minus-squarefrañzcoz@feddit.cltoTechnology@lemmy.world•New study sheds light on ChatGPT’s alarming interactions with teenslinkfedilinkEnglisharrow-up12arrow-down2·edit-218 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 linkfedilink
minus-squarefrañzcoz@feddit.cltoFediverse@lemmy.world•A Privacy-First Tool to Manage Your Bluesky AccountlinkfedilinkEnglisharrow-up2·2 months agoAnd “6 `oא in bsky social” linkfedilink
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