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)→
More from Models
- GPT-6 Sol and Luna already usable in Codex, early user reports — airesearch12 · 2026-09-23
- GPT-6 Sol scores slightly below GPT-5.6 Sol on DeepSWE, only cheaper — Angaisb_ · 2026-09-23
- Matt Shumer on Opus 5.5: 'feels like a much smarter Opus 4.6' — mattshumer_ · 2026-09-23
- GPT-6 Sol claimed to cost 50% less than GPT-5.6 Sol — cedric_chee · 2026-09-23
- Four frontier models in days: Grok 4.7, Opus 5.5, GPT-6 Sol and Luna — msg · 2026-09-23
- OpenAI reportedly rolling out GPT-6 Sol and GPT-6 Luna on ChatGPT, Codex, and APIs — testingcatalog · 2026-09-23