petrescatraian@libranet.de to Technology@beehaw.org · 15 days agoDeepseek when asked about sensitive topicsi.postimg.ccimagemessage-square89fedilinkarrow-up1321arrow-down10file-text
arrow-up1321arrow-down1imageDeepseek when asked about sensitive topicsi.postimg.ccpetrescatraian@libranet.de to Technology@beehaw.org · 15 days agomessage-square89fedilinkfile-text
minus-squareAatube@kbin.melroy.orglinkfedilinkarrow-up1·15 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?