Top all-time · #549
Jay Alammar
Personal blog · jalammar.github.io · on HN as jalammaraidata
Jay Alammar's personal blog at jalammar.github.io covers ai and data. Since 2016, 108 different Hacker News readers have linked it 157 times, most often “The Illustrated Transformer”. It is still writing: the last post was on 2025-03-26, and you can follow it by feed.
Often recommended · 21 of 40 sampled comments recommend it?
Why HN links it
HN readers link Jay Alammar's illustrated, visual explainers of transformers, word2vec, GPT-2 and Stable Diffusion, and call them approachable, digestible introductions.
- Recommended for · 21 comments
- Called a favorite tutorial sequence and the most approachable, digestible intro to the transformer paper; the blog called fantastic and high quality.
Summarised by Claude from a sample of 40 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Visualizing machine learning one concept at a time.
Most-linked posts?
- The Illustrated Transformer32 people · 36 mentions · first linked 2018-06-27
- The Illustrated Transformer19 people · 20 mentions · first linked 2018-10-10
- The Illustrated Stable Diffusion9 people · 9 mentions · first linked 2022-10-04
- The Illustrated Word2vec8 people · 8 mentions · first linked 2019-03-27
- Visualizing Transformer Language Models: Illustrated GPT-27 people · 8 mentions · first linked 2019-08-12
- The Illustrated Retrieval Transformer6 people · 6 mentions · first linked 2022-03-10
- The Illustrated BERT: How NLP Cracked Transfer Learning5 people · 5 mentions · first linked 2018-12-03
- /5 people · 5 mentions · first linked 2018-11-01
- Visualizing a Neural Machine Translation Model (Mechanics of Seq2seq+Attention)3 people · 3 mentions · first linked 2018-05-09
- A Visual and Interactive Guide to the Basics of Neural Networks3 people · 3 mentions · first linked 2016-12-15
What Hacker News says?
Jay Alammar has my favorite sequence of tutorials from basic neural network math to GPT2. Particularly [0], [1], and [2] [0] http://jalammar.github.io/illustrated-transformer/ [1] http://jalammar.github.io/illustrated-gpt2/ [2] https://jalammar.github.io/visualizing-neural-machine-transl...
Comment linking /visualizing-neural-machine-translation-mechanics-of-seq2seq-models-with-attention/
on “GPT in 500 Lines of SQL”Submitted The Illustrated Stable Diffusion as a story · 629 points
HN discussion> This is probably an unpopular opinion There's a reason The Illustrated Transformer[1] was/is so popular: it made the original paper much more digestible. [1] https://jalammar.github.io/illustrated-transformer/
Comment linking /illustrated-transformer/
on “Visualizing Attention, a Transformer's Heart [video]”Submitted The Illustrated Transformer as a story · 475 points
HN discussionhttps://jalammar.github.io/illustrated-stable-diffusion/ His whole blog is fantastic. If you want more background (e.g. how transformers work) he's got all the posts you need
Comment linking /illustrated-stable-diffusion/
on “Stable Diffusion 3”Submitted How GPT3 Works – Visualizations and Animations as a story · 398 points
HN discussionMy problem with this is that it doesn't explain a lot. You can manually make a vector of a word and then step wise get up to word2vec approach and then document embedding. My post[1] does some of the first part and this great word2vec post[2] dives into it in more detail. [1] https://earthly.dev/blog/cosine_similarity_text_embeddings/ [2] https://jalammar.github.io/illustrated-word2vec/
Comment linking /illustrated-word2vec/
on “Embeddings are a good starting point for the AI curious app developer”Submitted A Visual Intro to NumPy and Data Representation as a story · 366 points
HN discussionFor the uninitiated, I can't recommend enough, The Illustrated Transformer: https://jalammar.github.io/illustrated-transformer/
Comment linking /illustrated-transformer/
on “Transformers Explained Visually”Submitted The Illustrated Word2vec as a story · 348 points
HN discussionThis skips over Bag of Words / N-Gram / TF-IDF and many other things, but paints a reasonable picture of the progression. 1. https://jalammar.github.io/illustrated-word2vec/ 2. https://jalammar.github.io/visualizing-neural-machine-transl... 3. https://jalammar.github.io/illustrated-transformer/ 4. https://jalammar.github.io/illustrated-bert/ 5. https://jalammar.github.io/illustrated-gpt2/ And from there it's mostly…
