minus-squarelars@programming.devtoTechnology@lemmy.ml•ethinically ambigauslinkfedilinkarrow-up29·1 year agoYes. The training data has a bias, and they are using a cheap hack (prompt manipulation) to try to patch it. linkfedilink
Yes. The training data has a bias, and they are using a cheap hack (prompt manipulation) to try to patch it.