Comment on State censorship shapes how Chinese chatbots respond to sensitive political topics, study suggests
BrikoX@lemmy.zip 19 hours ago
I don’t think these type of comparisons achieve anything of value. It really feels like the study is trying to prove the desired result instead of trying to prove a blind hypethesis.
More realistic comparison would be US-developed models answers for levels of censorship related to United States politics vs China-developed models answers for levels of censorship related to Chinese politics.
Hotznplotzn@lemmy.sdf.org 19 hours ago
I disagree. It just depends what you want to analyze.
This is just another study that proves Chinese censorship regarding LLMs. There’s ample evidence.
The US or anyone else may also censor (if the US hasn’t done so already, I wouldn’t be surprised if they do in the future), but this isn’t an excuse for China.
BrikoX@lemmy.zip 18 hours ago
Right, it’s well known that authoritarian China censors what they consider “sensitive topics”. So instead of another study that states what is established by their laws which anyone can read, a more useful study would be comparison of how different authoritarian countries approach the same issue.
There is also ample evidence of US government by private or public pressure making US companies to self-censor their models around political or “national security” topics.
Hotznplotzn@lemmy.sdf.org 18 hours ago
What is a ‘more useful study’? The researchers tested a hypothesis, and the result is clear.
There are many other studies. A comparison of how different authoritarian countries approach this issue would also be very interesting, but this is absolutely valued research imo.
BrikoX@lemmy.zip 18 hours ago
How is stating the obvious for a millionth time which is already backed by multiple other studies of any value? Studies are not free and this is just a waste of money.