cm0002@lemmy.world to Technology@lemmy.worldEnglish · 8 days agoThe FTC cracks down on an AI content detector that promised 98% accuracy but was only right 53% of the time.www.pcmag.comexternal-linkmessage-square35fedilinkarrow-up1442arrow-down13
arrow-up1439arrow-down1external-linkThe FTC cracks down on an AI content detector that promised 98% accuracy but was only right 53% of the time.www.pcmag.comcm0002@lemmy.world to Technology@lemmy.worldEnglish · 8 days agomessage-square35fedilink
minus-squaresimple@lemm.eelinkfedilinkEnglisharrow-up80arrow-down7·8 days ago53% is abysmal, it might as well be a coin flip. FYI this article is about a random one called BrandWell, popular AI detectors like GPTZero are much more accurate.
minus-squarethemeatbridge@lemmy.worldlinkfedilinkEnglisharrow-up45arrow-down1·8 days agoMuch more accurate than guessing is not a strong endorsement.
minus-squareDr. Moose@lemmy.worldlinkfedilinkEnglisharrow-up35·7 days agoAll of it is snake oil, it’s fundamentally not possible to detect ai generated text without watermarking it first.
53% is abysmal, it might as well be a coin flip. FYI this article is about a random one called BrandWell, popular AI detectors like GPTZero are much more accurate.
Much more accurate than guessing is not a strong endorsement.
All of it is snake oil, it’s fundamentally not possible to detect ai generated text without watermarking it first.