Hacker News Reader

Comment by jimbokun | Hacker News Reader

I think LLMs have made a lot of developers forget the lessons in "Simple Made Easy":

https://www.youtube.com/watch?v=SxdOUGdseq4

LLMs seem to be really good at reproducing the classic Ball of Mud, that can't really be refactored or understood.

There's a lot of power in creating simple components that interact with other simple components to produce complex functionality. While each component is easy to understand and debug and predict its performance. The trick is to figure out how to decompose your complex problem into these simple components and their interactions.

I suppose once LLMs get really good at that skill, will be when we really won't need developers any more.

View on HN

> I suppose once LLMs get really good at that skill, will be when we really won't need developers any more.

I don't really get this argument. So when LLMs become "perfect" software developers are we just going to have them running 24/7 shitting out every conceivable piece of software ever? What would anyone do with that?

Or do you expect every doctor, electrician, sales assistant, hairdresser, train driver etc. to start developing their own software on top of their existing job?

What's more likely is a few people will make it their jobs to find and break down problems people have that could use a piece of software and develop said piece of software using whatever means they have available to them. Today we call these people software developers.

> Or do you expect every doctor, electrician, sales assistant, hairdresser, train driver etc. to start developing their own software on top of their existing job?

I started my software career by automating my job, then automating other people’s jobs. Eventually someone decided it would be easier to just hire me as a software engineer.

I just met with an architect for adding a deck onto my house (need plans for code compliance). He said he was using AI to write programs that he could use with design software. He demoed how he was using AI to convert his static renders into walkthrough movies.

you can tell them what to do though right? I think a lot of variance between people that say LLMs are useless and people that say they are useful is people that learn what they are good and bad at and can predict the quality of the output based on their input.

Like, I might ask an LLM on its opinion on the best way to break something down, to see if it 'thinks' of anything i havent, and then ask it to implement that. I wouldn't ask it to do the whole thing from scratch with no input on how to structure things.

> you can tell them what to do though right?

kind of.

> LLMs seem to be really good at reproducing the classic Ball of Mud, that can't really be refactored or understood.

This, but but only for code. I've seen "leaders" at work suggest that we "embrace" AI, even for handling production systems and managing their complexity. That's like saying: "We've built this obscure, inscrutable system, therefore we need another obscure, inscrutable system on top of it in order to understand it!". To me, this sounds deranged, but the amount of gaslighting that's going on also makes you think you're the only to believe that...

Reply on news.ycombinator.com