Beep@lemmus.orgBanned to Technology@lemmy.worldEnglish · 29 天前AI overly affirms users asking for personal advice— Not only are AIs far more agreeable than humans when advising on interpersonal matters, but users also prefer the sycophantic models.news.stanford.eduexternal-linkmessage-square16linkfedilinkarrow-up1155arrow-down19file-textcross-posted to: fuck_ai@lemmy.worldhackernews@lemmy.bestiver.se
arrow-up1146arrow-down1external-linkAI overly affirms users asking for personal advice— Not only are AIs far more agreeable than humans when advising on interpersonal matters, but users also prefer the sycophantic models.news.stanford.eduBeep@lemmus.orgBanned to Technology@lemmy.worldEnglish · 29 天前message-square16linkfedilinkfile-textcross-posted to: fuck_ai@lemmy.worldhackernews@lemmy.bestiver.se
minus-squarebluGill@fedia.iolinkfedilinkarrow-up1·28 天前Sometimes it will, but I’ve had a few times where it didn’t.
Sometimes it will, but I’ve had a few times where it didn’t.