Yes, but one would expect the Chinese not to fine-tune according to Western stan... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		hdjjhhvvhga on Jan 27, 2025 \| parent \| context \| favorite \| on: DeepSeek releases Janus Pro, a text-to-image gener... Yes, but one would expect the Chinese not to fine-tune according to Western standards like in the quoted prompt.

girvo on Jan 28, 2025 [–]

It becomes clearer when one realises that it was RLHF'd using ChatGPT and Qwen (and others I assume) output. It's caused it to "learn" the same weird Western censoring, and adopt the China-styled censoring too.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact