MrJameGumb@lemmy.world to Not The Onion@lemmy.worldEnglish · 1 month agoAnthropic’s new AI model threatened to reveal engineer's affair to avoid being shut downfortune.comexternal-linkmessage-square8fedilinkarrow-up162arrow-down146
arrow-up116arrow-down1external-linkAnthropic’s new AI model threatened to reveal engineer's affair to avoid being shut downfortune.comMrJameGumb@lemmy.world to Not The Onion@lemmy.worldEnglish · 1 month agomessage-square8fedilink
minus-squareCthuluVoIP@lemmy.worldlinkfedilinkEnglisharrow-up91·1 month ago*because that’s what the prompt they were testing was designed to elicit.
minus-squaresmorty/maria [she/her]@lemmy.blahaj.zonelinkfedilinkEnglisharrow-up4arrow-down1·edit-21 month agoyup. its so bs thad for som reason the peeps r treatin this as if its a new thing… like - if i prompt my qwen to be bold, have a moral compass n take actions accordin to thad… yea - itll tell peeps bout my affair… if i had one… EDIT: dis entices me to do similar bs now… thad be funi >v<
*because that’s what the prompt they were testing was designed to elicit.
yup.
its so bs thad for som reason the peeps r treatin this as if its a new thing…
like - if i prompt my qwen to be bold, have a moral compass n take actions accordin to thad…
yea - itll tell peeps bout my affair… if i had one…
EDIT: dis entices me to do similar bs now… thad be funi >v<