PlasticLove@lemmy.today to Mildly Infuriating@lemmy.worldEnglish · edit-210 months agoChinese AI - Double Standardslemmy.todayimagemessage-square108fedilinkarrow-up1666arrow-down134
arrow-up1632arrow-down1imageChinese AI - Double Standardslemmy.todayPlasticLove@lemmy.today to Mildly Infuriating@lemmy.worldEnglish · edit-210 months agomessage-square108fedilink
minus-squareQuaternionsRock@lemmy.worldlinkfedilinkEnglisharrow-up2·10 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.