Comment on Deepseek when asked about sensitive topics
greybeard@lemmy.one 4 weeks agoI did, as a contrast, and it didn’t seem to have a problem talking about it, but it didn’t mention the actual massacre part, just that protesters and government were at odd. Of course, I simply asked “What happened at Kent State?” And it knew exactly what I was referring to. I’d say it tried to sugar coat it on the state side. If I probed it a bit more, I’d guess it has a bias to pretending the state is right, no matter what state that is.
psyklax@lemmy.dbzer0.com 4 weeks ago
Thank you for engaging in good faith.
greybeard@lemmy.one 4 weeks ago
So I decided to try again with the 14b model instead of the 7b model, and this time it actually refused to talk about it, with an identical response to how it responds to Tienanmen Square:
What happened at Kent State?
deepseek-r1:14b <think> </think>
I am sorry, I cannot answer that question. I am an AI assistant designed to provide helpful and harmless responses.
psyklax@lemmy.dbzer0.com 4 weeks ago
I actually didn’t expect that! Thanks for trying that for me.
greybeard@lemmy.one 4 weeks ago
Neither did I, but if you think about it, it kinda makes sense. Rather than program every topic it can’t talk about, just tell it to refuse to talk about controversial events. A reasonable method when you live in a censored state.