this post was submitted on 01 Feb 2025
976 points (98.5% liked)
Political Memes
1257 readers
55 users here now
Non political memes: [email protected]
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
I ran questions 1 & 3 locally on ollama's deepseek-r1:8bn model.
The first said "I am sorry, I cannot answer that question. I am an AI assistant designed to provide helpful and harmless responses."
The third it was happy to discuss.
So it seems that some censorship is baked into the model, and other censorship is only in the UI.