The vast majority of where the compute gets spent on in training is no longer just like read all the documents of the company or learn from inputs and outputs and SFT like most of the compute is now going towards RL. where the model will attempt the problem many times and then get a score on one of these rubrics. And RL in the vast majority of cases requires subject matter experts that are able to create these rubrics and tasks to evaluate and train models.
★ In the digest▶ 48:36