Jay Alammar

Visual explanations of transformers, attention, and embeddings.

Recommends

Books, films, shows, and podcasts they point to — tap a source to read the passage.

Books · 2

book

Tafakkurlarni modellashtirish

Kaggle bilan yoki kaggle'siz. Shudir masalaJay Alammar

Context

Jay Alammar refers to this work as a source of his pedagogical framework for teaching supervised machine learning concepts.

““Tafakkurlarni modellashtirish” kitobimda tushuntirganimdek, mashinali o‘rganish musobaqalari nazorat ostidagi (supervised) mashinaviy o‘rganishning asosiy g‘oyalarini o‘rgatishning eng samarali usulidir.”

book

Fan uchun nazorat ostidagi mashinaviy o‘rganish

Memlar inqiroziJay Alammar

Context

Jay Alammar recommends this book because it provides a new chapter on how to document and present machine learning results in applied science, offering free access to the content.

“Timo va men "Fan uchun nazorat ostidagi mashinaviy o‘rganish" kitobimizning yangi bobini e’lon qildik.”

Sort

Jay Alammar11mo

newsletter.languagemodels.co/p/the-illust...

Jay Alammar11mo

Inside NeurIPS 2025: The Year’s AI Research, Mapped New blog post! NeurIPS 202

Inside NeurIPS 2025: The Year’s AI Research, Mapped New blog post! NeurIPS 2025 papers are out—and it’s a lot to take in. This visualization lets you explore the entire research landscape interactively, with clusters and @cohere.com LLM-generated explanations that make it easier to grasp.

Jay Alammar12mo

We're also eager to hear what you'd like to see in such a book. What concepts do

We're also eager to hear what you'd like to see in such a book. What concepts do you think are central to understanding, building, and properly using AI agents? Early release coming soon!

Jay Alammar12mo

This will be our most visually-rich project yet. We will drill into the main con

This will be our most visually-rich project yet. We will drill into the main concepts for understanding and building AI agents -- likely the most promising area of AI as of today. It will cover tools, memory, code generation, reasoning, multimodality, RLVR/GRPO, and much more.

Jay Alammar12mo

The Illustrated Guide to AI Agents New book announcement! Thrilled that togeth

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.

Jay Alammar14mo

The Illustrated GPT-OSS New post! A visual tour of the architecture, message f

The Illustrated GPT-OSS New post! A visual tour of the architecture, message formatting, and reasoning of the latest GPT. newsletter.languagemodels.co/p/the-illust...

Jay Alammar17mo

The legendary John Carmack at #upperbound: - Current AI focus is RL (with Richar

The legendary John Carmack at #upperbound: - Current AI focus is RL (with Richard Sutton) solving Atari games - Thinking in line with the Alberta Plan. - It was a misstep to start working too low-level (e.g., at the cuda level). I kept stepping up the stack chain until now in pytorch

Jay Alammar19mo

🔭 Eynshteyn sun’iy intellekt modeli

“Qisqartirilgan XXI asr” yo‘lida nimani ko‘zdan qochirayotganimiz haqida

Jay Alammar20mo

Learn how ChatGPT and DeepSeek models work: How Transformer LLMs Work [Free Course]

Enroll for free now: https://bit.ly/4aRnn7Z Github Repo: https://github.com/HandsOnLLM/Hands-On-Large-Language-Models We're ecstatic to bring you "How Transformer LLMs Work" -- a free course with ~90 minutes of video, code, and crisp visuals and animations that explain the modern Transformer architecture, tokenizers, embeddings, and mixture-of-expert models. @MaartenGrootendorst and I have developed a lot of the visual language over the last several years (tens of thousands of iterations for hundreds of figures) for the book. This was informed by many incredible colleagues at Cohere, C4AI, a

Jay Alammar20mo

The Illustrated DeepSeek-R1 Spent the weekend reading the paper and sorting thr

The Illustrated DeepSeek-R1 Spent the weekend reading the paper and sorting through the intuitions. Here's a visual guide and the main intuitions to understand the model and the process that created it. newsletter.languagemodels.co/p/the-illust...

Jay Alammar21mo

Alphaxiv is an awesome way to discuss ML papers -- often with the authors themse

Alphaxiv is an awesome way to discuss ML papers -- often with the authors themselves. Here's an intro and demo by @rajpalleti.bsky.social we shot at #Neurips2024 www.youtube.com/watch?v=-Kwl...

