100

the current tech is really unsustainable with its cost to usefulness ratio

needs a lot of optimisation to make it work and less “brute forcing” the models

i mean if you could in the future make an ai play long games from start to finish, it would be very useful to test games with thousands running at once

one problem ive seen with these game ai projects is that you have to constantly tweak it and reset training because it eventually ends up in a loop of bad habits and doesnt progress

so is it even possible to complete such a project with this kind of approach as it seems to take too much time to get anywhere without insane server farms?