Hacker News new | ask | show | jobs
by gruez 490 days ago
>Some versions of DeepSeek’s models have bias built in

Is this empirically supported? IME it doesn't hesitate to talk about Tienanmen Square or whatever, so if there's "bias" it must be very well hidden.
2 comments
blackeyeblitzar 490 days ago
Yes if you search, lots of people have shared evidence of this. But it depends on which model you’re using, as some seemingly don’t have the bias built into their training.
link
nickthegreek 490 days ago
And they also shared how trivial it is to bypass. It is one of the most uncensored released models that you can run privately from my understanding.

If you have a better model for the OP to run, please present it.

Edit: https://huggingface.co/perplexity-ai/r1-1776

Just released.

link
tiberius_p 490 days ago
The 1.1B model which I used refuses to talk about Tienanmen Square.
link