1. Introduction
2. Team Structure3. Process Flow
3.1. Module Learning & Experience Design
3.2. Individual Flow Design
3.3. Narrative Design & Skills Mapping
3.4. New Assets Creation
3.5. Annex: World Building - Learning & Experience Design
3.6. Annex: World Building - Story Design
3.7. Process Flow Conclusion4. Caveats
4. Caveats5. LLM Prompt Engineering Techniques
5.1. Use The Latest Model
5.2. Zero-shot Prompting
5.3. Few-shot Prompting
5.4. Chain-Of-Thought Prompting
5.5. Structuring Prompts
5.6. Describing Prompts
5.7. Editing Prompts
5.8. Extending Responses
5.9. Multiple Users Collaborating6. Text-to-Image Prompting Engineering Techniques
6.1. General Techniques
6.2. Photography
6.3. Architecture
6.4. Various Aesthetic Styles
6.5. Product & Material5.3. Few-shot Prompting
It refers to the ability of a model to understand and generate appropriate responses to a given input after being provided with a small number of examples or training data for that specific task or prompt.
In few-shot prompting, the model leverages its general understanding of language and knowledge acquired during the pre-training phase, as well as the limited examples provided, to generate meaningful responses to new prompts. This approach allows AI models to quickly adapt to new tasks with minimal additional training, demonstrating their flexibility and capacity to handle a wide range of situations and problems.
Demonstration 1:
Input: "happy"
Output: "joyful, content, delighted"
Demonstration 2:
Input: "cold"
Output: "chilly, freezing, frosty"
New Prompt:
Input: "quick"
"fast, rapid, swift"
Start with zero-shot, then few-shot (example), neither of them worked, then fine-tune.
← Previous
On this page: