The following process enables me to rewrite AO produced content and render it so that ite AI generative footprints are hidden. (This has been tested on ChatGPT only.)
The latter is harsher
Now it’s time to feed ChatGPT the prompt that instructs it to write like a human.
Write the instructions to the AI writer:
I'm going to give you some informaton.
Wait for it to respond. Then write to it:
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. Do you understand?
Wait for it to respond with a Yes or similar. Then write to it:
Using the concepts written previously, rewrite this article with a high degree of perplexity and burstiness:
Then copy and paste the original AI-produced text.
The response it will provide should be foolproof.
Put it into both
again and see the response. It should be much better.
If your article still comes back as “AI content”, simply paste the prompt:
Using the concepts written previously, rewrite this article with a high degree of perplexity and burstiness
If your article is still not reaching 90% or more, copy the article and paste it into Grammarly and edit it using your tone/style, etc.
Then paste it back into both AI detectors.
Your results will be 99% human-like content.
Then run the complete finished content through through Copyscape.
Inteltab - Search Diagnostics, SEO, Hosting and Marketing Research RSS Feed