Driftn.
What happens to a detector's accuracy as the underlying language models keep improving. A detector trained on last year's GPT output silently gets worse on this year's, because the gap between model writing and human writing has narrowed. The fix is continual re-evaluation, not a one-time benchmark.
Paste any text to see how likely it reads as AI — with the same calibrated three-way breakdown this glossary describes.
Try the free AI detector →