Re:Identifying and Eliminating CSAM in Generative ML Trainin...
by akomtu on Wednesday December 20, 2023 @05:07PM
(#38714281)
Are they going to "lobotomize" ML models to make csam unthinkable for it, or are they going to teach it that csam is bad?
[ Parent
| on HN ]
Re:Identifying and Eliminating CSAM in Generative ML Trainin...
by tedivm on Wednesday December 20, 2023 @05:22PM
(#38714431)
The two paragraph abstract states that the goal is to identify CSAM in the training data itself and remove it. They ran a study and found "many hundreds of instances of known CSAM in the [LAION-5B] training set".