Comment linking /illustrated-gpt2/
on “Harper – an open-source alternative to Grammarly”Submitted A Visual and Interactive Guide to the Basics of Neural Networks as a story · 234 points
HN discussionHere is another take on visualizing transformers from Georgia Tech researchers: https://poloclub.github.io/transformer-explainer/ The Illustrated Transformer: https://jalammar.github.io/illustrated-transformer/ Sebastian Raschka, PhD has a post on the architectures: https://magazine.sebastianraschka.com/p/from-gpt-2-to-gpt-os... This HN comment has numerous resources: https://news.ycombinator.com/item?id=35712334
Comment linking /illustrated-transformer/
on “LLM Visualization”Submitted A Gentle Visual Intro to Data Analysis in Python Using Pandas as a story · 195 points
HN discussionKudos to Author for writing this. The author's other guide, https://jalammar.github.io/gentle-visual-intro-to-data-analy... is THE most approachable introduction to Pandas for Excel users like me who are "comfortable" with Python(disclaimer: Self taught EE/Hardware guy). I will definitely spend some time this weekend to go over this tome. Thanks again.
Comment linking /gentle-visual-intro-to-data-analysis-python-pandas/
on “The Illustrated Stable Diffusion”Submitted The Illustrated Word2Vec (2019) as a story · 180 points
HN discussionhttps://jalammar.github.io/images/stable-diffusion/article-F... Can you say with a straight face that this image (from the original paper) was intended to explain rather than obfuscate?
Comment linking /images/stable-diffusion/article-Figure3-1-1536x762.png
on “The Illustrated Stable Diffusion”Submitted The Illustrated Transformer (2018) as a story · 162 points
HN discussionLove the visual explainers for machine learning nowadays. The author has more here: https://jalammar.github.io/ Amazon has some highly interactive ones here: https://mlu-explain.github.io/ Google had: distill.pub Hope to see education in this space grow more.
Comment linking /
on “The Illustrated Stable Diffusion”Submitted The Illustrated BERT: How NLP Cracked Transfer Learning as a story · 98 points
HN discussionI personally enjoy https://jalammar.github.io/ and https://mlexplained.com/- For machine learning & deep learning stuff
Comment linking /
on “Ask HN: What are good solo developer blogs that you enjoy reading?”Submitted The Illustrated Retrieval Transformer as a story · 75 points
HN discussionFor the uninitiated, this is the same author as the many other "The Illustrated..." blog posts. A particularly popular one: https://jalammar.github.io/illustrated-transformer/ Always very high quality.
Comment linking /illustrated-transformer/
on “The Illustrated DeepSeek-R1”Submitted The Illustrated Transformer as a story · 65 points
HN discussionI agree that in this case the animated parts of the graphics were not needed, it's an easy pitfall to be distracted by the beautiful aspects of visualisations when crafting them. I feel the need to defend the author though, it's hard to make research accessible while still distilling valuable insight. I think his post on transformer networks [1] did a good job for example, and you'll appreciate the lack of animation…
Comment linking /illustrated-transformer/
on “How GPT3 Works – Visualizations and Animations”Submitted Visualizing Transformer Language Models: Illustrated GPT-2 as a story · 64 points
HN discussionAnd now I see that you've already started one! https://jalammar.github.io/gentle-visual-intro-to-data-analy...
Comment linking /gentle-visual-intro-to-data-analysis-python-pandas/
on “A Visual Intro to NumPy and Data Representation”Submitted Show HN: A Visual and Interactive Guide to the Basics of Neural Networks as a story · 63 points
HN discussionThe Dune references aren't limited to this article. :) The BERT article [1] has 'em too! [1] https://jalammar.github.io/illustrated-bert/
Comment linking /illustrated-bert/
on “The Illustrated Word2vec”Submitted Finding the Words to Say: Hidden State Visualizations for Language Models as a story · 55 points
HN discussion
