Skip to main content
← Choose a different target

Unlock: Scaling Laws

Power-law scaling of LLM loss in parameters, data, and compute: Kaplan, Chinchilla, the Muennighoff data-constrained law for repetition, Schaeffer et al.'s evidence that some apparent emergence is metric-induced, MoE and muP extensions, and the test-time compute axis.

349 Prerequisites0 Mastered0 Working252 Gaps
Prerequisite mastery28%
Recommended probe

Peano Axioms is your weakest prerequisite with available questions. You haven't been assessed on this topic yet.

Scaling LawsTARGET
Gemini and Google ModelsFrontier
No quiz
Peano AxiomsAxiomsWEAKEST
Not assessed5 questions
Sparse Recovery and Compressed SensingResearch
No quiz
Convex Optimization BasicsFoundations
Not assessed32 questions
Optimizer Theory: SGD, Adam, and MuonAdvanced
Not assessed4 questions
Data Contamination and EvaluationFrontier
Not assessed3 questions
History of Artificial IntelligenceFrontier
No quiz
Ineffable IntelligenceResearch
No quiz
Inference Systems OverviewFrontier
No quiz
Lazy vs Feature LearningResearch
Not assessed2 questions
Distributed Training TheoryFrontier
Not assessed4 questions

Sign in to track your mastery and see personalized gap analysis.