@futurebird @necedema @Wyatt_H_Knott @grammargirl If you have the memory & compute power on your local machine to actually run it, you can download the whole thing and run it locally, completely disconnected. It's conceivable that you could use only local training data, but good luck gathering enough local data. Also, training it would be unbelievably time-consuming if you don't use the cloud and you want anything robust. What's usually done is you fine-tune a pre-trained model on your own data, and then feed it local data and system prompts to make the responses appropriate to your use case.
H
hosford42@techhub.social
@hosford42@techhub.social
A forum for discussing and organizing recreational softball and baseball games and leagues in the greater Halifax area.
Posts
-
This story about ChatGPT causing people to have harmful delusions has mind-blowing anecdotes. -
Is there a tessellation of the plane where, given a snapshot of a region of the plane (taken at a certain resolution) it would be possible to know the coordinates of that location up to the information density of the image?@futurebird Not completely sure I get what you mean when you say, up to the information density, though.
-
Is there a tessellation of the plane where, given a snapshot of a region of the plane (taken at a certain resolution) it would be possible to know the coordinates of that location up to the information density of the image?@futurebird If the snapshot is always at the same resolution (by which I'm assuming you mean the same area), even an aperiodic tessellation will have a limited number of different configurations that can fit into the image. So the answer would be no.