it probably doesnt know what language each set of words is referencing. i doubt ... | Hacker News

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

8note 35 days ago | parent | context | favorite | on: Apertus – Open Foundation Model for Sovereign AI

it probably doesnt know what language each set of words is referencing.

i doubt they are including a lot of training data labeled with the language.

"how to say X in language Y" is a different task from saying X in language Y

einpoklum 35 days ago [–]

Actually, it isn't all that different. There are only two words separating "how to say X in language Y" from "say X in language Y". And this "vulgar" metric is actually quite relevant for an LLM, which answers based on conversational context.

Consider applying for YC's Fall 2026 batch! Applications are open till July 27.
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact