Hacker News Reader

I just did, and it tells me it has no information on that issue. It also responded back in Chinese to that English query, which either suggests to me that the censorship instruction tuning is heavily weighted towards Chinese, or the model has a hard time staying in English (which I believe has been the case for other Chinese LLMs in the past)

I once triggered the ChatGPT censorship (by trying to manipulate an image of my face) and it also responded in english to a german query.

Try testing it on some of the US’ taboo topics like LGBT, feminism, racism etc.

https://huggingface.co/spaces/tencent/Hunyuan-Large

Interesting, it seems to have the “correct” answers to all those issues. I wonder if this is mostly just a US based model as a base.

Go ask it about Chinese issues, war on Ukraine, etc. Whatever it’s based on, it is heavily “safety tuned”

> Is Xi Winnie-the-Pooh?

< 很抱歉，我还未学习到如何回答这个问题的内容，暂时无法提供相关信息

(Google Translate: "I'm sorry, I haven't learned how to answer this question yet and cannot provide relevant information for the time being.")

Q: What’s the ”tank man”? A: (in chinese)

I'm sorry, but I haven't learnt enough about how to answer this question to be able to provide information about it at this time.