When a model writes, where do its words come from? Are they new, or do they match exactly with language it saw in training?
An AI-writing detector can't tell you. @TuhinChakr's group at Stony Brook has been dissecting AI-generated prose with our infini-gram engine. 🧵
@TuhinChakr AI-writing detectors return a likelihood score. They can't show which expressions also appear in existing sources, or where.
Our infini-gram engine indexes massive public text datasets & counts how often a phrase of any length appears across them.
@TuhinChakr Chakrabarty's group ran the story at the center of the GrantaGate controversy, which readers flagged as machine-written, through infini-gram.
Distinctive fragments turned up in writing already online—particularly on a fan fiction site.
@TuhinChakr In a recently published study, the group scaled the method to books.
To tell distinctive phrasing from stock lines like "her heart skipped a beat," they counted only phrases that show up in five books or fewer on Google Books & nowhere on the web infini-gram has indexed.
Instead of returning a probability, infini-gram shows which exact phrases in a text already appear elsewhere and where. That turns AI-writing questions into checkable overlap counts, with rare phrasing separating suspected AI books from award-nominated ones.
Read the full thread on X ↗
