• 1 post
  • 21 comments
Joined 2 years ago
Cake day: June 13th, 2024
  • You want to know why i assumed the worst? Because it was left unspecified.

    I’m not going to single handily vet every single slop project like a sleuth. I expect honest disclosures. If they’re not, then there’s no room in a good faith community like this.

    I assume the worst until specified otherwise. Why is it on me to be a detective, and not just you know, say how AI was used in the project in the post. That would have prevented this entire conversation.

    I see no reason not to assume something isn’t vibe coded until specified otherwise. Because it’s a filter that helps me filter out this community. I read a post, and maybe a couple of comments. If its not specified, I move on.

    If you want better disclosures, then do that. Dont wait for mods, just fucking do it yourself.

  • It doesn’t look like its in bad faith at all.

    With that label, I default to vibe code unless specified otherwise in the post. Its not really up to use to be invstegators. Especially non programmers. They rely on questions like that to understand if its vibe coded or not.

    Its like saying people should read the scripts they download before they run them. And like yes, but if the goal is adoption, you need to account for those who dont know what to look for.

  • But you can’t?

    It didn’t reason its way down a branch, it made coinflips all along the way. So its not actually thinking, just weighted coin flips. There’s no ‘why’ it chose a branch. Just the result of a coin flip.

    You can’t ask a coin why it chose heads. You can unroll the physics of it all day long til the cow comes home. But it still doesn’t help you on the next one.

  • No… No they’re not. Either that or nerual nets are even dumber than I thought. My understanding was emulating nodes of information like brains do. Thats not probabilities. But willing to be wrong if you can bring sources. The connection between points in probability doesn’t make sense. Thats a nonsense statement.

    Thats also no how simulated annealing works. The temperature value is roughly the probability it will pick a different, less optimal step, in order to try and find better alternative paths. The temperature value is roughly the probability of trying something ‘random’. Not deterministic at all. The temperature value is lowered with time and progression. Its known the entire time, but its still a weighted coin flip that determines which path to take.

    https://en.wikipedia.org/wiki/Simulated_annealing

  • For training maybe. But execution as far as i know are just a bunch of probabilities chucked into matrices. Back in my physcos days I could u derstand the math, but not today.

    Also what needs citing, that nodes translate to debugable, reproducible outputs.

    Because again, it’s all probablilties under the hood.