I use GPT3.5 for html/Laravel web site coding help. It sometimes sends me on wild goose chases while helping me debug, so I’m wondering if it’s any better for this use case in v4. Anyone know?

  • TropicalDingdong@lemmy.world
    link
    fedilink
    arrow-up
    7
    ·
    1 year ago

    Its great. I use both. I do coding at all kids of levels languages and environments and when I want boiler plate with out thinking about it, its mostly right.

  • OsrsNeedsF2P@lemmy.ml
    link
    fedilink
    arrow-up
    5
    ·
    edit-2
    1 year ago

    It won’t solve obscure problems, but it’s really good for generating lots of beginner-level code or answering beginner-level questions.

    Given that >75% of the coding you do is probably beginner level, I find it’s worth it, but you still need to know when to put it away and work on your own.

  • motsu@lemmy.world
    link
    fedilink
    arrow-up
    4
    ·
    1 year ago

    Significantly better code gen, but not to the point where it can make an application on its own. I tried using it for an embedded esp32 based project for fun, and while it could create mqtt support, the code for setting up WiFi / a small web backend / some HTML for a front end… It struggled with the application logic. Either way, it got about 70% of the way there

  • httpjames
    link
    fedilink
    English
    arrow-up
    3
    ·
    1 year ago

    GPT 4 can reason better with complex problems than 3.5

  • angelsomething@lemmy.one
    link
    fedilink
    arrow-up
    2
    ·
    edit-2
    1 year ago

    Personally I use perplexity.ai with gpt4 only because the answers it generates are preceded by a web search it does from what you ask it. I found it to be far more accurate just because of this.