QuentinCallaghanM to Political [email protected]English • 1 month agoMeanwhile at DeepSeeksopuli.xyzimagemessage-square140fedilinkarrow-up1989arrow-down114
arrow-up1975arrow-down1imageMeanwhile at DeepSeeksopuli.xyzQuentinCallaghanM to Political [email protected]English • 1 month agomessage-square140fedilink
minus-square@Knock_Knock_Lemmy_Inlink6•1 month agoI 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.
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.