AI Foundations

How AI actually works, answered as the 9 questions people really ask. Predict how these systems fail, brief them properly, check their work, and decide what to hand over.

9 sections ยท 19 lessons

Course outline

Where do its answers actually come from?

  1. There Is No Answer Database
  2. Where The Patterns Came From

Why did it forget what I said earlier?

  1. Working Memory, Not Storage
  2. The Middle Gets Lost

Why is it helpful at all, and why doesn't it know about last month?

  1. A Predictor Is Not An Assistant
  2. Why It Stops At A Date

Why is it brilliant at this and hopeless at that?

  1. The Boundary Is Not Where You Think
  2. Sort Your Own Tasks

Why did it invent a citation and sound certain?

  1. Guessing Was The Winning Strategy
  2. Where To Expect It

Why doesn't "make it better" work?

  1. It Cannot Infer What You Did Not Write
  2. Show, Don't Tell

It reads perfectly. How do I know it's right?

  1. Reading Well Is Not Being Right
  2. Match The Checking To The Stakes

Which parts of this should I hand over?

  1. Parts, Not Whole Tasks
  2. What Never Gets Handed Over

It's acting on its own. Where do I put the brakes?

  1. The Loop
  2. Errors Compound
  3. Where The Brakes Go

Start learning with Wondering