Basics of Prompting
![](https://cdn.prod.website-files.com/64a73265ea06a02bc3eab456/64e9c0c916c9dfdb0a07e190_Prompt-engineering-featured.png)
Impressive results can be achieved using simple prompts and precise guidance of the language model
You can achieve a lot with simple prompts, but the quality of results depends on how much information you provide it and how well-crafted it is. A prompt can contain information like the instruction or question you are passing to the model and include other details such as context, inputs, or examples. You can use these elements to instruct the model better and, as a result, obtain better outcomes.
Let's begin by examining a basic example of a simple prompt:
Prompt:
Apples taste
Output:
sweet and crisp
The taste of apples can vary depending on the variety. Some are sweet and crisp, while others might have a more tart flavor.
As you can observe, the language model generates a continuation of text that makes sense within the context of the prompt "Apples taste". The output may not always perfectly align with the intended task.
This basic example also underscores the significance of providing sufficient context or instructions to achieve the desired result.
Let's attempt to refine it slightly:
Prompt:
Please complete the sentence:
Apples taste
Output:
especially delicious when freshly picked from an orchard.
Is this an improvement? Certainly, because you directed the model to complete the sentence, the result corresponds more closely to your intended meaning, adhering to the specific instruction given. This practice of strategically designing prompts to guide the model's task performance is referred to as prompt engineering.
The example above serves as a fundamental illustration of the capabilities of modern Language Models (LLMs). Contemporary LLMs have the capability to perform a wide range of advanced tasks, spanning from summarizing text to engaging in mathematical reasoning to generating code.