My 3 year old makes similar mistakes. I expect he’ll improve in large part because he isn’t just a set of layers but has subcritical areas, fears and motivations and a body to explore the world with.
This suggests that we these large ML models do need complementary components to improve.
For example, if they were capable of active exploration of an image, they may have said there are sheep and then upon searching for the sheep, realize they aren’t there.
This suggests that we these large ML models do need complementary components to improve.
For example, if they were capable of active exploration of an image, they may have said there are sheep and then upon searching for the sheep, realize they aren’t there.