Comment by caconym_
3 days ago
> perhaps only in English
Wouldn't it work better to just write the thing in whatever language they can actually write in and then do a straightforward translation in a single pass?
> someone who is a lousy writer with deep domain knowledge going back and forth with the LLM to express some insight or communicate some information that the LLM would not produce on its own
This sounds reasonable on its face, but how often does it actually come up that somebody can't clearly express an idea in writing on their own but can somehow get an LLM to clearly express it by writing a series of prompts to the LLM?
And, if it does come up, why don't they just have that conversation with me, instead?
> Wouldn't it work better to just write the thing in whatever language they can actually write in and then do a straightforward translation in a single pass?
Nontrivial translation tools are AI(neural net)-based tools (although not necessary LLM). Whole transformer neural net architecture was originally designed for translation.
I don't have a problem with people using these tools to translate their writing into languages they aren't fluent/literate in. It's a completely different dynamic vs. having them write for you.
> And, if it does come up, why don't they just have that conversation with me, instead?
Because (the royal) you will be argumentative and shitty, and sour this person on their desire to communicate their knowledge at all.
This also seems mostly made up. In decades of using the internet, I can't remember ever seeing someone trying to share deep domain knowledge and getting mocked/shouted down just because they had a language gap or otherwise weren't a great communicator. In spaces where substantive discussion happens, people generally seem willing to engage in good faith and help close that particular gap.