The post discusses the release of research papers from NeurIPS 2025, highlighting an interactive visualization tool that helps users explore the research landscape. It emphasizes the challenges of information overload in the rapid...
About:
Jay Alammar is the author of 'Language Models & Co.', a Substack publication that focuses on large language models, their internals, and applications. The publication has tens of thousands of subscribers.
Website:
Specializations:
Incoming Links:
Subscribe to RSS:
OpenAI's GPT-OSS is its latest open-source LLM, marking a significant release since GPT-2. While it shares similarities with existing models, it introduces a mixture-of-experts architecture that enhances problem-solving capabiliti...
0How Transformer LLMs Work [Free Course]
2025-02-10 •
The text is an announcement for a free course on how Transformer LLMs work, covering the evolution of language representation, tokenization, embedding, transformer architecture, and implementation of recent models in the Hugging F...
0The Illustrated DeepSeek-R1
2025-01-27 •
DeepSeek-R1 is the latest AI model that excels at solving math and reasoning problems. It follows a general recipe of creating a high-quality LLM over three steps. The model is created using large-scale reinforcement learning and ...
The book 'Hands-On Large Language Models' is now available after 18 months of work. It is a 425-page book with 300 original figures explaining the main intuitions behind building and using LLMs. The book is divided into three part...
Jay provides updates on the recent course about semantic search with LLMs on Deeplearning AI and the upcoming book. The course covers LLM fundamentals, keyword search, dense retrieval, evaluation and implementation, and real-world...
The author is excited to co-write a book on large language models with Maarten Grootendorst. The book aims to provide practical use cases for developers and will cover topics such as classification, semantic search, topic modeling...
0LLM University, Generative AI, AI Product Moats
2023-05-21 •
The text discusses LLM University, Generative AI, and AI Product Moats. It shares key observations about the space of AI and offers a visual guide to language models. It also introduces a series called Generative AI is…Not Enough ...
0What a Time for Language Models
2023-03-26 •
The text discusses the rapid development of language models and their commercial potential, as well as the impact on various industries. It also highlights the author's observations on recent AI developments and the business moats...
0Coming soon
2023-03-12 •
...