Scaling laws project that a model with more parameters trained for longer on more data yields predictably better performance, and that generally you want to scale these factors commensurately. More of the compute budget is being spent on RLVR [0] for which we also fit scaling laws
Researchers tweak data mix, reward shape, model architecture, etc etc, breakthroughs which reduce the cost to train a just-as-smart model. But this increases the returns to scale, which further incentivizes bigger models trained for longer on more data
Scaling laws project that a model with more parameters trained for longer on more data yields predictably better performance, and that generally you want to scale these factors commensurately. More of the compute budget is being spent on RLVR [0] for which we also fit scaling laws
Researchers tweak data mix, reward shape, model architecture, etc etc, breakthroughs which reduce the cost to train a just-as-smart model. But this increases the returns to scale, which further incentivizes bigger models trained for longer on more data
[0] "...to run reinforcement learning training...at pretraining scale." https://x.ai/news/grok-4?_bhlid=b9339d7816a05adeb52bae7050cc...
thanks, what you just taught means diamonds for me
Lots of RLHF - reinforcement learning from human feedback.
Also: "distillation" - seeding or running training sessions on the output of frontier models.
many things to push it forward, like:more data, more post trainning...
compute and improvements in pretraning and RL