Blogs

A collection of my thoughts on AI, engineering, and more.

2025
📏 Bits-per-Byte (BPB): a tokenizer-agnostic way to measure LLMs
🎨 Creativity Is a Luxury
🔀 GPT-5 Router - Inevitable Future of Chat Interfaces
🧠 Instruction Aware Embeddings
🔍 Improving Retrieval in RAG (via Recall, Precision, and NDCG)
2024
☁️ AWS BedRock - Converse API - A single endpoint for all models ?
💾 Essential Database Design: Five Fields Every Table Must Have
2023
Speeding up the GPT - KV cache
2021
👨‍💻 LC contest problems summary
📝 Hugo commands