Ask HN: Anyone struggling to get value out of coding LLMs?

A c program is understandable even if it isn't efficient. It's also deterministic, or close enough that it shouldn't matter.

An llm project that can be generated from scratch every time is maybe understandable if you use very good prompts and a lot of grounding text. It is not deterministic unless you use zero temperature and stick with the same model forever. Something that's impossible now. Six months ago the state of the art model was deepseek r1.

There are two kinds of engineers.

Those who can’t stop raving about how much of a superpower LLMs are for coding, how it’s made them 100x more productive, and is unlocking things they could’ve never done before.

And those who, like you, find it to be an extremely finicky process that requires extreme amount of coddling to get average results at best.

The only thing I don’t understand is why people from the former group aren’t all utterly dominating the market and obliterating their competitors with their revolutionary products and blazing fast iteration speed.

I would never use an LLM for trying to generate a full solution to a complex problem. That's not what they're good at.

What LLMs are good at and their main value I'd argue, is nudging you along and removing the need to implement things that "just take time".

Like some days back I needed to construct a string with some information for a log entry, and the LLM that we have suggested a solution that was both elegant and provided a nicer formatted string than what I had in mind. Instead of spending 10-15 minutes on it, I spent 30 seconds and got something that was nicer than what I would have done.

It's these little things that add up and create value, in my opinion.

There’s also discussion here about an article written by David Crawshaw, the CTO of Tailscale:

> How I program with LLMs

— https://news.ycombinator.com/item?id=42617645

I find LLMs very useful when I need to learn something new, e.g. a new library or API, or a new language. It is much faster to just ask the LLM how to render text in OpenGL, or whatever, than read through tons of terrible documentation. Or, if I have a bunch of repetitive boilerplate stuff that I have no good templates for or cannot borrow from another part of the codebase. But when it comes to what I consider the actual 'work', the part of my codebase that is actually unique to the product I'm building, I rarely find them valuable in the "letting them write the code for me" sense.

I reflected once that very little of my time as a senior engineer is actually spent just banging out code. The actual writing of the code is never the hard part or time-consuming part for me - it's figuring out the right architecture, figuring out how to properly refactor someone else's hairball, finding performance issues, debugging rare bugs, etc. Yes, LLMs accelerate the process of writing the boilerplate, but unless you're building brand new products from scratch every 2nd week, how much boilerplate are you really writing? If the answer is "a lot", you might consider how to solve that problem without relying on LLMs!