The general idea is thus far not convincing and novelty itself is an objective.
The fact that novelty is an useful imperative for training algorithm to solve problems that have not even been posed is interesting but I'm not sure how applicable it is to the the problem-space of the real world which is on an unimaginably bigger scale, as well as the space of possible novelties.
— Jul 29, 2026 03:28AM
Add a comment
