Burstiness
The variation in complexity and length across the sentences of a passage. Human writing tends to be bursty — long sentences next to short ones — while generated text tends to be more uniform.
Why it matters
Burstiness is the second signal AI detectors measure, and unlike most detection jargon it is directly useful for editing: deliberately varying your sentence and paragraph rhythm is one of the fastest ways to make any draft read better, generated or not.
A concrete example
Read a paragraph aloud and notice whether every sentence takes about the same breath. A generated draft usually does. A human draft usually has one sentence that runs long while working something out, then a short one that lands — that unevenness is burstiness, and it is most of what makes prose feel alive.
How to use it
Burstiness is the other half of what detectors measure, and it is a useful idea for editing regardless of detection. Human writing varies: a long sentence working through a qualification lands on a short one, a six-line paragraph is followed by a two-line one. Generated prose is regular, because probable text is regular. If you are editing a draft, deliberately varying sentence and paragraph length is one of the highest-leverage changes you can make — it improves how the piece reads, and the detection effect is incidental.
The common mistake
Trying to raise burstiness mechanically. Varying sentence length at random produces rhythm that changes for no reason, which reads as odd rather than as human. The variation should follow the argument — short sentences where a point lands, longer ones where something is being worked through.
Related terms
Perplexity
A measure of how surprising a piece of text is to a language model — roughly, how unexpected each word is given the ones before it. Low perplexity means the text follows predictable paths.
AI Detector
A tool that estimates whether a passage of text was generated by an AI model, by measuring statistical properties of the writing rather than by checking any record of its origin.
AI Dubbing
Automated translation and re-voicing of audio/video content into other languages while preserving the original speaker's voice characteristics, timing, and emotional delivery.
AI Orchestration
Coordinating multiple AI models, tools, and data sources in a unified pipeline. An orchestration layer manages prompt routing, context passing, error handling, and output aggregation across different AI services.
API (Application Programming Interface)
A way for software applications to communicate with each other. AI APIs let developers integrate AI capabilities into their own applications programmatically.
Attention Mechanism
A technique that allows AI models to focus on the most relevant parts of input data when generating output. In language models, attention determines which words in a sentence are most important for understanding each other word.