…and I still don’t get it. I paid for a month of Pro to try it out, and it is consistently and confidently producing subtly broken junk. I had tried doing this before in the past, but gave up because it didn’t work well. I thought that maybe this time it would be far along enough to be useful.

The task was relatively simple, and it involved doing some 3d math. The solutions it generated were almost write every time, but critically broken in subtle ways, and any attempt to fix the problems would either introduce new bugs, or regress with old bugs.

I spent nearly the whole day yesterday going back and forth with it, and felt like I was in a mental fog. It wasn’t until I had a full night’s sleep and reviewed the chat log this morning until I realized how much I was going in circles. I tried prompting a bit more today, but stopped when it kept doing the same crap.

The worst part of this is that, through out all of this, Claude was confidently responding. When I said there was a bug, it would “fix” the bug, and provide a confident explanation of what was wrong… Except it was clearly bullshit because it didn’t work.

I still want to keep an open mind. Is anyone having success with these tools? Is there a special way to prompt it? Would I get better results during certain hours of the day?

For reference, I used Opus 4.6 Extended.

  • Michal
    link
    fedilink
    arrow-up
    5
    arrow-down
    4
    ·
    6 days ago

    You can’t really just use Claude code raw. You have to give it detailed instructions, use Claude skills,observe results, update prompts. It can be just as consuming, but rather that doing the productive work, you’re just reviewing and correcting AI. People who have success using AI have invested time in their setup and are continuously adjusting it.

    • KeenFlame@feddit.nu
      link
      fedilink
      arrow-up
      3
      arrow-down
      3
      ·
      6 days ago

      But all in all extremely much faster. That’s the reason it is not useless. Everyone whines that it takes so much time when no it is not close to manual. It’s not a magic pill and you need the know how still, but no, it does not take “just as time consuming”. You are more productive. But yes, it is also more boring.

      • RamenJunkie@midwest.social
        link
        fedilink
        English
        arrow-up
        4
        arrow-down
        1
        ·
        6 days ago

        The biggest benefit from LLM even just belping with coding is I never have to open the hellsite of assholes that is Stack Overflow.

        Fuck SO forever.

          • RamenJunkie@midwest.social
            link
            fedilink
            English
            arrow-up
            2
            ·
            6 days ago

            This question has been asked 1000 times before if you were not so stupid you would have used the search and weeded through 10,000 results, most for outdated versions of your question, to find the answer but then you are using PHP instead of GoSwift++, the hot new flash in the pants .0001ms faster code language so of course you are stupid.

            – Average SO reply bot