of Rc or Arc to simplify handling of the objects' lifecycle) that can often be incrementally refactored into a proper implementation. Very hard to do in other languages where you have no fixed boilerplate marking "this is…

Rust is a language for fast prototyping? That’s the one thing Rust is absolutely terrible at imo, and I really like the production/quality/safety aspects of Rust.

It's not specialized to fast prototyping for sure, but you can use for that with the right boilerplate.

Re: Eight years of wanting, three months of building with AI

#137

Post by viktorianer »

dirtbag__dad wrote: post #45

> Tests created a similar false comfort. Having 500+ tests felt reassuring, and AI made it easy to generate more. But neither humans nor AI are creative enough to foresee every edge case you’ll hit in the future; there are several times in the vibe-coding phase where I’d come up with a test case and realise the design of some component was completely wrong and needed to be totally reworked. This was a significant con…

[flagged]

Re: Eight years of wanting, three months of building with AI

#138

Post by ffsm8 »

devmor wrote: post #99
ffsm8 wrote: post #94

Earlier quoted context omitted.

really? have you ever learned a skill? Like carving, singing, playing guitar, playing a video game, anything? It's easy to get better at it without understanding why you're better at it. As a matter of fact, very very few people master the discipline enough to be able to grasp the reason for why they're actually better Most people just come up with random shit which may or may not be related. Which I just abstained f…

You can get better at something without understanding why, but you should be able to think about it and determine why fairly easily. This is something everyone who cares about improving in a skill does regularly - examine their improvement, the reasons behind it, and how to add to them. That’s the basis of self-driven learning.

Not really. I can obviously say something, like you learn which features the models are able to actually implement, and you learn how to phrase and approach trickier features to get the model too do what you want.

And that's not really explainable without exploring specific examples. And now we're in thousands of words of explanation territory, hence my decision to say it's hard to put it into words.

Re: Eight years of wanting, three months of building with AI

#139

Post by airstrike »

0xbadcafebee wrote: post #126
airstrike wrote: post #42

Earlier quoted context omitted.

vibing is different from... steering AI as it goes so it doesn't make fundamentally bad decisions

Both of these are not really the right way to use AI to code with. There are two basic ways to code with AI that work: 1. Autocomplete. Pretty simple; you only accept auto-completes you actually want, as you manually write code. 2. Software engineering design and implementation workflow. The AI makes a plan, with tasks. It commits those plans to files. It starts sub-agents to tackle the tasks. The subagents create te…

#2 does not negate my steering suggestion, so I'm not sure how you can conclude nobody thinks it's a real thing that works

also Claude Code is notoriously poorly built, so I wouldn't tout it as SOTA

Re: Eight years of wanting, three months of building with AI

#140

Post by zozbot234 »

0xbadcafebee wrote: post #126
airstrike wrote: post #42

Earlier quoted context omitted.

vibing is different from... steering AI as it goes so it doesn't make fundamentally bad decisions

Both of these are not really the right way to use AI to code with. There are two basic ways to code with AI that work: 1. Autocomplete. Pretty simple; you only accept auto-completes you actually want, as you manually write code. 2. Software engineering design and implementation workflow. The AI makes a plan, with tasks. It commits those plans to files. It starts sub-agents to tackle the tasks. The subagents create te…

> when Claude fucking Code has been produced this way for like 6 months

And people can look at the results (illegally) because that whole bunch of code has been leaked. Let's just say it's not looking good. These are the folks who actually made and trained Claude to begin with, they know the model more than anyone else, and the code is still absolute garbage tier by sensible human-written code quality standards.

Post reply on HN