Most active commenters

    ←back to thread

    AI makes tech debt more expensive

    (www.gauge.sh)
    466 points 0x63_Problems | 12 comments | 14 Nov 24 16:01 UTC | HN request time: 1.035s | source | bottom
    Show context
    dcchambers ◴[14 Nov 24 17:12 UTC] No.42138389[source]▶
    LLM code gen tools are really freaking good...at making the exact same react boilerplate app that everyone else has.

    The moment you need to do something novel or complicated they choke up.

    This is why I'm not very confident that tools like Vercel's v0 (https://v0.dev/) are useful for more than just playing around. It seems very impressive at first glance - but it's a mile wide and only an inch deep.

    replies(2): >>42138440 #>>42138881 #
    1. holoduke ◴[14 Nov 24 17:15 UTC] No.42138440[source]▶
    If can you can create boilerplate code, logging, documentation, common algorithms by AI it saves you a lot of time which you can use on your specialized stuff. I am convinced that you can make yourself x2 by using an AI. Just use it in the proper way.
    replies(6): >>42138509 #>>42138590 #>>42139129 #>>42139261 #>>42140602 #>>42144895 #
    2. endemic ◴[14 Nov 24 17:20 UTC] No.42138509[source]▶
    I feel like we should get rid of the boilerplate, rather than have an LLM barf it out.
    replies(4): >>42138708 #>>42138721 #>>42138872 #>>42139816 #
    3. dcchambers ◴[14 Nov 24 17:25 UTC] No.42138590[source]▶
    I guess that's a good way to think of it. Despite not being very useful (currently, anyway) for certain types of complicated or novel work - they still are very useful for other types of work and can help reduce development toil.
    4. JohnFen ◴[14 Nov 24 17:34 UTC] No.42138708[source]▶
    Honestly, this bit about genAI being good at generating boilerplate is correct, but it always makes me wonder... is this really a thing that would save a ton of time? How much boilerplate are people writing? Only a small fraction of code that I write involves boilerplate.
    replies(1): >>42143667 #
    5. lowbloodsugar ◴[14 Nov 24 17:35 UTC] No.42138721[source]▶
    When I try to read code on GitHub that has the var or val keyword, I have no fucking idea what the types of the variables are. Sure, the compiler can infer, since it’s just ingested your entire code base, but I have a single page of text to look at.

    Some boilerplate is good.

    6. Terr_ ◴[14 Nov 24 17:46 UTC] No.42138872[source]▶
    Yeah, I often like to point out that our entire industry is already built on taking repeatable stuff and then abstracting it away.

    Boilerplate code exists when the next step is often to start customizing it in a unique and unpredictable way.

    7. guluarte ◴[14 Nov 24 18:05 UTC] No.42139129[source]▶
    or you just can start with a well maintained boilerplate
    8. croes ◴[14 Nov 24 18:14 UTC] No.42139261[source]▶
    Tested code libraries save time, AI generated code saves time at writing but the review takes more time because it’s foreign code.
    9. danenania ◴[14 Nov 24 18:57 UTC] No.42139816[source]▶
    There's an inherent tradeoff here though. Beyond a certain complexity threshold, code that leans toward more boilerplate is generally much easier to understand and maintain than code that tries to DRY everything with layers of abstraction, indirection, and magic.
    10. kibwen ◴[14 Nov 24 20:07 UTC] No.42140602[source]▶
    > I am convinced that you can make yourself x2 by using an AI.

    This means you're getting paid 2x more, right?

    ...Right?

    11. tisdadd ◴[15 Nov 24 03:13 UTC] No.42143667{3}[source]▶
    I just tend to use am extension such as https://marketplace.visualstudio.com/items?itemName=Huuums.v... for my boilerplate, as I can customize along the way for the project and not think hard. I have seen a lot of younger devs not using such a thing or already existing CLI and instead copy paste then rename, or try writing from scratch every time but slight differences... It is weird to me how many don't look for ways to automate boilerplate, as it has always been my default.
    12. xarope ◴[15 Nov 24 08:20 UTC] No.42144895[source]▶
    I hate to say this, but you probably can only achieve x2 using AI on the "easy" parts of your work. Going by the 80/20 rule:

      - 80% of your work is easy, and is accomplished in 20% of the time
  - 20% of your work is hard, and takes 80% of the time
    If you believe AI can x2 that easy 80% of your work, you have only managed to reduce that 20% to 10%. Someone else can work out that x improvement (1.11?), but it's nowhere near x2.