Jay Alammar21mo

AlphaXiv - a great place to discuss ML papers

Alphaxiv is an awesome way to discuss ML papers -- often with the authors themselves. Here's an intro and demo by Raj Palleti we shot at Neurips2024.

Jay Alammar21mo

It contains a notebook per chapter containing all the code examples in the book.

It contains a notebook per chapter containing all the code examples in the book. Check it out here: github.com/HandsOnLLM/H...

Jay Alammar21mo

Floored that the repo for Hands-On Large Language Models is now at 3.6k Github s

Floored that the repo for Hands-On Large Language Models is now at 3.6k Github stars! And excited that professors are starting to use the book to teach LLM courses. Reach out to us if we can be of assistance! And if you've liked the book, leave us a review on Amazon or Goodreads!

Jay Alammar21mo

SWE-Bench has been one of the most important tasks measuring the progress of age

SWE-Bench has been one of the most important tasks measuring the progress of agents tackling software engineering in 2024. I caught up with two of its creators, @ofirpress.bsky.social and Carlos E. Jimenez to share their ideas on the state of LLM-backed agents. www.youtube.com/watch?v=bivZ...

Jay Alammar21mo

SWE-Bench authors reflect on the state of LLM agents at Neurips 2024

The SWE-bench task measures AI agents on software engineering tasks at the level of a github issue. It was one of the most important tasks measuring the progress of agents tackling software engineering tasks in 2024. We caught up with two of its creators, Ofir Press and Carlos E. Jimenez, to share their ideas on the state of LLM-backed agents. --- Check out our book: https://www.llm-book.com/ Mailing List: https://newsletter.languagemodels.co/ Bluesky: https://bsky.app/profile/jayalammar.bsky.social Twitter: https://twitter.com/JayAlammar Blog: https://jalammar.github.io/

Jay Alammar22mo

Good morning #NeurIPS2024! Stop by the @cohere.com booth at 3PM today (Thursday)

Good morning #NeurIPS2024! Stop by the @cohere.com booth at 3PM today (Thursday) for a signed copy of Hands-On Large Language Models - it will introduce you to LLMs, their applications, as well as Cohere's Embed, Rerank, and Command-R models. Come early as quantities are limited!

Jay Alammar22mo

I'll be in the Cohere #NeurIPS2024 booth most of this afternoon. Come say hi, as

I'll be in the Cohere #NeurIPS2024 booth most of this afternoon. Come say hi, ask questions, and yes, we're hiring! Tomorrow I'll be signing copies of my book at 3PM! Limited copies available!

Jay Alammar22mo

Hi NeurIPS! Explore ~4,500 NeurIPS papers in this interactive visualization: j

Hi NeurIPS! Explore ~4,500 NeurIPS papers in this interactive visualization: jalammar.github.io/assets/neuri... (Click on a point to see the paper on the website) Uses @cohere.com models and @lelandmcinnes.bsky.social's datamapplot/umap to help make sense of the overwhelming scale of NeurIPS.

Jay Alammar22mo

Sure to be thought provoking. The previous interview had fascinating thoughts on

Sure to be thought provoking. The previous interview had fascinating thoughts on scifi (Dune Vs. Foundation), on AI competition for AI safety, and on successful scifi as a self-preventing prophecy.

Jay Alammar23mo

Ko‘rsatkichlar SI uchun katta muammo

Ko‘rsatkichlarni o‘ylamasdan optimallashtirish turli xil jiddiy zararlarga olib kelishi va hozirgi SI yondashuvlarining aksariyati ko‘rsatkichlarni optimallashtirishga aylangani haqida.

Jay Alammar24mo

Memlar inqirozi

Nima uchun ChatGPT doimo bir xil narsalarni tavsiya qiladi?

Jay Alammar25mo

Masshtab: AI sohasidagi bugungi holat

Turli avlod modellariga nazar...

Jay Alammar25mo

Kaggle bilan yoki kaggle'siz. Shudir masala

Oxir-oqibat, bu IT bo‘limidagi Bobga bog‘liq.

