• 0 Posts
  • 17 Comments
Joined 1 year ago
cake
Cake day: October 31st, 2023

help-circle


  • Everything. Or just this.

    I need to get my car fixed so I can leave.
    I need to empty out my car so I can get it fixed.
    I need my car fixed so I can empty it out.
    I need to go shopping so I have food.
    I need to bike to go shopping.
    I need to eat to bike.
    I need food to eat.
    I need to get paniers and a rack for a bike so I’m not so reliant on my car.
    I need to get my car fixed so I’m not so reliant on a bike.
    I need to find a therapist to feel safe.
    I need to set up a computer to email every provider in a whole state to try to find one.
    I need to set up a computer so I can work.
    I need to feel safe to set up a computer.

    Everything seems like the most important thing to do right now. I know the actual only important thing to do today is get food for at least 3 days so I can have at least 1 day when that’s not a problem. I need someone to tell that to even though I’d already thought of that and thought that I have nobody to tell it to, so thank you for asking.










  • Whether or not you use downvotes doesn’t really matter.

    If what you like is well represented by the Boba drinkers and the Boba drinkers disproportionally don’t like Cofee then Cofee will be disproportionally excluded from the top of your results. Unless you explore deeper the Cofee results will be pushed to the bottom of your results. And any that happen to come to the top will have arrived there from broad appeal and will have very little contribution to thinking you like Cofee.

    If you don’t let the math effectively push things away that are disliked by the people who like similar things as you then everything will saturate at maximum appeal and the whole system does nothing.


  • There’s two problems. The first is that those other things you might like will be rated lower than things you appear to certainly like. That’s the “easy” problem and has solutions where a learning agent is forced to prefer exploring new options over sticking to preferences to some degree, but becomes difficult when you no longer know what is explored or unexplored due to some abstraction like dimension reduction or some practical limitation like a human can’t explore all of Lemmy like a robot in a maze.

    The second is that you might have preferences that other people who like the same things you’ve already indicated a taste for tend to dislike. For example there may be other people who like both Boba and Cofee but people who like one or the other tend to dislike the other. If you happen to encounter Boba first then Cofee will be predicted to be disliked based on the overall preferences of people who agree with your Boba preference.


  • No, not as simply as that. That’s the basic idea of recommendation systems that were common in the 1990s. The algorithm requires a tremendous amount of dimensionality reduction to work at scale. In that simple description it would need a trillion weights to compare the preferences of a million users to a million other users. If you reduce it to some standard 100-1000ish dimensions of preference it becomes feasible, but at the low end only contains about as much information as your own choices about subscribed to or blocked communities (obviously it has a much lower barrier of entry).

    There’s another important aspect of learning that the simple description leaves out, which is exploration. It will quickly start showing you things you reliably like, but won’t experiment with things it doesn’t know you’d like or not to find out.