Last reviewed
May 11, 2026
Sources
No citations yet
Review status
Needs citations
Revision
v2 · 2,150 words
Add missing citations, update stale details, or suggest a clearer explanation.
See also: Guides, ChatGPT Guides and Prompt Engineering Guides
This guide explains a popular prompt engineering pattern that asks ChatGPT to write text according to five sliders: perplexity, burstiness, professionalism, randomness, and sentimentality. The pattern circulated widely on YouTube and X in early 2023 as users tried to make AI output sound more human and less detectable by tools like GPTZero and Originality.ai. It is worth saying up front that this is a prompt template, not real model fine-tuning. The article uses the word "fine-tune" loosely. No weights are changed and no training data is added. The user simply gives the assistant a numbered set of style instructions and asks it to obey them on each turn.
The prompt declares a scale from 1 to 10 for each of the five parameters, sets a default value of 5, and asks the model to list its current settings at the top of every reply. After the parameter table the user includes a confirmation line such as "Please confirm that you understand the parameters of this prompt by responding with 'I understand'." Once the model confirms, the user can ask for an essay, a product description, a story, or any other piece of writing, and the model is supposed to honor the parameter values in its output.
In practice the technique works because large language models follow system-style instructions reasonably well within a single conversation. They do not always hit the requested numbers precisely, especially at the extremes, but they do shift their style in the requested direction. A perplexity setting of 9 makes the assistant reach for harder vocabulary. A burstiness setting of 9 makes it mix one-word sentences with rolling, clause-stuffed ones. A sentimentality setting of 1 strips out feeling words.
Perplexity is a real term from natural language processing. For a language model and a sequence of tokens, perplexity is the exponentiated average negative log-likelihood of that sequence. In plain English, it measures how surprised the model is by the text. A sequence the model finds very likely has low perplexity. A sequence full of rare words and odd transitions has high perplexity. The formula given by Hugging Face's documentation is PPL(X) = exp(-1/t sum log p(x_i | x_<i)).
AI detectors built on top of this idea, including GPTZero, treat low perplexity as a signal of machine authorship. The reasoning is straightforward. A model trained to maximize probability tends to produce text that other models also find probable. Human writers reach for slang, unusual word choices, and idioms that any single model would not have predicted, so their average perplexity sits higher.
When the prompt sets perplexity to 1, the assistant writes with short common words and predictable phrasing. At 10 it pulls in latinate vocabulary, uncommon idioms, and longer noun phrases. Asking for a perplexity of 8 or 9 is the standard move when the user is trying to evade detection. There is no guarantee the resulting score will actually rise on a detector, only that the surface style will look more varied.
Burstiness is variance in sentence length and structure. The term has two roots in computer science. In information retrieval it dates to work by Slava Katz in the mid 1990s on the observation that once a word appears in a document it is more likely to appear again. In streaming and topic detection it traces to Jon Kleinberg's 2003 paper "Bursty and Hierarchical Structure in Streams," which models sudden spikes in word frequency.
GPTZero borrowed the word for a related but distinct purpose. The detector compares the perplexity of each sentence in a passage and asks how much that score varies. A long passage of equally surprising sentences is treated as low burstiness. A passage that mixes a low-perplexity opener with a high-perplexity aside is treated as high burstiness. According to GPTZero's own write-up, burstiness is the metric that lets the tool reason about long-form context rather than only individual sentences.
Human writing tends to be bursty because writers slow down for setup, speed up for emphasis, and break rhythm on purpose. AI writing tends to be flat because models trained on cross-entropy loss converge on a comfortable middle band. Asking ChatGPT for a burstiness of 9 nudges it toward the human pattern: short sentences next to long ones, sometimes a one-word fragment, sometimes a clause that runs for half a paragraph.
Professionalism is not a detection metric. It is a style axis, similar to formality in linguistics. At a setting of 1 the assistant uses contractions, slang, hedge words, and conversational filler. At 10 it removes contractions, prefers passive constructions for distance, and reaches for the kind of vocabulary that appears in white papers and regulatory filings. The setting effectively chooses where on the register scale the output should sit.
This parameter overlaps with the system prompt idea of giving the model a persona. Asking for professionalism 10 is roughly the same as telling the model to write like a corporate lawyer. Asking for professionalism 2 is roughly the same as telling it to write like a friend texting on a Saturday afternoon. The numbered scale just makes it easier for users to dial the register up or down without rewriting the persona each time.
Randomness is the trickiest of the five because it collides with how the OpenAI API already works. The chat models expose two real sampling controls, temperature and top-p. Temperature scales the logits before softmax and ranges from 0 to 2 by default. Higher temperature flattens the probability distribution and produces more varied output. Top-p, also called nucleus sampling, restricts the next-token draw to the smallest set of tokens whose cumulative probability exceeds p. Lower top-p means more focused output.
