AI Safety and RiskCourse

Responsible AI / 5 weeks

AI Safety and Risk

Teaches builders and operators how to find, measure, and mitigate AI failure modes — including bias, robustness, security, misuse, and emergent behavior — before they reach production.

Learning path

Six modules with practical application.

  1. Systematically asking what could go wrong, who could cause it, and what the consequences would be before the system ships
  2. Pressure testing AI for distribution shift, adversarial input, and edge cases that look harmless but break the system
  3. Measuring performance and outcomes across groups, surfacing harm, and deciding what to fix and what to disclose
  4. Defending AI from prompt injection, data exfiltration, model extraction, and use by adversaries to scale harm
  5. Watching for behavior that was not designed in, including new capabilities, regressions, and unsafe combinations
  6. Detection, mitigation, communication, and learning for AI incidents that affect customers, regulators, or the public

Loading course material…