Y
Hacker News
new
|
ask
|
show
|
jobs
by
rahimnathwani
2 hours ago
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.
1 comments
bitexploder
1 hour ago
Oh… definitely not enough text. LLMs don’t work like that. Hmm.
link