Announcing a free Masterclass on RL for LLMs! This has been such a wonderful collaboration with some great people and personal heroes. 📅 Jan 15, 2026 (live) starting at 9 am PT / 12 pm ET Led by *The RAG Pack*: Jay Alammar, Maarten Grootendorst, Chris McCormick, and Joshua Starmer.

And here you have it! The cover of our “An Illustrated Guide to AI Agents” book! Why a Dolphin? The process of choosing cover animals is a closely guarded secret held deep within the legendary halls of O'Reilly. @jayalammar.bsky.social and I do not get to choose it, but we love it!

It’s time to guess the animal on the cover! Our cover animal is here, and @jayalammar.bsky.social and I are thrilled to celebrate it with an exciting contest for our upcoming release, An Illustrated Guide to AI Agents! Each person gets two guesses. Which animal do you think we got?

Drafts of the first two chapters of "An Illustrated Guide to AI Agents" are now available in Early Release on the O'Reilly platform!

The Illustrated Guide to AI Agents New book announcement! Thrilled that together with @maartengr.bsky.social , we're writing a new book titled “An Illustrated Guide to AI Agents” and published by @oreilly.bsky.social.

Excited to share that @jayalammar.bsky.social and I are writing the book “An Illustrated Guide to AI Agents” with @oreilly.bsky.social 🥳 Our new book will contain chapters on the fundamentals of agents (memory, tools, and planning), alongside more advanced concepts like RL and reasoning LLMs.

We've made so much extra (free!) content it could be its own book 😅 I counted more than 300 visuals across our illustrated and visual guides!

Happy to introduce my video on this alternative LLM architecture, Mamba and State Space Models! I wanted to do it for a while now and finally found the time to work on animating my visual guide. Expect to gain an intuitive understanding of this alternative LLM architecture. Link below 👇

Announcing BERTopic v0.17 🥳 This is a feature-packed update that includes the amazing Model2Vec, more interactive DataMapPlot functionalities, a method for lightweight installation, and much more!

Introducing "A Visual Guide to LLM Agents" 🤖 With over 60 (!) custom visuals, explore how Agents work, how they are created, their reasoning behavior, Model Context Protocol (MCP), Multi-Agent frameworks, and much more! Link below 👇

I discuss Model Context Protocol (MCP) in an upcoming article and figured I would share a small video illustrating a simplified flow!

Blazingly fast keyword generation with KeyBERT v0.9 and Model2Vec 🔥 I have been a big fan of the amazing embedding models by The Minish Lab, so I had to integrate them with KeyBERT. A release for the GPU-poor 😉

Did you know we continue to develop new content for the "Hands-On Large Language Models" book? There's now even a free course available with @deeplearningai.bsky.social!

A Visual Guide to Reasoning LLMs 💭 With over 40 custom visuals, explore DeepSeek-R1, the train-time compute paradigm shift, test-time compute techniques, verifiers, STaR, and much more! Link below

I'm incredibly grateful that "Exploring Language Models" has reached over 10k subscribers🔥 A big thank you to all readers who have enjoyed my visual guides to Mixture of Experts (MoE), Quantization, State Space Models (SSMs) and Mamba 🤗

I started working on animating "A Visual Guide to Mamba" and it's been a blast. Perhaps I should just add animations as a default to upcoming visual guides 😉

🍿 Introducing the animated "Visual Guide to Mixture of Experts (MoE)"! This was a blast to make and contains more in-depth descriptions than the original already had! Expect even more intuition as we break down visuals and discover the nuances behind MoE. www.youtube.com/watch?v=sOPD...

A Visual Guide to Mixture of Experts (MoE) in LLMs

YouTube video by Maarten Grootendorst

youtube.com

Next up, "A Visual Guide to Quantization"! Over 60 custom visuals explaining quantization of LLMs. Explore (a)symmetric quantization, dynamic/static quantization, post-training techniques (e.g., GPTQ and GGUF), quantization-aware training (e.g., BitNet 1.58b), and more! #llms #ai

👋 Hi, I'm Maarten. I enjoy demystifying LLMs in the form of visual guides. In the upcoming weeks, I'll be (re-)sharing some of my work if you are not already familiar with it. Today, with more than 50 illustrations: "A Visual Guide to Mamba"

A Visual Guide to Mamba and State Space Models

An Alternative to Transformers for Language Modeling

newsletter.maartengrootendorst.com