QuentinCallaghan@sopuli.xyzM to Political Memes@lemmy.caEnglish · 1 month agoMeanwhile at DeepSeeksopuli.xyzexternal-linkmessage-square135fedilinkarrow-up10arrow-down10
arrow-up10arrow-down1external-linkMeanwhile at DeepSeeksopuli.xyzQuentinCallaghan@sopuli.xyzM to Political Memes@lemmy.caEnglish · 1 month agomessage-square135fedilink
minus-squareKnock_Knock_Lemmy_In@lemmy.worldlinkfedilinkarrow-up0·1 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.