Learnings
Notes from the frontier.
Daily notes on AI, LLMs, RAG & building on the frontier. Everything I learn — code, math, experiments and ideas — shared in the open.
How RAG actually works (with code)
Retrieval-Augmented Generation grounds an LLM in your own data. The core loop in four steps — plus a tiny Python retriev...
18 Jun 2026
1 min read
The math behind transformer attention
Scaled dot-product attention in one formula, why the √dₖ scaling matters, and a tiny PyTorch sketch.
17 Jun 2026
1 min read
What actually mattered in AI this week
Longer context, on-device models and dependable agents — the signals worth paying attention to.
16 Jun 2026
1 min read