YOLO Responsibly! Part 2: Multi-file refactors, harness wars, and a Claude face-off
Pushing local Gemma 4 through a multi-file refactor, rerunning it under opencode, and racing Claude Code. The best security lesson came from the policy log.…
YOLO responsibly! Part 1: A local coding agent with Gemma 4 and Docker sandboxes
Running a coding agent in YOLO mode, powered by a local Gemma 4, inside a Docker Sandbox microVM. Everything that broke on the way, and the small YAML file that fixed it.…
Building Production-Grade RAG Systems: Kubernetes, Autoscaling & LLMs
Why Kubernetes for LLM workloads: GPU scheduling, autoscaling, and serving models like Gemma in a production-grade Java RAG system. Part 3 of the series.…
Building Production-Grade RAG Systems: Architecture Deep Dive
Architecture deep dive of a production RAG system in Java 25 and Spring Boot WebFlux: service boundaries, retriever design, and tradeoffs explained.…
Building Production-Grade RAG Systems: Understanding the Problem Space
The real production challenges of RAG systems: latency, reliability, cost, quality, and observability. Part 1 of building production-grade RAG in Java.…
A look into Deep Java Library!
Hands-on intro to DJL (Deep Java Library): building a speech recognition app with an engine-agnostic deep learning framework for Java developers.…
What the CRaC ?!
What CRaC (Coordinated Restore at Checkpoint) means for Java: instant JVM startup, Azul Zulu support, and Spring 6.1 integration explained simply.…
Building Native Covid19 Tracker CLI using Java, PicoCLI & GraalVM
Build a native Covid-19 tracker CLI in Java with PicoCLI and GraalVM native image: fast startup, single binary, and easy distribution.…