Technology has redefined how the world works in this modern era, where Artificial intelligence (AI) has started to take centre stage in the recent years. 

LLM or Large Language Model is a type of artificial intelligence model designed to understand and generate human-like text. These models are trained on large amounts of data and are capable of performing a wide range of natural language processing (NLP) tasks, including text generation, language translation, sentiment analysis, summarization, question answering, and more. 

Prompt Engineering is an art of crafting precise and effective prompts to enable LLMs like ChatGPT to generate desired responses. 

Here are 12 simplified and beginner-friendly prompt engineering techniques with examples:

Zero-shot prompting is a prompt engineering technique that allows LLMs to generate responses to tasks they haven't been explicitly trained on. It's like asking a friend a question on a topic they've never heard about, yet they manage to provide a reasonable answer based on their general knowledge.

Few-shot prompting takes zero-shot prompting a step further by providing the LLM with some examples or demonstrations of the desired task. It's like giving your friend a quick overview or specimen on a topic before asking them to provide insights.

Chain-of-thought prompting involves structuring prompts in a logical progression, guiding LLMs through a sequence of related concepts or ideas. It's like telling a story or explaining a concept step by step to help your friend understand better.

Tree-of-thoughts prompting expands on chain-of-thought prompting by organizing prompts in a hierarchical structure. It is used to generate coherent and structured responses by guiding them through a hierarchical structure of ideas or topics, resembling a tree-like branching structure.

Output template prompting provides LLMs with predefined structures or formats for generating responses. It's like filling in the blanks of a template to create a specific type of document. With output template prompting, a structured template is specified for the LLMs in the input prompts.

Reframing prompt means modifying the original prompt and input the reframed prompt after the initial response. It is a technique used to modify or rephrase the input prompt in a way that encourages the language model to generate more diverse or nuanced responses.

Reframed Prompt: How do human activities contribute to changes in Earth's climate?

Iteration means executing the same set of instructions a given number of times or until a specified result is obtained. It's like fine-tuning a musical instrument to produce the perfect melody.

Iterated Prompt: What are some nutritious foods that should be included in a balanced diet?

Role-play prompting immerses LLMs in simulated scenarios or personas. It's like asking your friend to pretend to be someone else for a role-playing game.

Summarization prompting requires LLMs to condense and distil large amounts of information into concise summaries. With summarization prompting, a longer piece of text or a complex topic can be condensed into a shorter, more digestible form.

Implicit prompting involves guiding LLMs to generate desired outputs without explicitly specifying the task or providing detailed instructions. Instead of directly stating what you want the model to do, implicit prompting relies on indirect cues, context, or partial information to steer the model towards the intended outcome.

Perspective prompting involves crafting prompts or questions for LLMs in a way that encourages a particular viewpoint or perspective in the responses. It's like seeing things from someone else's perspective to gain a deeper understanding.

Self-ask prompting in prompt engineering is directed towards the users as a guide for them to provide additional information or clarify their request within the same interaction. In short, the user is asked to elaborate on their initial input or specify their needs further in order to generate the desired output.

Mastering prompt engineering techniques is a pivotal skill for navigating the vast capabilities of Large Language Models (LLMs). Through this beginner's guide, we've explored foundational principles and practical strategies to craft prompts that optimize AI model responses effectively.