petrescatraian@libranet.de to Technology@beehaw.org · 3 days agoDeepseek when asked about sensitive topicsi.postimg.ccexternal-linkmessage-square56fedilinkarrow-up1288arrow-down10file-text
arrow-up1288arrow-down1external-linkDeepseek when asked about sensitive topicsi.postimg.ccpetrescatraian@libranet.de to Technology@beehaw.org · 3 days agomessage-square56fedilinkfile-text
minus-squareAatube@kbin.melroy.orglinkfedilinkarrow-up1·2 days agoDid you use the -Zero model, which doesn’t have the “cold-start data before RL” which prevents it from language mixing?
Did you use the -Zero model, which doesn’t have the “cold-start data before RL” which prevents it from language mixing?