WTF Is…? — Plain-English AI
A no-jargon beginner series that actually explains what is happening — RAG, MCP, agents, tokens and the rest — so you understand the ideas instead of memorizing definitions. Each piece assumes only what the ones before it taught.
1 module · 8 lessons
The beginner series
An eight-part, deliberately cumulative field guide to the AI terms everybody uses and almost nobody explains — search (RAG/vectors), tools (MCP, agents), what a model can see (tokens/context), which lever to pull (prompting/RAG/fine-tuning), and what's under the hood (next-token prediction, training vs. inference, parameters). Read straight through, or drop in anywhere.
A running cheat-sheet of the terms — vector, embedding, RAG, MCP, host/client/server, tools/resources/prompts, token, context window, parameters — each in one plain sentence.
- RAG vs. Embeddings vs. Vectors: WTF Is the Difference?6 minHow AI can search external knowledge.
- WTF Is an MCP?6 minHow AI applications connect to external systems.
- WTF Is an AI Agent? And How Is That Different From a Chatbot?4 minHow models move from answering to taking iterative action.
- Tokens, Context Windows & Memory: Why Does My AI Forget Shit?6 minWhat a model can see now, and why “memory” is overloaded.
- Prompting vs. RAG vs. Fine-Tuning: Which One Do You Actually Need?4 minWhich lever to pull when an AI system is failing.
- WTF Is an LLM Actually Doing?7 minNext-token prediction, attention, and why prediction can look like reasoning.
- Training vs. Inference: How an AI Goes From Expensive Science Project to Everyday Chatbot5 minHow a model goes from expensive training run to everyday chatbot response.
- Parameters, Weights & Neural Networks Without the Math Bullshit8 minWhat billions of parameters actually are, without requiring calculus.