QuentinCallaghan@sopuli.xyzM to Political Memes@lemmy.caEnglish · 23 hours agoMeanwhile at DeepSeeksopuli.xyzimagemessage-square70fedilinkarrow-up1696arrow-down19
arrow-up1687arrow-down1imageMeanwhile at DeepSeeksopuli.xyzQuentinCallaghan@sopuli.xyzM to Political Memes@lemmy.caEnglish · 23 hours agomessage-square70fedilink
minus-squareKnock_Knock_Lemmy_In@lemmy.worldlinkfedilinkarrow-up6·13 hours 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.