Hacker News Reader

It can't now. It will be able to in the future, when the translation actually becomes fluent for the user.

My point is that a succinct and correct translation for the pun does not exist in the target language.

My point is that the AI will have that info understood as part of "being a translator," and react accordingly. The phenomenon you're describing is a basic fact of linguistics. Many things don't have direct translations, but they are still translated by fluent speakers of both languages.

I am fluent in both languages and I can't succinctly translate it.

If I changed the meaning of the sentence, I could say, "can I study civil rights if I'm a lefty?"

If it were text, I might give you the translation I already gave yesterday and add a footnote explaining the pun.

Neither of these are ideal. One changes the meaning, the other is hard to understand.

Ok, so if a human, which is at the top of this ability to translate, choose this route.

What's the problem with an LLM-translatoin bot doing it? It would just do that, give a possible translation, and explain the issue.

Reply on news.ycombinator.com