Utover grunnleggende prompting, avanserte teknikker — few-shot, chain-of-thought, strukturert output, system prompts, og andre — forbedrer LLM-resultater betydelig for komplekse oppgaver. Å forstå dem hjelper deg få mest mulig ut av LLM-er.
Viktige avanserte teknikker
✓ FEW-SHOT → provide EXAMPLES of input/output in the prompt → the model follows the pattern
(great for specific formats/behaviors); ZERO-SHOT = no examples (just instructions)
✓ CHAIN-OF-THOUGHT (CoT) → ask the model to REASON step by step ('think step by step') →
improves complex reasoning/math (shows its work → more accurate)
✓ STRUCTURED OUTPUT → ask for a specific format (JSON, etc.) → reliable parsing for app
integration (often with schemas/tools)
✓ SYSTEM PROMPTS → set overall behavior/role/rules (the model's persistent instructions)
✓ ROLE/persona → 'You are an expert X' → frames responses
