tils (page 9)
-
Chain of Draft to Speed Up LLM Reasoning
Chain of Draft (CoD) prompts LLMs to use short, minimal reasoning steps, achieving near-CoT accuracy with far lower token use and latency.
-
How To Classify Gmail Messages With LLMs
Useful Google script to classify all incoming emails using OpenAI
-
Working With Dot Product And Cosine Similarity For Unit Vectors
Why dot product is equal to cosine similarity when working with unit vectors
-
FAISS vs pgvector - why one's a library and the other's a database
FAISS is a rocket-fast in-memory index, pgvector is Postgres with vectors. Here's when to pick each, with code.
-
Absorbing Data and Overcoming Information Blindness
How to design data systems that help users absorb information and avoid information blindness, with actionable strategies.