
Yong Zheng-Xin (Yong)
@yong_zhengxin
π― reasoning and alignment
π making LLMs safe and helpful for everyone
π phd @BrownCSDept + research @AIatMeta @Cohere_Labs
ID: 955679485273153537
https://yongzx.github.io/ 23-01-2018 05:51:59
553 Tweet
1,1K Followers
1,1K Following

π§΅ Multilingual safety training/eval is now standard practice, but a critical question remains: Is multilingual safety actually solved? Our new survey with Cohere Labs answers this and dives deep into: - Language gap in safety research - Future priority areas Thread π
