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 & Material5.4. Chain-Of-Thought Prompting
The model is expected to provide answers or outputs based on the information it has learned from the previous prompts in the sequence. This technique aims to guide the AI model through a specific line of reasoning or train of thought, thus making the model's responses more focused and contextually relevant.
Q: Roger has 5 tennis balls. he buys 2 more cans of tennis balls. Each can has 3 tennis balls. how many tennis balls does he have now?
A: The answer is 11
A juggler can juggle 16 balls. half of the balls are golf balls and half of the golf balls are blue. how many blue golf balls are there?
A: The answer is 8.
The answer above is wrong.
Q: Roger has 5 tennis balls. he buys 2 more cans of tennis balls. Each can has 3 tennis balls. how many tennis balls does he have now?
A: Roger started with 5 balls. 2 cans of 3 tennis balls each is 6 tennis balls. 5 + 6 = 11. The answer is 11.
Q: A juggler can juggle 16 balls. half of the balls are golf balls and half of the golf balls are blue. how many blue golf balls are there?
Roger initially has 5 tennis balls. He buys 2 cans of tennis balls, each containing 3 balls, for a total of 2 x 3 = 6 tennis balls. After purchasing the additional balls, he has 5 + 6 = 11 tennis balls.
The juggler can juggle 16 balls in total. Half of the balls are golf balls, so there are 16 / 2 = 8 golf balls. Half of these golf balls are blue, so there are 8 / 2 = 4 blue golf balls.
The above answer is correct.
There are also combinations of Zero-Shot and Few-Shot Prompting with Chain-Of-Thought Prompting techniques such as the Zero-Shot + Chain-Of-Thought Prompting Technique where we add “Let’s think step by step” to a prompt to as a quick method to encourage the AI to follow the Chain-Of-Thought approach.
What advice would you give the instructional designer to enable them to create a scenario-based learning solution on this subject matter?
Let’s think step by step.
Note that Chain-Of-Thought prompting is less required in the latest ChatGPT model compared to the previous versions.
← Previous
Next →
On this page: