Learn · Intermediate
Working Knowledge
You use AI already. Understand what is happening under the hood and get better results.
Prompting That Works
What actually improves AI prompts: context, examples, structure, and iteration — the myths worth dropping, and when prompting stops being the fix.
IntermediateContext Windows and Tokens, Explained
Tokens, context windows, and why AI models forget: what the limit is, what happens when you hit it, the long-context tradeoffs, and practical habits.
IntermediateLocal Models: Hardware and Quantization
What determines which local AI models you can run: memory first, unified memory vs VRAM, what Q4 and Q8 quantization mean, GGUF, and realistic tiers.
IntermediateRAG, Explained
How RAG works in plain terms: embeddings, retrieval, and chunking; where it shines and disappoints; RAG vs long context; and when to build vs use built-in.
IntermediateAgents and Tool Use, Explained
From chatbot to agent: how tool use and function calling work, the reason-act-observe loop, coding agents, MCP, and what agents still get wrong.
IntermediateHow to Read AI Benchmarks Without Being Fooled
How to read AI benchmarks without being fooled: saturation, contamination, why beats-X-on-Y headlines mislead, and a checklist for model announcements.
IntermediateFine-Tuning vs RAG vs Prompting
Fine-tuning vs RAG vs prompting: what each changes, costs, and fails at; the wrong reasons to fine-tune; and system prompts plus few-shot as the middle.