Detecting AI writing is doable: pattern matching in high dimensions is what DL does best

Afinetheorem · x · 2026-09-22

In a thread on how to tell whether an author or provost used AI to write something, mathematician blogger Afinetheorem argues humans only notice the kind of clues a Shakespeare scholar would spot — short sentences, metaphors — while models pick up far more subtle signals.

He adds that pattern matching on high-dimensional or nonparametric aspects of data is literally what deep learning is best at, so it's no surprise that seriously attempting AI-authorship detection turned out to be completely doable.

Related event: Models can spot writing patterns invisible even to their authors(3 posts)→

Original post →

More from Models

Models channel →