AI
Everyday AI
5
Optional
60 minutes

Under the Hood

Peek inside how AI actually works (optional technical module)

TechnicalOptionalDeep Dive

What You'll Learn

  • The high-level flow: Data → Training → Model → Application
  • What tokens are and why they matter for cost and context
  • The concept of embeddings (turning words into numbers)
  • What parameters mean and why GPT-4 is bigger than GPT-3

Key Ideas

The AI Pipeline: Data to Application

AI follows a flow: (1) Collect massive amounts of text/image data, (2) Train a model by learning patterns, (3) Fine-tune for specific tasks, (4) Deploy as an application (like ChatGPT). Understanding this helps you grasp AI's strengths and limitations.

Examples:

  • Data: Books, websites, conversations
  • Training: Learning word relationships and patterns
  • Fine-tuning: Making it helpful, harmless, and honest
  • Application: The chatbot you interact with
Tokens: The Currency of AI

AI doesn't see words; it sees tokens (word chunks). 'Hello' might be one token, 'ChatGPT' might be two. This matters for costs (priced per token) and limits (max tokens per conversation).

Examples:

  • Roughly 1 token ≈ 4 characters or 0.75 words
  • A typical conversation uses thousands of tokens
  • Longer prompts = higher costs and slower responses
Parameters and Model Size

Parameters are like the 'brain cells' of an AI model. More parameters generally mean better capability but also more compute power needed. GPT-4 has hundreds of billions of parameters.

Suggested Resources

Google's Introduction to Generative AI

Google

Course
Machine Learning Specialization

Coursera

Course

Try This Now

Put your learning into practice with these hands-on exercises. Copy the prompts and try them in your favorite AI tool.

Exercise 1: Read Technical Documentation
Practice reading technical AI docs and extracting key insights.
20 minutes

Visit OpenAI's GPT-4 technical report or Anthropic's Claude documentation. Read the introduction and summarize 3 key capabilities or limitations in plain English.

Exercise 2: Count Tokens
Experiment with token counting tools to understand how text is processed.
10 minutes

Use OpenAI's tokenizer tool to see how different texts are broken into tokens. Compare: 'Hello' vs 'Supercalifragilisticexpialidocious' vs 'ChatGPT'.

Exercise 3: Explore Model Cards
Learn to read model documentation to understand capabilities and limitations.
15 minutes

Find a model card for GPT-4, Claude, or Gemini. What does it say about the model's training, intended use, and limitations?

Reflection Questions

Take a moment to reflect on what you've learned
  • 1.How does understanding the technical side change how you use AI tools?
  • 2.What technical concepts do you want to learn more about?
  • 3.How might this knowledge help you explain AI to others?
Previous Module
View All Modules
Next Module