tutorial
Forget frameworks. Forget agents. Start with a fence, a regex, and a loop. In this article, you'll build (a adhoc) tool calling from first principles and discover what really happens when an AI "uses" a tool.
tutorial
We tend to judge AI models by parameter count. That's like buying a car based on its engine displacement. Modern architectures, Mixture-of-Experts, and reasoning capabilities have changed the game, allowing smaller models to outperform much larger ones.
tutorial
Learn why LLMs hallucinate, how RAG reduces mistakes by providing context, and why stronger models still matter.
tutorial
Ready to take your local LLMs beyond the terminal? Discover how to upgrade your workflow with Open WebUI, a self-hosted browser interface providing chat history, rich formatting, and easy model switching. Finally, we dive into the theory of tokens, embeddings, and new multimodal models like Gemma 4.
tutorial
Setting OLLAMA_HOST=0.0.0.0:11434 opens Ollama to your network, but the correct method differs by OS and the security risks are easy to overlook. This guide covers systemd, macOS, and Windows setup, firewall configuration, and how to avoid exposing an unauthenticated inference server.
tutorial
Get started with local LLMs! This post breaks down how the transformer architecture works, why you need an inference engine to run models, and how to set up your first local llm using Ollama.
tutorial
Running local LLMs isn't just about privacy—it's about cost, control, and understanding how AI really works. Here's where to learn, what to ignore, and how to get started.