Skip to content

Instantly share code, notes, and snippets.

Show Gist options
  • Save fmachado/324f351bba11ced334a3bfc00067bf0c to your computer and use it in GitHub Desktop.
Save fmachado/324f351bba11ced334a3bfc00067bf0c to your computer and use it in GitHub Desktop.
prompt-write-like-a-human
1. Using Dependency Grammer:
Dependency grammar, a linguistic framework, connects words in a sentence based on their dependencies, showing how each word relies on a main word (like a verb) to form meaningful structures. You can test it out by copying and pasting the below prompt. But I can already perceive the content created by ChatGPT to be atleast 90% human written.
Prompt:
Use the dependency grammar linguistic framework to craft a [ARTICLE/POST/BLOG/ETC.]. The idea is that the closer together each pair of words you’re connecting are, the easier the copy will be to comprehend. Here is the topic and additional details: [TITLE] [DETAILS]
2. Burstiness and Perplexity:
The provided prompt aims to guide large language models (LLMs) to generate content that closely resembles human-written text. It does this by emphasizing two key factors: "perplexity" and "burstiness." Perplexity measures the complexity of the text, essentially how difficult it is to understand. By asking the model to incorporate a good amount of perplexity, the prompt encourages the generation of content with varying degrees of complexity, similar to what humans naturally produce.
Prompt:
When it comes to writing content, two factors are crucial, "perplexity" and "burstiness." Perplexity measures the complexity of text. Separately, burstiness compares the variations of sentences. Humans tend to write with greater burstiness, for example, with some longer or complex sentences alongside shorter ones. AI sentences tend to be more uniform. Therefore, when writing the following content I am going to ask you to create, I need it to have a good amount of perplexity and burstiness. Here is the topic and additional details: [TITLE] [DETAILS]
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment