Fixing GRPO's credit assignment problem without evaluating every step
arxiv.org
1 thread
How do frontier labs choose which ideas to include in a training run? It seems that there are too many to choose from
I think maybe they have enough compute to try out all the promising directions at a smaller scale first and then port them to larger run
They also have incredibly smart people that can understand which improvements and directions are even worth pursuing for, I think these people are being paid in millions
Why do you think they are buying compute and accelerating to RSI? It’s for this.