Fine-tuning
Further training of an existing model on your own examples, to change its behaviour rather than its knowledge.
Fine-tuning continues training a pretrained model on a dataset of your input and output pairs. It is effective for teaching a consistent format, a house style or a narrow classification task, and it can let a small model match a large one on that one task at much lower cost.
It is a poor way to add facts. Knowledge baked in this way cannot be updated without retraining and cannot be cited. For facts, use rag.
Before fine-tuning, exhaust prompting. A few worked examples in the prompt, described under few-shot-prompting, solve a surprising share of the problems people reach for fine-tuning to fix, with no training run and no dataset to maintain.
Tagged
Where this comes up
Prompts, configs and tutorials in the library that touch this term.
- PromptUniversal
Strict code review of a diff
A review prompt that reports only what would break in production, gives the smallest fix for each finding, and is allowed to say the diff is fine.
- PromptUniversal
Turn a vague request into a written brief
Takes a one-line request from a colleague or client and returns the questions that have to be answered before work starts.
- GuideUniversal
What a prompt actually is
The three parts every working prompt has, why their order changes the answer, and how to tell a vague prompt from a specific one.
- GuideUniversal
Working with long documents and code
Why long sessions drift, what a large context window actually buys you, and how to keep a model on task across a big input.
- GuideUniversal
Giving a model a role and constraints
How naming the audience, the format and the exclusions turns unpredictable answers into repeatable ones.
No-padding everyday default
The one to set if you set only one. Answer first, nothing before it, nothing after it, and no offer to help further.
Tested on Claude Sonnet · May 2026