hackertube.io

AI Language Models & Transformers - Computerphile

Computerphile · explainer · Watch on YouTube

LLMs & generative AIMachine learning & deep learningComputer vision, speech & NLP

What it is

Rob Miles explains on Computerphile how language models generate plausible text and how transformers improved on recurrent networks, with a look at what comes next.

Why Hacker News recommends it

Pointed to as an accessible early explanation of transformers and attention for newcomers.

  • 3 people recommended it
  • 3 different months
  • 0 strong recommendations
  • first 2022, last 2025

What HN commenters said

  1. “This video by Computerphile is a great overview of transformers and how we got to this point [0].”

    Overview of transformers and how earlier recurrent networks forgot information

    cercatrova, 2022-08 · Recommendation · in “A demo of GPT-3's ability to understand long instructions”

  2. “Those Computerphile videos[0] by Rob Miles helped me understand transformers.”

    Rob Miles explains transformers and the attention paper

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

  3. “there are a number of Computerphile videos which are quite informative.”

    Early Computerphile introduction to what language model systems do

    mhast, 2025-02 · Recommendation · in “Modern-Day Oracles or Bullshit Machines? How to thrive in a ChatGPT world”

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

Topics: transformers, language models, attention, rob miles, computerphile

Also recommended by the same people