Researchers are selecting favorable asymmetries in training environments and relying on models to generalize across task horizons.

“bug um through like you know tens of thousands of human and llms combined and like turn that into a very very neat environment which in a single lm could theoretically find within like you know a few million tokens so like there's all these asymmetries which we're cherry picking and like we're counting on like kind of this task horizon generalization um but i think yeah again it's just going to hit diminishing returns at some point like at some point it's diminishing returns and how hard it is to create those environments in the first place like”