The AI Field

The AI Field

3 min read

Welcome

This is a knowledge base of information about the general field of AI.

The goal is to demystify the field. Explain the terms, cut through the buzzwords, and show you what’s actually happening behind the scenes. Additionally this is one of my ways to give back to the community and to answer people where can I learn about AI.

Where to start

If you’re completely new, start with the big picture:

  • AI - what artificial intelligence actually means
  • Machine Learning - how machines learn from data
  • LLMs - the large language models behind ChatGPT, Claude, and others
  • AI Engineering - the emerging field of building products with LLMs

How this works

Every concept is its own page. They’re all connected — you’ll see links between them (those [[wikilinks]]) and a graph view that shows how everything relates. There’s no single “correct” order. Pick what interests you and follow the links.

If you want a more structured path, here’s a suggested reading order:

  1. What is AI? → Model → Parameters → Architecture → Numerical Representation
  2. Training → Supervised vs Unsupervised → Reinforcement Learning → Data → Data Quality → Data Splitting
  3. Training Process → Cost Function → Gradient Descent → Overfitting/Underfitting → Transfer Learning
  4. AI Landscape → ML → DL → CV → NLP → Data roles
  5. LLMs → Transformer → Tokens/Tokenization → Next Token Prediction → Scaling Laws → SLMs → Knowledge Distillation
  6. Using LLMs → Inference → Pre-Training → RLHF → Fine-Tuning → Prompt Engineering → System Prompt → Temperature → Context Window → Memory → Chain of Thought
  7. Building with LLMs → API → Structured Outputs → Embeddings → Semantic Search → Vector Databases → RAG → Tool Use → Agents → Agentic Workflows
  8. Production → Hallucination → Guardrails → Evaluation → Cost & Pricing → Batch Processing → Latency → Synthetic Data
  9. Ecosystem → Open vs Closed Models → GPU → Quantization → Benchmarks → Multimodal → Image Generation
  10. Society & Future → Bias in AI → AI Regulation → AGI

What you’ll learn

By the end, you should be able to:

  • Understand what people mean when they say things like “fine-tuning,” “RAG,” “embeddings,” or “context window”
  • Have a practical sense of how AI products are built, what they cost, and where they break
  • Hold your own in conversations about AI without nodding along to things you don’t understand
  • Make better decisions about when and how to use AI in your own work

Graph View