Models spot writing tics humans can't — why AI-detection goes beyond style feel
Afinetheorem · x · 2026-09-22
The author argues AI-detection shouldn't rely on human intuition alone: models can pick up subtle stylometric signals, like differences in how male vs. female characters begin sentences — habits even the original author wouldn't realize. One or two such tics are normal; all of them together are nearly impossible to fake.
Related event: Models can spot writing patterns invisible even to their authors(3 posts)→
More from AGI Musings
- AI professor Toby Walsh publishes call for control of frontier AI models — TobyWalsh · 2026-09-23
- Andrew Ng: AI danger fears are an orchestrated PR hype, a setback for the field — sudoraohacker · 2026-09-23
- Alignment researcher: without a slowdown, p(doom) > 0.1 — ArthurConmy · 2026-09-23
- Alignment researcher: without slowdown, p(doom) is above 10% — ArthurConmy · 2026-09-23
- ICLR load debate: capping submissions per author would barely dent paper counts, data shows — jonasgeiping · 2026-09-23
- Hackers breached OpenAI in days, per WSJ — challenging the case for frontier-model advantage — ben_j_todd · 2026-09-23