Key Takeaways
- If you want to make ChatGPT's tone more human-like, use ChatGPT Plus subscription to switch to GPT-4 rather than GPT-3.5 Turbo. You'll also have access to the "Humanize" plugin which will also make the text more natural.
- If you don't have ChatGPT Plus, you can simply ask for more humanized text, or prompt ChatGPT to imitate a specific author's voice.
By default, ChatGPT has a voice and writing style that might not come across as completely natural or could even be flagged by AI text "detectors," but you don't have to settle for the default tone and style ChatGPT uses.
We're using a popular AI text detector here as a way to demonstrate that these methods make a real difference to the text, but it's important to note that AI text-detection tools are not a reliable way to tell if the text is AI-generated or not. These tools have fundamental problems that make them unsuitable for determining whether text is human-written. On top of this, while text may pass a detector, it might still obviously read as nonsense to a human reader. So use your own judgment on whether the humanized output is good enough for your needs or not.
Method 1: Use ChatGPT-4
If you're a ChatGPT Plus subscriber, you'll have access to GPT-4, which is much more capable and sophisticated than the standard GPT 3.5 Turbo model that's on by default. Just left to its own devices, GPT-4 produces much more natural text, and in my testing using the popular GPT Zero service is much less likely to trigger a result that's confident of AI text. Here I've asked GPT-4 to write an opinion piece on why manual transmissions are better than automatic (because they are).
In this case, on the second re-roll of the prompt, we get a good result and manually editing the few low-perplexity sentences is no big deal.
Not sure what that means? With AI text detectors, you'll often run into the terms "perplexity" and "burstiness." These are two specific measures used to estimate whether a piece of text was generated by an AI. Perplexity is a measurement of the randomness in the text, and burstiness is a measurement of how much perplexity itself varies.
The detector uses the results of these two measurements to estimate how likely a text is to be AI-generated. Different AI detectors might use different algorithms or measurements, but the principle is broadly the same. If we put the text from this article into GPT Zero we get the result "Your text is most likely human written" (phew!) and this is what the perplexity and burstiness scores look like.
Method 2: Use The "Humanize" Plugin
This is another method only available to ChatGPT Plus subscribers. Using the third-party "Humanize" plugin, you can process text generated by ChatGPT so that its vocabulary, cadence, and other text attributes are more human-like. We just ask ChatGPT to use the plugin on our text.
However, plugins are still a beta feature, and at the time of writing, the Humanize plugin seemed to have issues, although I've had good results with it in the past. There are also many other plugins in the store (with more added frequently) that promise to rephrase or otherwise humanize text for you, so have a browse of what's on offer.
Method 3: Just Ask for Humanized Text
However, you might not need that plugin at all, since you can use the magic word "Humanize" in your ChatGPT prompt, whether you're using 3.5 or version 4. Of course, GPT-4 is much more successful on average, but you can take text generated by GPT 3.5 and ask GPT-4 to humanize it as well, or you can write your prompt to ask for humanized text, e.g. "Please write a humanized article."
After asking GPT-4 to humanize its text, we get a full endorsement from GPT Zero, but also the actual text reads much better than before.
Method 4: Prompt Specific Author Styles
Finally, another way to get more human-like output is to ask ChatGPT to emulate an author it knows or by providing it with a sample writing style. We've covered how to make ChatGPT copy your writing style in detail, so I won't repeat it all here. I'm simply going to ask ChatGPT to rewrite that first piece of text in my own writing style.
If you're a ChatGPT Plus subscriber, you can use the Custom Instructions to make permanent changes to how ChatGPT responds in every chat, as long as those instruction are active.
Again, we get a result for human, with a few single sentences flagged as potentially AI-generated.
You can also add additional flavor to your prompt, such as asking for the tone to be casual, friendly, etc., and in many cases, this will result in GPT Zero reporting with confidence that the text is human.
While I'm using GPT Zero as an example here, you'll find similar outcomes with any AI detection tool you may want to try. You'll also find that these detectors do not agree on the same piece of text.
These are just a few of the ways you can improve the quality of the text that you get from ChatGPT, but don't forget that ChatGPT is still prone to providing inaccurate information, and just making things up out of thin air. Which is perhaps the most human thing that it does!