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)→
More from Models
- Yacine: 'It might be over for OpenAI — and the killer isn't Claude, it's Gemini' — yacineMTB · 2026-11-21
- InferenceBench ranks agents on LLM serving speedup: Claude Opus 5.5 tops at 12.08x, agents lose to simple hyperparameter search — maksym_andr · 2026-11-21
- Inkling-2-Mini quants are a trap: 17GB weights overflow 48GB VRAM at long context — EmilPi · 2026-11-21
- Cloudflare launches multimodal model clairic-flash, trending on Hugging Face — Cloudflare · 2026-11-21
- Claude's Riemann Hypothesis proof called 'almost certainly true' by mathematicians — Just-Grocery-2229 · 2026-11-21
- Long-press Gemini's model selector reveals periodic-table UI with four Gemini 4 models — testingcatalog · 2026-11-21