Responsible AI: the learning path

  1. AI bias and fairness: how models go wrong and how to audit them (12 steps, about 8 h 45 min, Intermediate)
  2. AI safety and alignment for beginners: the core ideas (9 steps, about 6 h, Beginner)
  3. Write a model card and datasheet to document AI limits (11 steps, about 5 h 10 min, Intermediate)
  4. Assess AI risk before release (8 steps, about 3 h 55 min, Intermediate)
  5. Red-teaming LLMs: find failures before users do (13 steps, about 6 h 15 min, Intermediate)
  6. Privacy in ML: anonymisation, differential privacy, DP-SGD (11 steps, about 8 h 9 min, Intermediate)