Good vs Bad prompting practices

Okayish one

Your task is to - Write a one liner to summarize batman movie

You should write in positive tone

You should write about the positive intent of movie

You should make it inspiring note

You should write in less than 400 characters

Result - "Batman: A captivating and inspiring tale of resilience and justice, portraying a fearless vigilante driven to protect his city and battle the forces of corruption and evil, reminding us that everyone can make a difference."

Good one

Your task is to - Write a one liner to summarize batman movie

You should write in positive tone, positive intent with inspiring words and total length less than 200 words

Result - "An inspiring and thrilling journey of Bruce Wayne's transformation into Batman, a symbol of justice and hope that courageously battles the pervasive darkness in Gotham City."

• Words are better than character limitations
• One liner condensed instruction is much better than additive instructions

I observe a lot of fluffy descriptions

Ref - Link

Keep Prompting!!!

Prompt Examples - Zero shot - Few Shot

Zero-Shot

Classify which of the below foods is vegetarian. Given it vegetarian or  non-vegeterian. The foods to classify are

1. Carrot
2. Coconut
3. Brinjal
4. Chicken
5. Egg

Few shot

Given a mapping of fruits, the person prefers

1. <carrot, count, brinjal - likes>
2. <Chicken, egg - does not like>

Suggest whether a person likes potatoes or meatballs. Give answer as 

1. item - like or don't like

Keep Exploring!!!

Prompt Engineering Notes

NLP use cases are handled with instant model work :) 

• Prompting as Developer Tool
• No more data labeling
• No more training

• Segment cells in the given image with prompt engineering
• Prompt based segmentation
• Free Flow segmentation

With Vision, it needs a bit of look alike, refinement to be put on usage

• Quickly train and segment models
• Quickly get a result. Meta’s SAM model is one example of Visual Prompting

A combination of similar segments, zero shot learning we may need to do to arrive at domain related customization

This looks good for text. With vision positive + negative prompting need to work on it.

Keep Exploring!!!