TimeCapsuleLLM: LLM trained only on data from 1800-1875

Re:TimeCapsuleLLM: LLM trained only on data from 1800-1875 by feisty0630 on Monday January 12, 2026 @11:58AM (#46591144)

Interesting that it reads a bit like it came from a Markov chain rather than an LLM. Perhaps limited training data?

[ Parent | on HN ]

Re:TimeCapsuleLLM: LLM trained only on data from 1800-1875 by kgeist on Monday January 12, 2026 @03:54PM (#46594171)

Early LLMs used to have this often. I think's that where the "repetition penalty" parameter comes from. I suspect output quality can be improved with better sampling parameters.

[ Parent | on HN ]

Re:TimeCapsuleLLM: LLM trained only on data from 1800-1875 by nomel on Tuesday January 13, 2026 @02:57AM (#46598352)

It is lacking all recorded text from the past 200 years. ;)

It would be interesting to know how much text was generated per century!

[ Parent | on HN ]