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 concinds on Friday December 19, 2025 @09:13AM (#46326053)
And it's a 4B model. I worry that nontechnical users will dramatically overestimate its accuracy and underestimate hallucinations, which makes me wonder how it could really be useful for academic research.
[ Parent | on HN ]
Re:Trained LLMs exclusively on pre-1913 texts by DGoettlich on Friday December 19, 2025 @04:53PM (#46331395)
valid point. its more of a stepping stone towards larger models. we're figuring out what the best way to do this is before scaling up.
[ Parent | on HN ]
Re:Trained LLMs exclusively on pre-1913 texts by spicyusername on Sunday December 21, 2025 @11:04PM (#46351201)
If there's very little text before the internet, what would scaling up look like?
[ Parent | on HN ]