←back to thread

Ask HN: Best practices using AI as an experienced web dev

9 points thebordella | 1 comments | 17 Nov 24 23:26 UTC | HN request time: 0.199s | source

As an Old, I came up learning the OG web dev languages - HTML, CSS, JS, PHP, etc. As a solo dev, I still largely work with these as natively as possible. But I am not a total dinosaur. I embraced jQuery in the early 2000's, Bootstrap scaffolding, and now often build reactive UI's using Vue 3.

Still, I continue to be picky about the many abstractions-of-abstractions that litter the dev landscape, mostly devised to drive their founders' business models.

AI-driven co-pilots are red hot now, and I want to evaluate their usefulness to my style of dev work. I've begun dabbling with services like Codeium and Claude, particularly within VSCode.

At first these AI tools seem exciting. A whole function conjured out of thin air from a short prompt! But the more I test drive, the more I find that I'm spending my time trying to craft prompts that are accurate enough to generate the code I want. Whereas I could be using that time to just conceive and write the code myself.

If you are not already well-versed in your coding languages, these AI tools must save a ton of time and effort. My question is - what about you devs who are already proficient in your languages of choice? How do you leverage AI co-pilots to maximize their usefulness without just falling into the "distracted by another abstraction" hole?

Show context
yen223 ◴[18 Nov 24 16:01 UTC] No.42173649[source]▶
I use LLMs to write "secondary" code. Things like deployment scripts, autoformatters, Github Actions, Dockerfiles or Kubernetes config. Stuff that isn't strictly part of the main web project, but is still valuable to have. I use LLMs there because

a) those tend to be boilerplate, and LLMs are great for boilerplate, and

b) code quality doesn't really matter too much, and

c) those tend to be written in languages that you may not be well-versed in, since they usually aren't in the "primary" language of the project

replies(1): >>42226007 #
1. hack_fraud13 ◴[24 Nov 24 05:03 UTC] No.42226007[source]▶
Yeah ironically enough I think what’s cutting edge about LLMs is their ability to let you spend more time in the command line and less in the gui. With AI writing the time cost/opportunity cist of writing shell scripts is so low, even if you find yourself working on a machine you’re not used to (e.g. Windows for linux users).