AI Tutorials

Learn how to run PrismML's fast and efficient 1-bit Bonsai model locally on Windows, from download and setup to WebUI testing, reaching 88.6 tokens per second.

Learn how to install and use the Claude Code VS Code extension, what it can do across your codebase, and how it compares to working from the terminal.

A deep dive into ResNet architecture, covering how residual learning and skip connections solve the vanishing gradient and degradation problems that make training deep neural networks difficult.

Learn how to run GLM 5.1 locally on an H100 GPU with llama.cpp, test it, use the WebUI, and integrate Claude Code.

Learn how to install Google's new AI-optimized CLI, authenticate it, and wire it up to a Gemini-powered RAG pipeline that answers questions about your own Drive files.

Learn how to install and set up Hermes Agent, the open-source AI agent by Nous Research that remembers, learns, and grows smarter with every task.

This step-by-step guide teaches you to build a secure local AI agent with NanoClaw on Windows, connect it to WhatsApp, and control everything from the chat.

Learn how to fine-tune Gemma 4 E4B-it on a human emotions dataset using LoRA, 4-bit quantization, and a single 3090 GPU.

Learn how to build a fully local, multimodal AI coding assistant powered by Gemma 4 via Ollama, featuring agentic tool use wrapped in Gradio UI.

Discover how Gemini Embedding 2 has revolutionized the way we can build search and RAG systems by introducing native multimodality. Text, video, images, and audio can now all live in the same embedding space.

Learn how to build a browser-based AI agent that searches the web, extracts live flight data, and returns clean recommendations using GLM-5-Turbo.

Learn how to install and configure claude-mem, the Claude Code plugin that gives your sessions persistent memory through structured compression and retrieval.