Why I Started This Site
The Beginning Over the years of learning and working, I've written many notes across many tools and platforms — physical...
Featured
11 articles
GPT Series Evolution
Overview From 2018 to 2025, the GPT series went from an obscure paper to a worldchanging product in seven years. Underst...
Transformer Attention Mechanism Explained
Why We Need Attention Before Transformer, the dominant approach to sequence processing was RNN and LSTM. They processed ...
RAG Retrieval-Augmented Generation in Practice
What RAG Solves LLMs have two persistent problems: a knowledge cutoff training data only goes up to a certain date and h...
Building a Personal AI Second Brain
The Second Brain Concept Tiago Forte coined "Second Brain" — using external tools to extend human memory and thinking. O...
AI Industry Trend Watch
From Model Competition to Application The past two years were about "who built the strongest model." Now the narrative i...
Running LLMs Locally with Ollama
What Is Ollama Ollama is a local LLM runtime developed by a San Francisco startup. It packages model downloading, quanti...
Obsidian Getting Started Guide
Why Obsidian Obsidian is a local Markdownbased notetaking tool. Unlike Notion, your data lives entirely on your own hard...
Reading Notes: Attention Is All You Need
Paper Background In 2017, Vaswani et al. published a paper of just over 6,000 words that completely transformed NLP and ...
How Far Away Is AGI
Two Camps Sam Altman believes AGI could arrive within 510 years. Yann LeCun argues autoregressive LLMs are not the path ...
Will AI Replace Programmers
What the Data Shows GitHub's research shows developers using Copilot complete tasks 55% faster on average. 85% report hi...