concept:rag-vs-tuning
RAG Vs Tuning
RAG Vs Tuning in the context of production machine-learning systems.
Lessons
Formal explanations, examples, simulations, and checkpoints.
Foundation-model lifecycle
Prompt, retrieve, adapt, train, or buy?
Match the intervention to the failure: prompts shape instructions, retrieval updates knowledge, tuning shapes behavior, and training or buying changes base capability.
Foundation-model lifecycleCorpus provenance, mixtures, and decontamination
Corpus quality is governed by provenance, realized sampling, and auditable exclusions—not merely by token count.
Foundation-model lifecyclePretraining objectives, scaling, and checkpoints
Pretraining progress is tokens transformed into validated capability, backed by slice-aware loss and checkpoints that preserve the exact continuation state.
Courses & assignments
Dependency-authoritative learning units.
Casebook
Reported facts and course reconstructions.