Merve Noyan says that while watching PewDiePie's post-training with environments video, she recognized a common problem. When generating environment tasks herself, she finds the task count is small, and regenerating leads to an endless cycle of trying to improve, so she says training needs a deadline.
when watching pewdiepie's post-training with envs video I resonated so bad
often times you generate env tasks yourself → notice how little number of tasks you have → generate again and it's an endless loop of trying to improve you have to put a deadline to your training
Source: merve · x.comPublished
