# Three Levers and What Each One Changes — Fine-tuning vs Prompting

Source: https://www.skillbyai.com/en/fine-tuning/d-levers

> Prompting, RAG and fine-tuning solve different problems.

## Instructions, knowledge, behaviour

**Prompting** changes the **input** (instructions, examples, format); the model is untouched, so changes are instant and reversible. **Retrieval (RAG)** also changes the input, adding **knowledge** the model lacks at question time. **Fine-tuning** changes the **model itself**: continued training on your examples shifts its weights and so its **default behaviour** (style, format, narrow skills). Missing or changing **facts** point to retrieval, unclear **instructions** to prompting, and consistent **behaviour** a prompt cannot reliably produce to fine-tuning. They combine well: a tuned model can still use retrieval.

## Change the input, add knowledge, or change the model

Three levers change an LLM system in different ways and at very different costs.

![Four ideas: levers, ladder, fit, cost.](assets/figures/fine-tuning/section-1-map.svg) — Figure 1.1 — Levers, ladder, fit and cost.

## Which lever for which problem

A first-pass guide; always confirm with an evaluation.

```text
Symptom                                                Likely lever
answers lack our private / recent facts                 RAG (retrieval)
model ignores or misreads instructions                  better prompt, examples, structure
format/tone drifts despite clear instructions            few-shot first; then fine-tune
prompt is huge (many examples) and costs too much        fine-tune a smaller model
need a narrow skill a general model does poorly          fine-tune (with enough good data)
model does not know the topic at all                     stronger model and/or retrieval
```

## Name the gap first

Write down whether the failure is facts, instructions or behaviour before picking a lever; most wasted fine-tuning starts with a skipped diagnosis.

**Quiz:** Which lever adds fresh, changing facts most reliably?

- [ ] A longer style prompt
- [ ] Fine-tuning
- [x] Retrieval (RAG)
- [ ] Raising temperature

*Answer:* Retrieval (RAG). Retrieval brings current, citable facts at question time.