Attention Is All You Need
What it is
Yannic Kilcher walks through the Attention Is All You Need paper, which introduced the Transformer, a sequence model based solely on attention without recurrence or convolutions. He reviews the architecture and the paper's translation results.
Why Hacker News recommends it
HN recommends it as an accessible, clear walkthrough of the transformer paper for people with some AI background.
- 4 people recommended it
- 4 different months
- 1 strong recommendations
- first 2020, last 2025
What HN commenters said
“I find the channel amazing explaining super complex topics in simple enough terms for people who have some background in AI.”
Detailed, simple explanation of the transformer paper
bfung, 2023-01 · Strong recommendation · in “The Transformer Family”
“for the theory bit you may find Yannic Kilcher's videos [0,1] helpful”
Video walkthrough of the Attention paper theory
kanche, 2020-10 · Recommendation · in “Rethinking Attention with Performers”
“For accessibility I recommend Yannic Kilcher video review of”
Accessible review of the Attention Is All You Need paper
visarga, 2021-12 · Recommendation · in “The potential of transformers in reinforcement learning”
“The Yannic kilcher review is quite good.”
Good review explaining transformers and attention
throwawaymaths, 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: transformers, attention, paper review, deep learning, nlp, yannic kilcher
Also recommended by the same people
courseRL Course by David Silver - Lecture 1: Introduction to Reinforcement LearningGoogle DeepMind · 9 HN recommenders · 2017–2026
interviewWhy Greatness Cannot Be Planned — Kenneth StanleyMachine Learning Street Talk · 4 HN recommenders · 2021–2024
demoHigh-Speed Robot HandHizook · 1 HN recommender · 2012–2020
explainerNeural Network Learns The Physics of Fluids and Smoke | Two Minute Papers #118Two Minute Papers · 1 HN recommender · 2017–2024
talkRAAIS 2017 - Simon Knowles, Co-Founder and CTO of GraphcoreThe Research and Applied AI Summit - RAAIS · 3 HN recommenders · 2017–2018
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