Zum Hauptinhalt springen

Sort Training, Tuning, and Inference

Distinguish pretraining, fine-tuning, prompting, retrieval, and inference-time controls.

how-llms-work4 min read

Sort each technique by where it primarily changes the system. Changes learned model behavior Changes runtime context Changes generation behavior Measures the result Pretraining on broad corpora Fine-tuning on task examples Prompt instructions Retrieving current policy passages Lowering temperature Structured decoding or schema constraints Regression eval set Human scoring rubric lifecycle

Read the full lesson

Sign up free: one personalized lesson every day, matched to your role and goals.

← Back to library

Kontakt aufnehmen