The randomness slider in this prompt does not actually change temperature or top-p. The model has no way to alter its own sampling settings mid-conversation. What it does instead is mimic the perceived effect of higher temperature: it picks less obvious next words, swerves into unexpected topics, and lets sentences drift. At a setting of 10 the prompt warns that output may be "almost completely random and nonsensical," which matches what real temperature 2 output tends to look like.
For users who have access to the API rather than the consumer ChatGPT interface, the more reliable way to get the randomness effect is to set temperature directly. Useful values for creative writing tend to sit between 0.7 and 1.2. Anything above 1.5 produces text that drifts off topic and contradicts itself.
Sentimentality is the emotional dial. At 1 the output is neutral and reportorial. At 10 it leans on adjectives of feeling, includes first-person reactions, and reaches for metaphors of warmth, loss, and longing. This parameter draws on sentiment analysis intuition without using a formal sentiment score. The model knows what emotionally loaded writing looks like because it has seen plenty of it in training data, so the slider works through stylistic mimicry rather than measurement.
Users writing marketing copy often set sentimentality to 6 or 7 to add warmth without melodrama. Users writing technical documentation usually set it to 1 or 2 to keep the prose factual. Users writing fiction or personal essays push it higher.
The most common version of the prompt looks something like this in spirit, though specific wording varies across the YouTube tutorials that popularized it:
In order to generate a text response, please adhere to the following parameters.
Each parameter is set on a scale from 1 to 10, where a higher value represents
more of the specified attribute. Include the current values at the top of your
response in a bulleted list before the actual text.
Perplexity: (1-10)
Burstiness: (1-10)
Professionalism: (1-10)
Randomness: (1-10)
Sentimentality: (1-10)
Default each parameter to 5. Confirm that you understand by responding
with "I understand." Then wait for the topic.
After the confirmation, the user supplies the actual request. Example: "Write a 400 word blog introduction about home espresso machines. Perplexity 8, burstiness 9, professionalism 4, randomness 5, sentimentality 6." The assistant then produces a draft with those settings echoed at the top of the reply.
GPTZero went public in January 2023, built by Princeton undergraduate Edward Tian. Within a week the tool had over 30,000 users and crashed once before Streamlit gave it more capacity. By July 2024 GPTZero reported around 4 million users. As schools and editors started pasting student work and freelance submissions into the checker, students and content writers began looking for ways to keep their AI-assisted drafts under the radar.
The perplexity and burstiness prompt pattern was the first widely shared answer. It made intuitive sense because it named the same metrics the detector was using. A YouTube tutorial in early 2023 by content creators around the SEO and AI writing space spread the template fast, and copycat prompts spawned variations that added randomness, sentimentality, professionalism, sarcasm, formality, and other style axes.
Whether the trick actually works against detectors is contested. Researchers at the University of Maryland published work showing that several AI text detectors are not reliable in practical settings, and Futurism reported error rates that would falsely accuse close to 20 percent of innocent students on certain samples. Ars Technica showed GPTZero flagging the United States Constitution as AI-generated because its phrasing is so regular. The point is that detectors miss in both directions, and a well-tuned prompt can produce text that passes them, but a hand-edited human draft can also fail them.
The biggest limitation is that the model does not actually measure perplexity or burstiness on its own output. It estimates the style it thinks would produce those scores. A user who pastes the result into GPTZero may find that perplexity has only moved slightly. The shift in surface style is real, but the underlying token probabilities still come from the same base model, and a fine-tuned classifier can still recognize the fingerprint.
A second limitation is consistency. Across a long document the model tends to drift back toward its comfortable middle band. Users who run the prompt across many turns often have to remind the assistant of the current parameter values every few exchanges. Some workflow guides recommend pasting the values at the start of every request instead of relying on the model to remember them.
A third limitation is that the most aggressive settings produce writing that humans also find odd. Perplexity 10 reads like a thesaurus with no taste. Burstiness 10 reads like a draft no one has revised. Randomness 9 produces sentences that contradict each other. The technique is most useful in the middle of the dial, with one or two parameters pushed up a notch, rather than at the extremes.
Real fine-tuning, in the sense OpenAI uses the term, involves additional training on a curated dataset to shift the model's weights toward a target style or domain. It changes how the model behaves at the parameter level, not just within a conversation. The five-parameter prompt does none of that. It is a style instruction, similar to telling the model to write in the voice of a particular author.
For users who genuinely need durable style control, the OpenAI fine-tuning API lets developers train a custom model on input-output pairs. A few hundred examples of the target voice is often enough to bias the model in that direction. The prompt-based approach is cheaper and instant, but it lives and dies with each conversation. Closing the chat resets the parameters, and a long enough document will start to slip out of the requested style.
The five-parameter prompt is a useful shorthand for getting ChatGPT to write in a more controlled style. Perplexity and burstiness are the two parameters that map to actual detector metrics. Professionalism, randomness, and sentimentality are style axes that the model handles through mimicry. The technique nudges output in the requested direction but does not literally measure or guarantee any numerical score. Used in moderation it produces livelier, more varied prose. Used at the extremes it produces text that is harder to read for humans and not necessarily safer from detectors.