3 GenAI prompting methods worth trying
In our past few issues, we’ve been highlighting specific career areas, namely business management, data analytics, and cybersecurity. This week, we’re going to zoom out and return to a more widely applicable topic, AI skills.
At first glance, AI skills may seem highly technical. The name alone can bring to mind mechanical and robotic imagery. And, truthfully, some aspects of AI are highly technical. For example, if you’re aspiring to become an AI engineer, you’ll become intimately familiar with words like Python and LangChain. (Sidenote: If this sounds like your dream scenario, read our interview with Isaac Ke, an AI engineer at IBM. He reflects on his journey and top skills, plus offers detailed advice for entering the field.)
But for the rest of us, AI skills are more about real-world uses, like as creating a task tracker with Google Gemini, than they are about creating pipelines. You will be better able to take use of AI’s time-saving advantages the more at ease you are with applying GenAI tools and your practical AI skills. Professionals that use GenAI to enhance their skills are saving 1.75 hours a day, according to a Visier research.
The trick to maximizing your efficiency with GenAI? Good communication.
How to prompt LLMs
If you’ve ever had a conversation with a large language model (LLM), you’ll see that it can react to nearly any kind of input or query. Because these tools are conversational in nature, you can probably expect a response, or output, regardless of how you frame your input. However, there are a number of less efficient ways to communicate with the tool, much like in human-to-human communication.
In general, the caliber of your intake is reflected in the caliber of your output. Thankfully, there are standards for creating high-quality inputs that will increase the likelihood of producing high-quality outputs. This technique explains prompting, where a prompt is an input that tells the LLM what kind of output you want.
There are several prompting methods that are worth trying as you practice using LLMs. Here are some of the methods described in the course Google AI Essentials:
1. Zero-shot prompting is a simple prompt that provides no example to guide the output. Here, you provide a sentence or two instructing the LLM.
Example: Draft an email to my physician’s office requesting to schedule an appointment for my annual check-up on October 14.
2. One-shot prompting includes one example of the type of output you’re seeking. Similarly, few-shot prompting includes two or more examples of the type of output you’re seeking. This helps to instruct the LLM on the format and tone you’d like to achieve. Here, you provide your instruction, an instruction to review the example(s), your labeled example(s), and an open label for your request.
Example: Write a short, fun phrase to open a social media caption about my beach vacation. Review the examples provided and write in the same style.
Hike: Climbing to the top!
Game day: Rolling the dice!
Beach vacation:
3. Chain-of-thought prompting asks the AI to explain the reasoning for the output. This helps to ensure accuracy for logic and problem-solving questions. Here, you provide the context, an example, and your request. If you don’t have an answer to provide, you can alternatively instruct the LLM to “Solve the problem in a step-by-step manner.”
For instance, I usually go food shopping once a week, and my family consumes three bags of frozen spinach per week. Every time I go grocery shopping, I buy three bags of frozen spinach (3 bags each week * 1 week = 3 bags). I can only purchase entire frozen spinach bags. Describe the procedures I must follow in order to decide how many bags of spinach I should purchase in each shopping scenario.
Question: For one and a half weeks, I won’t be able to visit the grocery shop. How many frozen spinach bags should I purchase?
Answer: 5 bags. To determine this, multiply 3 bags/week by 1.5 weeks (3 bags/week * 1.5 weeks = 4.5) , then round up to the nearest whole number (5).
Question: I will be unable to go to the grocery store for 2.5 weeks. How many bags of spinach should I buy?
Answer:
With any of these methods, if you aren’t satisfied with the output, you can (and should) try different ways of phrasing your prompt. Iteration describes an approach where you write a prompt, see the output, and refine your prompt to get a more exact output.
you may be interested in this blog here:-
Advanced OOP Concepts in SAP ABAP A Comprehensive Guide
Leave a Reply