CS480/680 Lecture 19: Attention and Transformer Networks
What it is
A university lecture from CS480/680 by Pascal Poupart on attention mechanisms and transformer networks, worked through on a chalkboard.
Why Hacker News recommends it
HN recommends it to newcomers as a clear explanation of attention, including the query/key/value intuition.
- 3 people recommended it
- 3 different months
- 0 strong recommendations
- first 2023, last 2023
What HN commenters said
“I would also recommend Pascal Poupart's talk [1] on Attention and Transformers.”
Chalkboard lecture working through attention and transformer details clearly.
abhgh, 2023-04 · Recommendation · in “Transformers from Scratch”
“These are very excellent resources”
Excellent resource on attention and transformers for newcomers.
elankart, 2023-05 · Recommendation · in “Ask HN: Can someone ELI5 Transformers and the “Attention is all we need” paper”
“Another good video on attention that tries to give a bit more intuition on the query/key/value stuff”
Gives more intuition on query/key/value in attention.
metanonsense, 2023-06 · Recommendation · in “Attention is Turing complete [pdf]”
Excerpts from Hacker News comments, linked to the originals. Summaries and labels were written by a language model from those comments.
Topics: attention, transformers, query key value, deep learning, nlp
Also recommended by the same people
talkAndrew Ng: Artificial Intelligence is the New ElectricityStanford Graduate School of Business · 2 HN recommenders · 2017–2019
explainerTransformers, the tech behind LLMs | Deep Learning Chapter 53Blue1Brown · 13 HN recommenders · 2024–2026
lectureDeep Dive into LLMs like ChatGPTAndrej Karpathy · 10 HN recommenders · 2025–2026
tutorialLet's build GPT: from scratch, in code, spelled out.Andrej Karpathy · 14 HN recommenders · 2023–2025
tutorialA Hackers' Guide to Language ModelsJeremy Howard · 8 HN recommenders · 2023–2024
talk[1hr Talk] Intro to Large Language ModelsAndrej Karpathy · 9 HN recommenders · 2023–2026
lectureSparks of AGI: early experiments with GPT-4Sebastien Bubeck · 7 HN recommenders · 2023–2026
lectureLet's build the GPT TokenizerAndrej Karpathy · 5 HN recommenders · 2024–2025