Vectors are the fundamental way AI models understand and process information. Small vectors describe simple attributes, such as a point in a graph, while “high-dimensional” vectors capture complex information such as the features of an image, the meaning of a word, or the properties of a dataset. High-dimensional vectors are incredibly powerful, but they also consume vast amounts of memory, leading to bottlenecks in the key-value cache, a high-speed "digital cheat sheet" that stores frequently used information under simple labels so a computer can retrieve it instantly without having to search through a slow, massive database.

Vector quantization is a powerful, classical data compression technique that reduces the size of high-dimensional vectors...

archive.org

ghostarchive.org

[–] 2 points 11 months ago*

I was not aware how bad some of the new features have made youtube, since I almost never go there anymore "directly", I use alternative frontends like nadeko.net provides, so thanks for posting this. Once this loophole is closed, I will loose my favorite creators forever, if they do not migrate to other platforms, or start blogging like this guy.

  • source
  • [–] 1 point 11 months ago (1 child)

    This is a fairly interesting story, how do they manage to identify you with (high enough) certainty. People should shudder at the possibilities here. Maybe they track your screen resolution mouse-movement speed and even typing anomalies to detect you.

  • source
  • [–] 0 points 11 months ago* (1 child)

    example of using uv to install a python tool:

    uv tool install harlequin
    

    nice! It just works (harlequin.sh is a python program that allows to interact with databases using SQL qury langues, you can also load csv and json data)

  • source
  • [–] [S] 3 points 1 year ago (2 children)

    The guy has pretty big constraints on his setup: Voice Cloning AND open source …

    At the top of the leaderboard is Kokoro. Kokoro is an amazing model! Especially for a modest 82 Million (!) parameters and a mere 360 MB (!). However, like many models in this leaderboard - I can’t use it - since it doesn’t support voice cloning.

  • source
  • view more: next ›