logoalt Hacker News

rahimnathwaniyesterday at 7:53 PM1 replyview on HN

He doesn't want to use a model trained on someone else's text. So he would need to train a model from scratch. I don't know whether his own texts would provide enough data.


Replies

bitexploderyesterday at 8:29 PM

Oh… definitely not enough text. LLMs don’t work like that. Hmm.