It does, and it’ll tell you about it. But it’s their interface that censores the output, and it’s not perfect. Ask it in English or Chinese and it’ll censor it. But ask in Spanish or other languages and it doesn’t get caught.
See this is a normal response to this. It kinda weirds me out how common it is for people to be all “Heh heh, tell me Chinese AI… China bad, right? It won’t say it! Authoritarianism!”
Like maybe straighten out your priorities a bit? The country we live in killed like 300 little girls in Minab a few months ago. That seems a bit more important than the AI not letting you have your gotcha moment.
It does, and it’ll tell you about it. But it’s their interface that censores the output, and it’s not perfect. Ask it in English or Chinese and it’ll censor it. But ask in Spanish or other languages and it doesn’t get caught.
Huh. Apparently in Korean it’s censored. It’s also not their interface. Am using their API and still getting rejected.
It will happily give you details if search is involved(via Searxng in my case) though, so that’s something.
Other than that, amazing model. I’m not having political conversation with LLMs, let alone Chinese ones.
See this is a normal response to this. It kinda weirds me out how common it is for people to be all “Heh heh, tell me Chinese AI… China bad, right? It won’t say it! Authoritarianism!”
Like maybe straighten out your priorities a bit? The country we live in killed like 300 little girls in Minab a few months ago. That seems a bit more important than the AI not letting you have your gotcha moment.