I’ve been exploring the capabilities of the recently announced successor to GPT-4: GPT-4o (“omni”). At a glance, GPT-4o feels like a natural evolution of the GPT family. Not just bigger or faster, but more flexible in how it interacts with me across text, voice and vision. Where GPT-4 felt like a defining step into multimodality, GPT-4o feels more like that step applied across real workflows I care about. What’s Different: From GPT-4 to GPT-4o When comparing GPT-4 to GPT-4o, a few clear shifts stand out.

I recently discovered Ollama (ollama.com), a platform that allows you to run open-source Large Language Models (LLMs) directly on your local machine. As someone with an M1 Pro MacBook Pro, I was intrigued by the idea of leveraging my hardware to run advanced AI models privately. After exploring Ollama and experimenting with open-source models like Llama, Mistral, and Phi, I’ve been amazed at the speed and quality these models deliver—especially considering they’re running locally.

Prompt engineering is a crucial skill in today’s AI-driven world. At its core, it’s the process of designing and optimising prompts to interact effectively with natural language processing (NLP) models like ChatGPT. Crafting a good prompt is an art and a science, and when done well, it can drastically improve the quality of responses from AI systems. Whether you’re writing prompts for work, learning, or creative projects, understanding the basics of prompt engineering can make your interactions with AI more productive and rewarding.

We’re living in the middle of an AI revolution. The rapid advancements in artificial intelligence feel like the dawn of a new era—much like how the internet and the World Wide Web transformed the way we live, communicate, and work. In just a few short years, AI has gone from a buzzword to a daily tool many of us use, and the pace of progress shows no signs of slowing.

Diving into the world of Linux naturally led me to discover the vibrant homelab community. What began as casual curiosity soon became a genuine fascination, fuelled by countless YouTube videos showcasing everything from compact, single-board computers to sprawling, business-grade server racks. The creativity and technical depth on display resonated with my own desire to experiment and learn by doing. But as I watched, a set of questions began to form: Did I actually need a homelab? What would I use it for? Did it require a significant investment in hardware? And, crucially, how should I even begin?