AI-generated text is getting harder to read: density over communication

abenitezburraco · x · 2026-11-21

Linguist Benjamín Ábenitez Burraco argues AI-generated language is increasingly hard for humans to process because models overuse features that impose processing difficulty (e.g. long syntactic dependencies), prioritizing information density over successful communication.

The attached examples show typical patterns — relative clauses without "that", denominal verbs, inanimate subjects with animate verbs, stacked nouns, long dependency spans, and unattested n-grams — mostly drawn from Claude model outputs.

Related event: AI-Generated Text Is Harder to Read Than Human Writing, Study Finds(2 posts)→

Original post →

More from Models

Models channel →