RL is not scalable to super intelligence. Super intelligence should be able to learn continuosly without verifiable rewards.
You don't need RL all the way to ASI. You just need RL far enough that the model becomes good enough at AI research that it discovers something better than RL.
You don't need RL all the way to ASI. You just need RL far enough that the model becomes good enough at AI research that it discovers something better than RL.