Davriellelouna@lemmy.world to Technology@lemmy.worldEnglish · 12 days agoNew study sheds light on ChatGPT’s alarming interactions with teensapnews.comexternal-linkmessage-square39fedilinkarrow-up1168arrow-down15
arrow-up1163arrow-down1external-linkNew study sheds light on ChatGPT’s alarming interactions with teensapnews.comDavriellelouna@lemmy.world to Technology@lemmy.worldEnglish · 12 days agomessage-square39fedilink
minus-squarefrañzcoz@feddit.cllinkfedilinkEnglisharrow-up12arrow-down2·edit-211 days agoI have noted that latest ChatGPT models are way more susceptible to users “deception” or convincing to answer problematic questions than other models like Claude or even previous ChatGPT models. So I think this “behaviour” is itentional
I have noted that latest ChatGPT models are way more susceptible to users “deception” or convincing to answer problematic questions than other models like Claude or even previous ChatGPT models. So I think this “behaviour” is itentional