News for hackers. Stuff that matters.

A comment on Trained LLMs exclusively on pre-1913 texts. Parent comment

Re:Trained LLMs exclusively on pre-1913 texts by libraryofbabel on Thursday December 18, 2025 @07:48PM (#46320948)
Good point, informal letters might actually be a better source - AI chat is (usually) a written rather than spoken interaction after all! And we do have a lot transcribed collections of letters to train on, although they’re mostly from people who were famous or became famous, which certainly introduces some bias.
[ Parent | on HN ]
Re:Trained LLMs exclusively on pre-1913 texts by pigpop on Friday December 19, 2025 @03:31PM (#46330547)
The question then would be whether to train it to respond to short prompts with longer correspondence style "letters" or to leave it up to the user to write a proper letter as a prompt. Now that would be amusing

Dear Hon. Historical LLM

I hope this letter finds you well. It is with no small urgency that I write to you seeking assistance, believing such an erudite and learned fellow as yourself should be the best one to furnish me with an answer to such a vexing question as this which I now pose to you. Pray tell, what is the capital of France?

[ Parent | on HN ]