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.
An accessible tour of word embeddings, from Word2Vec to GloVe, with intuition, a touch of maths, and practical notes on training and using them. Includes caveats, examples, and where modern models fit.
Do machines understand words? And if not exactly, do they use Google Translate?
Why I keep my own blog as my main tool of exposure, why I rented a VPS to show real projects, and what I learned moving from Windows to macOS.
What can I do to learn better? What ways can I expose myself? And are we really lucky that we are born in Europe in modern times?
How being a data nerd helps me manage my weight and hit my goals. Progress over perfection.
Find out my motivation behind writing and what software I am using for e-book production.
Create re-usable and maintable data science projects in Python. Snippet from my upcoming e-book.
A step by step guide for Windows users to develop Python projects locally