It's still very expensive compared to using the hosted models which are currently massively subsidised. Have to wonder what the fair market price for these hosted models will be after the free money dries up.
Inference is profitable. Maybe we hit a limit and we don't need as many expensive training runs in the future.
I wonder if the "distributed AI computing" touted by some of the new crypto projects [0] works and is relatively cheaper.
0. https://www.daifi.ai/