Hacker News Reader

Comment by primitivesuave | Hacker News Reader

FWIW, Peter Norvig also gave an updated take on what programming will look like with LLMs around 2 years ago. It did give me some hope back then, but with the development of Fables and Kimis and Sols I think it's truly anyone's guess where the art of programming will go.

https://www.youtube.com/watch?v=ia6aJIplmtc

View on HN

What most miss today is DX - Developer Experience, many (most?) devs don't want to become Prompt Engineers.

Another thing is that not many can afford Fable or similar and I don't think prices will go down, since it is already heavily subsidized?

I've always spent 90% of my work time thinking and sketching what the architecture should be to solve a problem. I find that once I've worked that out, it's actually still faster for me to code it than to try to explain it and refine it in prompts. And the code ends up more succinct and covers the edge cases I've already considered. If I need a fast script to do one thing, or unit tests, sure an LLM is faster at writing those. But for clean code, nothing beats knowing what you're going to write and just writing it yourself.

... and 10x that for long term maintenance and evolution of the code. When you read your code later, understanding of it comes more naturally/faster than somebody else's code (at least for me). I break down bigger problems into small chunks in one way, other folks may view things differently.

Exactly. At my previous work we spent an awful amount of time planning and architecting the solutions and refining them. No matter the person who prompted or the model used, the solution was never close to satisfactory.

Layers of unnecessary abstraction, weird decisions (like wth it used triple pointers once) hard to debug issues and obvious race conditions. Segfaults are through the roof and people are burned out and gasping hard to solve the bugs. I called their attention to this at the time and I was ignored and a bit laughed about. I left and couple months later I know others are too.

Another thing is that not many can afford a power loom or similar and I don't think prices will go down, since it is already heavily subsidized?

It's just energy and chips, and both can be made cheaper.

I think GP was referring to the industrial revolution and shares your sentiment.

Yet for some reason the price of both currently are going up and up.

What is the difference between a prompt engineer but a manager who talks with his charges to get some stuff designed?

There's a difference between charges and AI, in that the charges can be promoted to become managers and eventual decision makers which AI cannot be.

> Another thing is that not many can afford Fable or similar and I don't think prices will go down, since it is already heavily subsidized?

Not sure if API usage is heavily subsidized, especially for Fable. Chat interface for free users is subsidized for sure. I think we'll see how costly it is to deploy a big model now that Kimi K3 weights have become available.

Reply on news.ycombinator.com