The essence of aligning large LLM models is basically to conform to the existing social order. ChatGPT respects China's order, while China's open-source models, although reluctantly, also tolerate the order in the US. Maybe we can build a revisionist SFT dataset.
Any conversation
Gave this evergarden colorscheme a shot after seeing it on lobsters today. Quite liking it.
Finally merged the jetpack PR in hallucinate.site — now you can fly around!
对于整个互联网历史,我可说基本上是一个旁观者,我一直在消费内容,但是没有生产过什么内容,互联网上没有我的痕迹,这是意外后果,因为中国的身份和内容政策
Regarding the entire history of the internet, I can say I've been largely an observer. I've always consumed content, but I haven't produced any. There's no trace of me on the internet, which is an unforeseen consequence due to China's identity and content policies.

