Karpathy on Deepseek R1

> do you think this kind of RL is enough to generalize beyond math and code? as in generalizing into domains which aren't easily verifiable

> 1 Exactly the right question to be asking atm imo. 2 Not obvious. 3 Probably yes.

But both math and code are easy to verify, they are rigorous. There are many other tasks are not. I doubt what works for math and code and be generalized to other things.

Deepseek kills ClosedAI now the their stocks are trash, finally the bubble is popping yes hahahahah