AI
AI2026-04-06
Your Million-Token Context Window Is a Lie
Models advertise 1M tokens but fall apart at 130K. The context window arms race is solving the wrong problem.
9 min read
// TAG
#RAG
3 articles
AI
AI2026-03-09
RAG Is Not a Silver Bullet — When to Skip It
RAG solves real problems, but teams reach for it reflexively. Here are the specific scenarios where it makes your system slower, harder to maintain, and dumber.
8 min read
AI
AI2025-02-28
How to Build a RAG Pipeline in 100 Lines of Python
Retrieval-Augmented Generation is the most practical AI pattern of 2025. Here's a minimal but production-ready implementation using LangChain, ChromaDB, and the OpenAI API.
1 min read