AI Tutorials
Practical AI development tutorials
Articles
Avoiding Entity Key Drift in a Data Lake: Step 1, Normalization⭐9
Learn how entity key drift breaks IoT data lakes and dashboards using 719 real sensors, plus a fix using natural keys from strings like SNMP, Kubernetes, and Pr...
Prompt vs Loop Engineering: A Guide for Developers⭐8
Compare prompt engineering vs. loop engineering: when one prompt is enough vs. when you need multi-step AI systems. A 2026 guide for developers.
How Much Does a Local LLM Actually Cost to Run? I Measured Every⭐9
Measuring real energy costs of local LLMs on Apple Silicon M3 Ultra: 120B model costs 5x less per token than a smaller model, with detailed watt measurements.
MCP Explained: How Modern AI Agents Connect to the Real World⭐9
MCP solves the AI-tool integration problem by replacing M×N custom connectors with a standard protocol, enabling scalable, interoperable agent-to-tool connectio...
Don't Just "Throw Adam at It": Misunderstanding Adam Will Cost You⭐10
Don't blindly use default AdamW parameters. Tuning beta values, especially in reinforcement learning, can be the crucial fix when nothing else
Backpropagation Explained for Beginners (Part 2): There Has to⭐9
Discover a simpler approach to backpropagation, moving beyond manual derivatives to efficient neural network training in this beginner-friendly guide.
How I Reproduced BM25, Dense Retrieval, and SPLADE on a 16GB MacBook⭐9
I reproduced BM25, dense retrieval & SPLADE on a 16GB MacBook, matching RAG baselines; includes crash fixes & score interpretation.
How to Efficiently Prompt Claude Code⭐9
Learn effective prompting strategies for Claude Code and coding agents: be explicit, specify testing methods, and discuss features before writing code for effic...
How to Give an LLM Agent a Browser⭐9
Learn how to build a browser-using LLM agent with the OpenAI Agents SDK and Playwright MCP, including core loop design and real-world case studies.
How to Optimize Vector Search When RAM Gets Too Expensive:⭐8
Learn when to use on-disk vs in-memory ANN indexes to scale vector search affordably. Compare HNSW, DiskANN, and other algorithms for cost, speed, and accuracy.