Understanding Large Language Models: How They Actually Work
A plain-language look at how large language models turn text into predictions, one token at a time.
A JOURNAL ABOUT TECHNOLOGY
Learn something new.
Write. Share.
A space to connect knowledge, one line of code a day.
Discover tutorials, ideas, and notes from a learning journey.
FOR YOUR CURIOSITY
Latest notes.
The Transformer Architecture, Explained
Break down self-attention and feed-forward layers, the two building blocks behind every modern language model.
Fine-Tuning vs. Prompt Engineering: Which One Do You Need?
Compare two ways to adapt an AI model to your task, and learn when each one actually pays off.
Open-Weight vs. Closed AI Models: What's the Real Difference?
Llama and Mistral ship their weights; GPT and Claude stay behind an API. Here's what that trade-off means in practice.
What Is a Context Window, and Why Does Size Matter?
Every AI model has a limited memory span. Learn what a context window is and how it shapes what the model can do.
Retrieval-Augmented Generation (RAG): Giving AI Models a Memory
Learn how RAG lets a language model answer questions using information it was never trained on.
Knowledge grows when shared.
Stay curious. There is always something new to learn.
ABOUT THE AUTHOR
Dr (C). Ir. Putu Adi Guna Permana, S.Kom., M.Kom., IPM., ASEAN Eng.
Writer and founder of Diary Coding — sharing notes, tutorials, and experiences about programming for anyone who wants to keep learning.