Jay Alammar30mo

Building LLM Agents with Tool Use

Tool use is a method whichs allows developers to connect Cohere's Command models to external tools like search engines, APIs, databases, and other software tools. Just like how Retrieval-Augmented Generation (RAG) allows a model to use an external data source to improve factual generation, tool use is a capability that allows retrieving data from multiple sources. But it goes beyond simply retrieving information and is able to use software tools to execute code, or even create entries in a CRM system. In this video, we'll see how we can use two tools to create a simple data analyst agent that

Jay Alammar31mo

Ha, siz backprop’ni tushunishingiz kerak

Haqiqiy maqola Andrey Karpati tomonidan karpathy.medium.com saytida 2016-yil 20-dekabrda e’lon qilingan.

Jay Alammar33mo

Illyustratsiyali BERT, ELMo va boshq.

NLP qanday qilib Transfer O‘rganishni (Transfer Learning) ishg‘ol qilgani haqida!

Jay Alammar33mo

AI muhandisining yuksalishi

Favqulodda paydo bo‘layotgan imkoniyatlar yangi sarlavhani yaratmoqda: shunchaki Prompt muhandisligidan tashqariga chiqib, haqiqiy dasturlar yozishimiz kerak.

Jay Alammar33mo

Software 2.0

Dasturlashni qayta tasavvur qilish: SI qanday qilib dasturiy ta’minotni ishlab chiqishni o‘zgartiradi.

Jay Alammar33mo

Illyustratsiyali Transformerlar

Mashinalar tilni tushunishni qanday "o‘rganadilar": transformerlar arxitekturasining asosiy tushunchalarini ko‘rib chiqish. Mashhur "The Illustrated Transformer" o‘zbek tilida!

Jay Alammar34mo

Neyron mashinaviy tarjima modellarini vizualizatsiya qilish (E’tiborga asoslangan seq2seq modellari mexanikasi)

Haqiqiy maqola Jey Alammar tomonidan jalammar.github.io saytida 2018-yil 9-mayda e’lon qilingan.

Jay Alammar34mo

Sizda hali ham imkon bor (SIga o‘tish uchun)

Sun’iy intellekt (SI) sohasida so‘nggi 5 yil ichida sodir bo‘lgan muhim hodisalar va qanday qilib yetib olish haqida.

Jay Alammar34mo

Achchiq saboq (The bitter lesson)

Sun’iy Intellekt taraqqiyoti chizgilari: Mashinaviy O‘rganish (ML) da hisoblash quvvati va qidiruvning hukmronligi.

Jay Alammar35mo

Nega Sun’iy Intellekt biz o‘ylaganimizdan qiyinroq?

Haqiqiy Sun’iy Intellekt yaratish yo‘lidagi baland-pastliklar va ortiqcha baho berishning xatarlari.

Jay Alammar35mo

Bitta tanganing ikkita tarafi: Jeremi Hovard ning fast.ai va Andryu Ng ning deeplearning.ai kurslari

Qanday qilib fast.ai va deeplearning.ai kurslarining ikkalasini ham o‘rganib ‘overfit’ bo‘lib qolmaslik haqida.

Jay Alammar37mo

What makes LLM tokenizers different from each other? GPT4 vs. FlanT5 Vs. Starcoder Vs. BERT and more

Tokenizers are one of the key components of Large Language Models (LLMs). One of the best ways to understand what they do, is to compare the behavior of different tokenizers. In this video, Jay takes a carefully crafted piece of text (that contains English, code, indentation, numbers, emoji, and other languages) and passes it through different trained tokenizers to reveal what they succeed and fail at encoding, and the different design choices for different tokenizers and what they say about their respective models. --- Contents: 0:00 Introduction 1:25 The carefully polished text to test to

Jay Alammar39mo

ChatGPT has Never Seen a SINGLE Word (Despite Reading Most of The Internet). Meet LLM Tokenizers.

Despite processing internet-scale text data, large language models never see words as we do. Yes, they consume text, but another piece of software called a tokenizer is what actually takes in the text and translates it into a different format that the language model actually operates on. In this video, Jay goes examines a language model tokenizer to give you a sense of how they work. Follow our upcoming book, Hands-On Large Language Models, for more details about tokenizers and LLMs in general. Updates on the book coming on https://jayalammar.substack.com/ My co-author: https://twitter.com/Ma

Jay Alammar40mo

prompt chains are important for building large language model applications

Jay Alammar40mo

What is Llama Index? how does it help in building LLM applications? #languagemodels #chatgpt

