Back to library

🎛️Fine-Tuning vs In-Context Learning

Stop reaching for fine-tuning every time a prompt fails — diagnose whether you have a capability gap, format gap, or knowledge gap, then pick the cheapest fix that closes it. By the end you'll write a one-page memo your team can defend.

Applied14 drops~2-week path · 5–8 min/daytechnology

Phase 1Two Different Tools, Not Two Versions of the Same Thing

Why both 'teach' the model but solve different problems

4 drops
  1. Fine-tuning changes the model; prompts change the request

    6 min

    Fine-tuning rewrites a slice of the model's weights; in-context learning rewrites only the request you send. Different surgeries, different recovery times.

  2. Capability gap, format gap, knowledge gap — name yours first

    7 min

    Almost every fine-tuning vs prompting decision collapses into one of three gap diagnoses — and the right fix depends entirely on which gap you have.

  3. In-context learning is pattern recognition, not learning

    7 min

    The model doesn't 'learn' from your in-context examples — it pattern-matches them against patterns it already saw during pretraining. That distinction tells you exactly when ICL will and won't work.

  4. Fine-tuning shifts a probability cloud, not a fact

    7 min

    Fine-tuning doesn't write new facts into the model — it shifts the probability distribution over outputs toward your training examples. That's why it's great for behavior and bad for knowledge.

Phase 2Diagnose the Gap, Then Pick the Fix

Decide: prompt, few-shot, RAG, or fine-tune

5 drops
  1. The four-question triage that picks your tool in 60 seconds

    7 min

    A four-question decision tree — capability, format, knowledge, latency — picks between prompt, few-shot, RAG, and fine-tune in under a minute. The tree beats vibes every time.

  2. Case 1: The support bot that 'doesn't understand our products'

    7 min

    When users say the bot 'doesn't understand,' it's almost always a knowledge gap dressed as a capability gap — and the right answer is RAG, not fine-tuning.

  3. Case 2: The output-format problem few-shot fixes in twenty minutes

    6 min

    When the answer is right but the shape is wrong, you have a format gap — and few-shot prompting plus structured-output constraints solve it almost instantly.

  4. Case 3: The medical NER task that genuinely needs fine-tuning

    8 min

    Sometimes the base model truly can't do the task — niche domain skills with sparse pretraining coverage are real capability gaps, and fine-tuning is the right answer.

  5. RAG plus fine-tune: when both are right at the same time

    7 min

    The most resilient production systems combine fine-tuning for behavior with retrieval for knowledge — each tool used only for what it's actually good at.

Phase 3Adapters, LoRA, and the Three Flavors of Tuning

Adapters, LoRA, and the three flavors of tuning

4 drops
  1. LoRA: most of the quality at a fraction of the cost

    7 min

    LoRA fine-tunes just a tiny set of low-rank adapter weights, achieving most of the quality of a full fine-tune at a fraction of the cost — and it's now the production default.

  2. Instruction tuning vs domain tuning vs preference tuning

    8 min

    'Fine-tuning' means three different things — instruction tuning teaches new task formats, domain tuning teaches new vocabulary, preference tuning teaches new values — and conflating them leads to using the wrong recipe.

  3. Run the actual numbers before you propose anything

    7 min

    Most fine-tuning vs ICL debates dissolve once someone runs the inference-cost-times-volume math against the one-time training cost — but almost no team actually runs it.

  4. Fine-tuned models age — and aging is expensive

    8 min

    Fine-tuning isn't a one-time cost — every base-model upgrade, data drift, and behavior change can force a re-train, and that maintenance burden is what kills most fine-tune projects in year two.

Phase 4Write the One-Page Memo

Write a one-page memo your team can defend

1 drop
  1. Draft a memo your team can actually defend

    8 min

    Draft a memo your team can actually defend

Frequently asked questions

What is the difference between fine-tuning and in-context learning?
This is covered in the “Fine-Tuning vs In-Context Learning” learning path. Start with daily 5-minute micro-lessons that build from fundamentals to hands-on application.
When should I fine-tune an LLM versus just improve my prompt?
This is covered in the “Fine-Tuning vs In-Context Learning” learning path. Start with daily 5-minute micro-lessons that build from fundamentals to hands-on application.
Is RAG cheaper than fine-tuning for adding domain knowledge?
This is covered in the “Fine-Tuning vs In-Context Learning” learning path. Start with daily 5-minute micro-lessons that build from fundamentals to hands-on application.
What is LoRA and how is it different from full fine-tuning?
This is covered in the “Fine-Tuning vs In-Context Learning” learning path. Start with daily 5-minute micro-lessons that build from fundamentals to hands-on application.
What's the difference between instruction tuning, domain tuning, and preference tuning?
This is covered in the “Fine-Tuning vs In-Context Learning” learning path. Start with daily 5-minute micro-lessons that build from fundamentals to hands-on application.