AI by Hand

(byhand.ai)

307 points | by sans_souse 18 hours ago

13 comments

  • iamnotarobotman 14 hours ago
    This is also recommended reading if you want to learn more about building LLMs from scratch: See:

    Train your own LLM - https://github.com/angelos-p/llm-from-scratch

    HN Discussion - https://news.ycombinator.com/item?id=48017948

  • vivzkestrel 4 hours ago
    - half the posts are locked

    - other half have no visualizations whatsoever

    - i have posted far better resources than this in the past collecting everything HN has over a 10 yr period on these subjects https://news.ycombinator.com/item?id=49183198

  • rustyminnow 16 hours ago
    https://www.byhand.ai/p/library

    > AI by Hand is the research publication of By Hand Research, founded by Prof. Tom Yeh. By Hand Research studies model interpretability and explainability at the math and algorithm level. Subscribers receive free new articles and join live seminars. Members get access to our full research library.

  • zhainya 17 hours ago
    I'm not sure what this is. Click past the subscribe page to get a bunch of links to descriptions of articles I could read if I was a subscriber?
    • lacoolj 15 hours ago
      Scroll all the way down and there's a video, it's a course he's making for deep-dive into how Qwen 3.6 works internally
    • mille562 17 hours ago
      Click "Later->" to bypass subscribe.
      • kevincox 9 hours ago
        I clicked "Back" to leave the user-hostile website.
        • arcfour 8 hours ago
          Yes. Convince me why your site is worth my attention, don't try to force it through a dark pattern and then try to justify why I should waste my time figuring it out.
        • shric 1 hour ago
          Welcome to Substack
      • dominotw 16 hours ago
        dont see later
        • PTOB 12 hours ago
          Eventually, none of us do.
  • slowin 12 hours ago
    I found Deep Learning by No Starch Press to be an excellent primer the foundation of AI:

    https://nostarch.com/deep-learning-visual-approach

  • docheinestages 1 hour ago
    I watched the intro video and all I saw were numbers in an Excel sheet. That doesn't make this fun. I'd rather have AI ELI5 it to me.
  • megadragon9 15 hours ago
    i created something similar a while back. Inspired by micrograd for showing the connection between math/calculus and code, then building along the way to a full NumPy deep learning library that I pretrained GPT-2 124M model with it. One way to learn is to trace through the PRs merged to the repo in chronological order.

    The philosophy is the same: "What I cannot create, I do not understand." https://github.com/workofart/ml-by-hand

    • dominotw 15 hours ago
      wow this is nice work. i am diving into this world and was hoping to this exact thing. i am going to look to see how you did it. ty for sharing.
  • copperx 15 hours ago
    My professor used this "by hand" technique when teaching quantum computation algorithms, so I have a soft spot for it.
    • alok-g 11 hours ago
      Nice! Is that also accessible online?
  • ThunderousVoid 13 hours ago
    I’d say bad UX design. It may or may not be something good behind the door. But why do I enter?
  • AdieuToLogic 8 hours ago
    See also:

      Foundations of Large Language Models[0]
    
    0 - https://arxiv.org/pdf/2501.09223v2
  • Damjanski 15 hours ago
    this is sick!
  • anthropic-dario 2 hours ago
    [dead]