Comment by geraneum
6 hours ago
> And incredibly good ways to assess & test it's weights
What weights are you referring to? How does [Claude?] code do that
6 hours ago
> And incredibly good ways to assess & test it's weights
What weights are you referring to? How does [Claude?] code do that
Look into RLVR (Reinforcement Learning with Verifiable Rewards). It happens during model post-training.