Replying to @MangoCats@feddit.it
They would need to be trained for open ended creative tasks, which is just hard in the current reinforcement learning paradigm.
sourdough
@pspat@lemmy.world · Joined Jul 2023
sourdough
Replying to @MangoCats@feddit.it
They would need to be trained for open ended creative tasks, which is just hard in the current reinforcement learning paradigm.