@sbszine @Moss Honestly, in my opinion, any AI inference that is not able to use on-device or edge compute is not ready for mass usage by the public.

There’s multiple AI and AI-adjacent tools that I use that have no reliance on cloud compute for inference or decision making. For example, my insulin pump’s operation to keep my blood glucose near target. This runs on a device the size of a pager.

@sbszine @bedast @Moss as a rule of thumb, if it can run locally it's probably not too outrageously wasteful

@sbszine @bedast @Moss The issue has pretty much never been the energy cost of using the model, but the energy cost of training it. And there's also the ethics of the sourcing of the training data as well.