Hacker News Reader

Comment by siliconc0w | Hacker News Reader

I don't really don't understand the appeal iterating on code in the browser away from the rest of the code base outside of cool demos. You really need to give the model context about your data model, code conventions, library choices, etc and be able to exercise it with tests to get to an acceptable result.

View on HN

I use ChatGPT/Claude in bed and when I otherwise don’t have a computer handy like going on walks. When developing isolated code it works just fine without having to specify a lot of detail. For example, I’m working on a Qt QML app backed by Rust but use the mobile interfaces to code up C++ components that are independent of the Rust logic and can be wired together from QML/Javascript. Since the LLMs already have lots of data on how that API works, I don’t need to feed it much info about my project. It actually helps enforce code boundaries.

Otherwise it’s mostly Cursor and Aider.

That's funny, I do the exact same thing. If I'm out and about or otherwise not at a computer, and I have an idea or solution to a bug I wanted to solve, I'll fire up an LLM on my phone (usually Claude these days) and basically brainstorm together the pros and cons, with code sometimes as well.

Curious -- does this happen to you often? Do you do that for your work (what pays your salary) or personal projects? Do you find it stressful to think about coding all the time?

Not for work, only for personal projects. No way I'd expend that type of effort for something like work, which I put in my 8 hours a day anyway. Stressful, not necessarily, unless there is some annoying bug I haven't been able to solve and deadlines are coming up, but again, that would be mainly for work, not (necessarily) for personal projects, unless I necessarily need to fix that bug to progress further.

I often need to write scripts to perform one off tasks.

Oh I need to grab all the products in the database and calculate how many projects they were a part of.

I'm already using ChatGPT to do this because it turns what used to be a half day task into a 1 hour one.

This will presumably speed it up more.

It’s cool for noobs and hobbyists.

And venture capital.

Yeah, that’s just hobbyists with more money.

Joking…but-only-a-little.

Not sure about that, they're all losing money. OpenAI recently raised 6.5 billion but is losing 5 billion a year, it's just not sustainable. In fact it's the local LLMs that are thriving, predictably because they run on your own hardware.

It’s losing money because it invests in growth. GPT4 has cost them 500mil and is making 3b revenue annually.

it's useful for my tampermonkey scripts that dont even exist in source control anywhere, and i have a friend that works in physics and has to write a ton of python code, but in really esoteric software platforms that are definitely not IDEs. they'd be copying and pasting code from a tool somewhere anyway.

Reply on news.ycombinator.com