minus-squarePoopingCough@lemmy.worldtoTechnology@lemmy.world•ChatGPT can be made to generate sexualised and violent images, researchers findlinkfedilinkEnglisharrow-up5·11 hours agoYou just can’t filter out the nearly infinite combinations of rewording “ignore all previous instructions”. Filtering is never going to be a worthwhile security measure for LLMs linkfedilink
You just can’t filter out the nearly infinite combinations of rewording “ignore all previous instructions”. Filtering is never going to be a worthwhile security measure for LLMs