RLVR might be disproportionately bad at science
the verification loop for theories can be on the order of decades and centuries, and even then we know today as the better theory can often actually make worse predictions
点赞
收藏
点踩
分享评论
?
参与讨论
the verification loop for theories can be on the order of decades and centuries, and even then we know today as the better theory can often actually make worse predictions