I wrote this as a practical engineering guide to modern foundation models. It covers architectures, training systems, inference, RAG, agents, evaluation, interpretability, and safety. I would love feedback from people building or operating LLM systems.
I saw Realm's speak at Deview 2014 conference in South Korea, and they released android version during the presentation that introduce about Realm. When you guys opened up the terminal and deployed web service with android version during the seminar, It feels very impressive. Great job guys! :)