That censorship is not inherited. The censorship in the corpus of training data is though.
Seems like the CPC just approached someone in Deepseek and said “fix this up before the next release” and provided tool to determine what qualifies for removal, which is why it happens post-generation.
That censorship is not inherited. The censorship in the corpus of training data is though.
Seems like the CPC just approached someone in Deepseek and said “fix this up before the next release” and provided tool to determine what qualifies for removal, which is why it happens post-generation.