Vacuously true. The actual question is: how much do you need to sample? My guess is it’s too much, but we’d see the base model scaling better than the RL’d model just like in this paper.
Fortunately, DeepSeek’s Mathv2 just dropped which is an open-source model that gets IMO gold. We can do the experiment: is it similarly not improving with sampling compared to its own base model? My guess is yes, the same will happen.
Vacuously true. The actual question is: how much do you need to sample? My guess is it’s too much, but we’d see the base model scaling better than the RL’d model just like in this paper.
Fortunately, DeepSeek’s Mathv2 just dropped which is an open-source model that gets IMO gold. We can do the experiment: is it similarly not improving with sampling compared to its own base model? My guess is yes, the same will happen.