Part 1 · Foundations
Probability and Uncertainty
AI rarely knows for sure. It makes its best guess and assigns a likelihood to each possibility.
Key concepts
- A probability is a number from 0 to 1 that expresses how likely something is.
- A distribution spreads belief across all possible outcomes.
- Bayes' rule updates a belief when new evidence arrives.
- A model is calibrated when its stated confidence matches reality: things it calls 80% likely happen about 80% of the time.
- Confidence is not correctness. A model can be highly confident and wrong.
Bayesian updating. A prior belief is combined with evidence to form a posterior.
Formal view and evidence
- Established. Bayes' theorem, . Cross-entropy, , equals , so minimizing it is equivalent to maximum likelihood estimation.
- Debated. The most practical route to uncertainty in deep learning, including ensembles, approximate Bayesian inference, and conformal methods.
- Open problem. Calibrated uncertainty under distribution shift, and for open-ended language generation.
Common misconception
Common belief
"99% confidence means the AI is right 99% of the time."
In practice
Only a well-calibrated model behaves that way, and many are not.
Key takeaways
- Probability expresses uncertainty as a distribution over outcomes.
- Bayes' theorem updates beliefs when evidence arrives.
- Confidence is useful only when it is well calibrated.