How Models Learn
A beginner-safe bridge from training examples to model behavior before deeper optimization topics.
Core lesson
AI Foundations
Every AI term explained before it's used — starting from zero.
All articles · 22
- 01What Is AI?foundation12 min read
- 02AI vs Machine Learning vs Deep Learning vs Generative AIfoundation8 min read
- 03What Is A Model?foundation7 min read
- 04Training vs Inferencefoundation7 min read
- 05Data, Datasets, Examples, And Labelsfoundation6 min read
- 06What Is A Neural Network?foundation5 min read
- 07Parameters And Weightsfoundation5 min read
- 08What Is A Large Language Model?foundation6 min read
- 09Tokens And Tokenizationfoundation7 min read
- 10Prompts, Context, And Completionsfoundation6 min read
- 11Training Data vs Context vs Memoryfoundation5 min read
- 12Hallucinationsfoundation5 min read
- 13Embeddings In Plain Englishfoundation6 min read
- 14Vectors In Plain Englishfoundation5 min read
- 15Semantic Meaning And Similarityfoundation5 min read
- 16Cosine Similarityintermediate4 min read
- 17Retrieval In Plain Englishfoundation6 min read
- 18RAG In Plain Englishfoundation6 min read
- 19Fine-Tuning vs Prompting vs Retrievalfoundation5 min read
- 20Multimodal AI In Plain Englishfoundation5 min read
- 21What Is An AI Agent?foundation5 min read
- 22What Are Evals?foundation5 min read
Planned
Coming soonThese will slot into the reading order above as they're published.
Why Models Follow Instructions
A plain-English explanation of instruction following before agent, tool, and system-prompt mechanics.
Context Windows And Their Limits
What fits into a model request, what gets left out, and why context limits shape AI product design.
System Prompts
How high-priority instructions shape model behavior without turning prompts into magic control panels.
Temperature And Sampling
Why generation can vary, what sampling controls do, and when randomness helps or hurts.
Structured Outputs
How AI systems ask models for JSON-like outputs and why validation still matters.