Coding interview problems are currently used for substantial RLVR training and are cheap and easy to verify algorithmically, according to the speaker.

“like these like, you know, these like, you know, coding interview problems,”

“which they're currently doing lots of RLVR on,”

“That's like very, very cheaply, very easily algorithmically verifiable. And then there's these sort of like real world things which have sort of more expensive and longer horizon.”