hackertube.io

Large Language Models from scratch

Graphics in 5 Minutes · explainer · Watch on YouTube

LLMs & generative AIMachine learning & deep learning

What it is

A short cartoon explaining how language models like ChatGPT work, from autocomplete and conditional probabilities to neural networks, gradient descent and backpropagation. It shows how networks act as universal function approximators.

Why Hacker News recommends it

HN recommends it as a quick, non-dumbed-down way to get up to speed on how LLMs are built.

  • 3 people recommended it
  • 2 different months
  • 2 strong recommendations
  • first 2023, last 2024

What HN commenters said

  1. “I highly recommend this video by Steve Seitz”

    Quick overview of how LLMs are built without dumbing down

    sainez, 2023-04 · Strong recommendation · in “A Completely Non-Technical Explanation of Deep Learning”

  2. “I had never made the connection between Fourier Series, Taylor Series, and Neural Networks”

    Shows neural nets approximate functions like Fourier and Taylor series

    peter_d_sherman, 2023-05 · Strong recommendation · in “Large Language Models from scratch (2022)”

  3. “At least they helped me get up to speed fast.”

    Short video that quickly gets you up to speed on LLMs

    runetech, 2023-05 · Recommendation · in “Ask HN: Can someone ELI5 Transformers and the “Attention is all we need” paper”

Excerpts from Hacker News comments, linked to the originals. Summaries and labels were written by a language model from those comments.

Topics: llm, neural networks, gradient descent, transformers, language modeling

Also recommended by the same people