The Token Bill: What Your LLM App Really Costs (and How to Measure It)
Token pricing looks simple until you're running a million calls a month. Here's a practical way to count the real cost — and a small harness for trading cost against quality.
The journal
Notes on fullstack & AI engineering.
Essays with runnable code and interactive demos — from React frontends to JVM backends, data pipelines to LLM-powered features. Written by a fullstack developer working in AI. Browse by category or tag.
How Spark Really Runs Your DataFrame
Your code runs top to bottom. Spark doesn't. A small-dataset walkthrough of lazy execution order, shuffles, caching, persist, checkpointing — and the best practices that fall out of them.
Java 27: The Release Where Good Defaults Win
JDK 27 shipped September 15, 2026 with 9 JEPs. Four are final — and two of them change how every JVM you run behaves without touching a line of code.
Gen AI vs Llama: What's Actually Different (and How Llama Works)
Gen AI is the field; Llama is one open-weight model family inside it. The differences, the use cases, the transformer architecture under the hood — with an interactive token sampler you can play with.