This instalment shows how to build a lightweight llama.cpp server image and wire it up with docker-compose and Caddy on a VPS. It continues from last week's server prep and sets the stage for CI/CD next.
Set up secure SSH access to an affordable VPS and automate its provisioning with Ansible - Docker, Caddy, firewall rules, and a small language model ready to go. Part of the Guardrail Garage series.
A small, practical plan for building a snack-size RAG assistant with a tiny local LLM on a VPS. Goals, constraints, and a quick tour of RAG options, plus a few personal updates.
A hands-on introduction to Claude Code as an AI pair programmer, with setup tips, workflow patterns, and hard-won lessons from a two-week refactor sprint. Includes guidance on planning, testing, and keeping control over agentic tools.
A practical introduction to getting better results from LLMs: free ways to compare models, meta-prompting, a simple prompting framework, and Socratic questioning. Part of the Guardrail Garage series.
A practical tour of tokenisation for LLMs. Why word-level fails, how subwords and BPE work, and what modern tokenisers look like, with tips and resources. Plus a brief personal update.