Learn AI Create the Future — with Pranay
Main site

Safety, Ethics and Law Section 114

AI Safety and Ethics

How AI goes wrong, who it hurts, and what you can actually do about it as a developer.

Every lesson in this section is written by .

13 of 13 lessons published Three reading levels on every lesson

Start with “Why AI safety matters”

Lessons in order

Work top to bottom. Each lesson assumes the one above it.

  1. Why AI safety matters
  2. Bias in datasets
  3. Fairness metrics
  4. Explainability
  5. SHAP and LIME
  6. Privacy in machine learning
  7. Differential privacy
  8. Federated learning
  9. Adversarial attacks
  10. Prompt injection
  11. Model cards and documentation
  12. AI regulation
  13. Deploying responsibly