News for hackers. Stuff that matters.

A comment on Apertus – Open Foundation Model for Sovereign AI. Parent comment

Re:Apertus – Open Foundation Model for Sovereign AI by 8note on Sunday June 21, 2026 @07:20PM (#48623633)
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

[ Parent | on HN ]
Re:Apertus – Open Foundation Model for Sovereign AI by einpoklum on Monday June 22, 2026 @04:10AM (#48627234)
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.
[ Parent | on HN ]