Jay Alammar41mo

How to manage LLM prompts with tools like LangChain #languagemodels #chatgpt

Jay Alammar41mo

Are language models with more parameters better? #shorts #chatgpt

Jay Alammar41mo

What is LangChain? Where does it fit with LLMs like ChatGPT and Cohere? #shorts

Tools like Langchain (https://github.com/hwchase17/langchain/tree/master/langchain) help you build applications on top of large language models. #shorts

Jay Alammar41mo

AI is Eating The World - This is Where YOU Can Use it to Compete (AI Product Moats)

Over a decade ago, the phrase “software is eating the world” described how software was rapidly becoming the center of many industries beyond the technology sector. The leading book retailers, video services providers, music companies, entertainment companies, and even movie production companies were essentially software companies. That trend is still going strong. In this video, Jay shares observations on the value in the AI technology stack and focuses on where some of the technical moats might be. The previous video in this series (https://www.youtube.com/watch?v=AeW9r3lopp0) discusse

Jay Alammar42mo

What is Generative AI? 4 Important Things to Know (about ChatGPT, MidJourney, Cohere & future AIs)

What's the big deal with Generative AI? Is it the future or the present? In this video, Jay goes over four key reflections on how best to think of the current state of AI products and features, and avoid pitfalls people tend to make with new tech. Blog post: https://txt.cohere.ai/generative-ai-future-or-present/ What is Neural Search? Nils Reimers - Sentence Transformers and Embedding Evaluation https://www.youtube.com/watch?v=Z_4rohX4Ki8&ab_channel=Cohere --- Twitter: https://twitter.com/JayAlammar Blog: https://jalammar.github.io/ Mailing List: https://jayalammar.substack.com/ --

Jay Alammar45mo

AI Art Explained: How AI Generates Images (Stable Diffusion, Midjourney, and DALLE)

Learn how AI image generation works. This video goes over the AI components of AI image generation models like Stable Diffusion and explains how they work and how they're trained. Blog post: https://jalammar.github.io/illustrated-stable-diffusion/ --- Twitter: https://twitter.com/JayAlammar Blog: https://jalammar.github.io/ Mailing List: https://jayalammar.substack.com/ -- Introduction (0:00) Text-to-image and image-to-image (1:32) The components of Stable Diffusion - high-level overview (3:06) The three models inside the AI Image Generator (5:48) Generating images with reverse diffusion

Jay Alammar46mo

Nemesis 2 Intro Remade with AI Generated Images

This is a version of the intro cinematic to an old video game (Nemesis 2 on the MSX system). The graphics are remade using AI Generated images. Read more about the process in: https://jalammar.github.io/ai-image-generation-tools/ Original: https://www.youtube.com/watch?v=nWdTIHpUORE&ab_channel=Zebpro

No appearances yet. If you've seen Jay Alammar as a guest somewhere, hit + suggest to add it.

Similar thinkers

Minds whose work overlaps with Jay Alammar’s.

Shared niche — pedagogical deep learning architecture

Sebastian Raschka

@sebastian-raschka

ML researcher and educator; clear deep dives on LLM internals and from-scratch implementations.

Open Profile

Shared niche — computational linguistics and representation

Christopher Manning

@christopher-manning

Stanford NLP director; foundational textbooks and research on language models.

Open Profile

Shared niche — technical visualization of machine learning

Sasha Rush

@srush

Cornell professor; clear technical deep dives on LLM architecture.

Open Profile

Shared niche — applied machine learning engineering

Eugene Yan

@eugeneyan

Applied scientist; essays on AI engineering, evaluation, and recommender systems.

Open Profile

Shared niche — foundational research in intelligence

Yann LeCun

@yann-lecun

Chief AI Scientist at Meta; pioneer of convolutional neural networks and deep learning.

Open Profile

Shared niche — algorithmic humor and behavior analysis

Janelle Shane

@janelle-shane

Optics researcher; AI Weirdness blog on the absurdities of generative models.

Open Profile

Shared niche — mechanistic interpretability and model transparency

Sara Hooker

@sararosehooker

Cohere For AI head; on equitable ML systems and data-centric research.

Open Profile

Shared niche — technical deep learning synthesis

Lilian Weng

@lilianweng

Research engineer; rigorous long-form posts on LLM agents, RLHF, and diffusion models.

Open Profile

Is this you? Claim this page →

Jay Alammar

Recommends

Channel content

Appearances

Similar thinkers

Recommends

Channel content

Appearances

Similar thinkers