We’re super excited to welcome Jay Alammar to the show. Jay is a well-known AI educator, applied NLP practitioner at co:here, and author of the popular blog, “The Illustrated Transformer.” In this episode, he shares his ideas on creating applied NLP solutions, working with large language models, and creating educational resources for state-of-the-art AI. Join the discussionChangelog++ members support our work, get closer to the metal, and make the ads disappear. Join today!Sponsors:Fastly – Our bandwidth partner. Fastly powers fast, secure, and scalable digital experiences. Move beyond your content delivery network to their powerful edge cloud platform. Learn more at fastly.com Fly.io – The home of Changelog.com — Deploy your apps and databases close to your users. In minutes you can run your Ruby, Go, Node, Deno, Python, or Elixir app (and databases!) all over the world. No ops required. Learn more at fly.io/changelog and check out the speedrun in their docs. Featuring:Jay Alammar – Website, GitHub, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes: Jay’s popular blog (with posts including “The Illustrated Transformer”) co:here Topically sandbox - topic modeling co:here’s prompt engineering guide Something missing or broken? PRs welcome!

Jay Alammar, renowned AI educator at Cohere, dives into the world of large language models (LLMs) and retrieval augmented generation (RAG). He explains how RAG enhances data interactions and factual accuracy in AI. Jay discusses challenges in implementing AI in industry and shares expert advice for newcomers. He emphasizes the evolution from deep learning to LLMs, the power of semantic search, and strategies to keep pace with rapid advancements. Lastly, he reflects on his journey in making complex AI concepts accessible through visual learning.

My interview with Jay Alammar, widely known inthe AI and NLP field mainly through his great blog on transformers and attention. ►Watch on YouTube: https://youtu.be/TO0IV9e2MMQ ►LLM University: https://docs.cohere.com/docs/llmu ►Jay's blog: http://jalammar.github.io/illustrated-transformer/ ►Twitter: https://twitter.com/JayAlammar, https://twitter.com/Whats_AI ►My Newsletter (A new AI application explained weekly to your emails!): https://www.louisbouchard.ai/newsletter/ ►Support me on Patreon: https://www.patreon.com/whatsai ►Join Our AI Discord: https://discord.gg/learnaitogether How to start in AI/ML - A Complete Guide: ►https://www.louisbouchard.ai/learnai/ Become a member of the YouTube community, support my work and get a cool Discord role : https://www.youtube.com/channel/UCUzGQrN-lyyc0BWTYoJM_Sg/join Chapters: 0:00 Hey! Tap the Thumbs Up button and Subscribe. You'll learn a lot of cool stuff, I promise. 00:43 Introduction of Jay Alammar 04:00 Why Jay got into AI 8 years ago? 08:07 Why teach after learning 16:12 What is a Transformer? 21:03 What the blocks are made of and how they work? 26:27 Training steps of LLM explained in simple words 39:31 Re-rank Systems 41:47 How to know that your problem can be solved by LLM? 45:31 Chatbot on private or proprietary data 47:10 Challenges with AI Apps 50:51 The requirement to create AI apps 56:11 Mitigate model hallucination from your side 59:05 How does ChatGPT work with any language you type in? 01:02:56 AI evolution in next few years 01:05:38 Jay wants AI to be able to do this 01:08:10 AI apps used by Jay 01:10:10 Projects of Jay