Back to index
OtherSelf paced blog posts and video walkthroughs, plus a full length book and short courses that run a few hours each·Blog posts are free, the DeepLearning.AI and Cohere short courses are free, and the O'Reilly book is paid

Jay Alammar (The Illustrated Transformer and Hands-On Large Language Models)

4.6

If you have ever finally understood attention or embeddings, there is a fair chance Jay Alammar drew the picture that made it click. His illustrated explanations are the clearest free introduction to the internals of modern language models that exists, and his book and short courses extend that same visual clarity into hands on building.

What We Liked

  • The Illustrated Transformer and its companion posts are genuinely the reference explainers a lot of practitioners send to newcomers
  • Visual first teaching that turns attention, embeddings and diffusion from equations into pictures you can actually hold in your head
  • The core blog content is free, and the DeepLearning.AI and Cohere short courses he is involved in are free too
  • Hands-On Large Language Models, his O'Reilly book with Maarten Grootendorst, carries the same clarity into working code

What Could Be Better

  • The blog is a set of standalone explainers rather than a structured course, so you have to assemble a path yourself
  • It teaches you to understand the models far more than it drills you on production engineering
  • Some of the most famous posts predate the very latest architectures, so a few details are a little dated
  • You will still need a coding heavy resource alongside it to go from intuition to shipping something

Detailed review

Jay Alammar occupies an unusual and valuable spot in AI education, because he is less a course creator and more the person who drew the diagrams that an entire generation of practitioners learned attention from. The Illustrated Transformer, The Illustrated Word2Vec, The Illustrated Stable Diffusion and the rest of the series on his blog took papers that most people found impenetrable and rebuilt them as a sequence of pictures, walking one token or one vector through the model and showing what happens to it at each step. The effect is hard to overstate. When someone new to the field asks how attention works, the honest answer for years has been go read Alammar, and that is still largely true.

What makes it work is discipline about intuition. He resists the temptation to show off the maths and instead keeps asking what is this actually doing, so you come away with a mental animation of queries matching against keys rather than a memorised formula, and that picture is what makes the real papers readable afterwards. Beyond the free blog, he has widened his reach in two directions. First, he co authored Hands-On Large Language Models with Maarten Grootendorst for O'Reilly, which takes the same visual sensibility and pairs it with real code for tokenisation, embeddings, semantic search, prompt engineering and fine tuning, and it is one of the more approachable serious books on the topic.

Second, through his work at Cohere he has been involved in free short courses on DeepLearning.AI, including the semantic search and embeddings material, which are a nice practical complement to the reading. The honest limitations are the flip side of the strengths. This is not a packaged curriculum with a start and a finish, it is a brilliant collection of explainers you have to string together yourself, and because it leans so hard on understanding it will not on its own teach you the messy engineering of running these systems in production. A couple of the landmark posts are also old enough now that the frontier has moved past some of the specifics, though the core ideas they teach have aged remarkably well.

My take is simple. If you want to actually understand what is happening inside a language model rather than just call an API, start with Alammar, and do it early, because almost every other resource gets easier once his pictures are in your head. Then reach for the book when you want to build, and layer a more production focused course on top when you are ready to deploy.

[ final ]

The verdict.

Close to essential reading for anyone learning how transformers and large language models work under the hood. Treat the illustrated posts as the mental model everything else hangs on, pick up the book when you want to build, and pair both with a hands on engineering course when you are ready to ship.