from Hacker News

Karpathy on Deepseek R1

by sonabinu on 1/27/25, 7:13 PM with 3 comments

  • by billconan on 1/27/25, 7:32 PM

    > 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.

  • by johnneville on 1/27/25, 7:18 PM

  • by mainecoder on 1/27/25, 8:37 PM

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