←back to thread

Generative AI coding tools and agents do not work for me

(blog.miguelgrinberg.com)
399 points nomdep | 1 comments | 17 Jun 25 00:33 UTC | HN request time: 0.21s | source
Show context
dvt ◴[17 Jun 25 03:18 UTC] No.44295444[source]▶
I'm actually quite bearish on AI in the generative space, but even I have to admit that writing boilerplate is "N" times faster using AI (use your favorite N). I hate when people claim this without any proof, so literally today this is what I asked ChatGPT:

    write a stub for a react context based on this section (which will function as a modal):
    ```
        <section>
         // a bunch of stuff
        </section>
    ```
Worked great, it created a few files (the hook, the provider component, etc.), and I then added them to my project. I've done this a zillion times, but I don't want to do it again, it's not interesting to me, and I'd have to look up stuff if I messed it up from memory (which I likely would, because provider/context boilerplate sucks).

Now, I can just do `const myModal = useModal(...)` in all my components. Cool. This saved me at least 30 minutes, and 30 minutes of my time is worth way more than 20 bucks a month. (N.B.: All this boilerplate might be a side effect of React being terrible, but that's beside the point.)

replies(2): >>44295643 #>>44297881 #
1. Winsaucerer ◴[17 Jun 25 04:00 UTC] No.44295643[source]▶
This kind of thing is my main use, boilerplate stuff And for scripts that I don't care about -- e.g., if I need a quick bash script to do a once off task.

For harder problems, my experience is that it falls over, although I haven't been refining my LLM skills as much as some do. It seems that the bigger the project, the more it integrates with other things, the worse AI is. And moreover, for those tasks it's important for me or a human to do it because (a) we think about edge cases while we work through the problem intellectually, and (b) it gives us a deep understanding of the system.