Glossary · Phase 6 · Modern LLM engineering
Payback period
How long before the money a change saves covers what it cost to set up.
Learn it properly
Prompting vs RAG vs fine-tuning · Pick the cheapest approach that works. About 30 minutes.
Other terms from the same lesson
- parameter-efficient fine-tuning: Fine-tuning that trains only a small number of new or chosen weights, such as LoRA adapters, instead of the whole model.