Dean Hipkiss / Personal journal
Exploring technology.
Learning by building.
Notes on AI, software development and digital creativity. Things I build, experiments I try, and what I learn along the way.
Latest story / Technology
Getting started with Kali Linux on my Windows PC: setting up a VMware virtual machine, securing it and running a first home network discovery scan.
Read the story19 articles
Newest firstRevisiting my original Ollama guide to explore what's changed in local AI, from desktop chat and multimodal models to coding agents and local APIs.
Building my own always-on digital jukebox and home media server with a Raspberry Pi 5, Lyrion and Plex, using music and movies I already own.
Rediscovering my CD collection made me rethink streaming. Now I’m buying music again and building a digital library that I actually own.
From a fictional performing arts school to a live website: using Codex to write the files, GitHub to save them and Cloudflare Pages to publish them.
A command-line approach to local image generation on Apple Silicon, using Qwen Image 2.1, Q4 GGUF models and a little help from ChatGPT.
From a playable prototype to closer racing and better drifting: how I built DUSTLINE with Codex and ChatGPT Astra, one test drive at a time.
An experiment in practical AI agents: researching the news, writing a daily briefing, generating a cover image and publishing a static website automatically.
How I built a SwiftUI MP3 player for iPhone using OpenAI Codex inside Xcode 26.3 — and why AI coding agents are changing software development.
In 2026, simple HTML and CSS websites remain one of the fastest, most secure, and cost-effective ways to build a site. Learn why static sites still outperform website builders.
In 2026, artificial intelligence has transformed how websites are built. From instant layouts to auto-generated content, AI can now create a functioning website in minutes. This has led many businesses to ask an important question: Do we still need human web developers, or is AI enough?
Stable Diffusion is a robust open-source AI model that creates detailed images from text prompts through a diffusion process. This guide walks you through the steps to install and run Stable Diffusion on your local desktop.
Would you like to build a chatbot that interacts with your own documents? In this guide, you’ll learn how to run Ollama with a local LLM, use OpenWebUI as your AI chat interface, and enable RAG for smarter document-aware conversations using your own PDF files.
Docker is an open-source platform that simplifies the creation, deployment, and management of containers. It provides tools to build, share, and run containerized applications efficiently.
The Windows Subsystem for Linux allows you to run a Linux environment directly on Windows without a traditional virtual machine or dual-boot setup.
Ollama helps developers run and interact with large language models locally, offering command line tools for pulling models, running prompts, and building AI-powered applications.
Learn how to run your own AI language model locally on your computer with Ollama, keeping your prompts private and avoiding external cloud services.
In this example we are going to build a very simple website and host it on GitHub Pages. This demonstration requires a Git client and a code editor app.
When you're ready to build and host a website, there are many options to consider, from website generators and hand-written code to AI tools and free hosting with GitHub Pages.
