Beep@lemmus.org to Technology@lemmy.worldEnglish · 8 days agoAI 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-square16fedilinkarrow-up1142arrow-down18file-textcross-posted to: [email protected]
arrow-up1134arrow-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.org to Technology@lemmy.worldEnglish · 8 days agomessage-square16fedilinkfile-textcross-posted to: [email protected]
minus-squarePabloSexcrowbar@piefed.sociallinkfedilinkEnglisharrow-up2·7 days agoYou can give system prompts that tell most of them to be more antagonistic, but I don’t know of any that do it by default.
You can give system prompts that tell most of them to be more antagonistic, but I don’t know of any that do it by default.