← Back to context

Comment by cscurmudgeon

3 months ago

A US Tiananmen-comparable example would be ChatGPT censoring George Floyd's death or killing of Native Americans, etc. ChatGPT doesn't censor these topics

There may not be a proper US example. But if you ask a western LLM about the impact of the 20th century Nordic involuntary sterilizations, you’ll see some heavy RLHF fingerprints. Not going to make an argument one way or another on that, other than to say I would not expect the same answers from a Chinese LLM.