floofloof@lemmy.ca to Technology@lemmy.worldEnglish · 1 year ago‘ChatGPT detector’ catches AI-generated papers with unprecedented accuracywww.nature.comexternal-linkmessage-square49fedilinkarrow-up1185arrow-down140cross-posted to: science@mander.xyzacademia@mander.xyz
arrow-up1145arrow-down1external-link‘ChatGPT detector’ catches AI-generated papers with unprecedented accuracywww.nature.comfloofloof@lemmy.ca to Technology@lemmy.worldEnglish · 1 year agomessage-square49fedilinkcross-posted to: science@mander.xyzacademia@mander.xyz
minus-squaresimple@lemm.eelinkfedilinkEnglisharrow-up36·1 year agoWilling to bet it also catches non-AI text and calls it AI-generated constantly
minus-squarefloofloof@lemmy.caOPlinkfedilinkEnglisharrow-up12·edit-21 year agoThe original paper does have some figures about misclassified paragraphs of human-written text, which would seem to mean false positives. The numbers are higher than for misclassified paragraphs of AI-written text.
Willing to bet it also catches non-AI text and calls it AI-generated constantly
The original paper does have some figures about misclassified paragraphs of human-written text, which would seem to mean false positives. The numbers are higher than for misclassified paragraphs of AI-written text.