Unlock: Constitutional AI
Anthropic's approach to alignment: replace human harmlessness labels with a constitution of principles that the model uses to self-evaluate, enabling scalable AI feedback.
421 Prerequisites0 Mastered0 Working279 Gaps
Prerequisite mastery34%
Recommended probe
Bernstein Inequality is your weakest prerequisite with available questions. You haven't been assessed on this topic yet.
Constitutional AITARGET
No quiz
Not assessed4 questions
Chernoff BoundsFoundations
Not assessed3 questions
Hoeffding's LemmaFoundations
No quiz
Not assessed11 questions
Not assessed2 questions
Symmetrization InequalityAdvanced
Not assessed3 questions
Not assessed5 questions
Contraction InequalityAdvanced
Not assessed1 question
Hardware for ML PractitionersFoundations
No quiz
Peano AxiomsAxioms
Not assessed5 questions
Not assessed1 question
No quiz
Clustering for Gene ExpressionResearch
No quiz
Not assessed3 questions
Reward HackingFrontier
Not assessed1 question
RLHF and AlignmentResearch
Not assessed3 questions
Sign in to track your mastery and see personalized gap analysis.