PlasticLove@lemmy.today to Mildly Infuriating@lemmy.worldEnglish · edit-28 months agoChinese AI - Double Standardslemmy.todayimagemessage-square82fedilinkarrow-up1721arrow-down135
arrow-up1686arrow-down1imageChinese AI - Double Standardslemmy.todayPlasticLove@lemmy.today to Mildly Infuriating@lemmy.worldEnglish · edit-28 months agomessage-square82fedilink
minus-squareQuaternionsRock@lemmy.worldlinkfedilinkEnglisharrow-up2·8 months agoI think this is from an open-source model, possibly running locally. I doubt it has a robust post-generation censor. This output is probably a result of RLHF, which is even more precarious than an output censor.
I think this is from an open-source model, possibly running locally. I doubt it has a robust post-generation censor. This output is probably a result of RLHF, which is even more precarious than an output censor.