Yun-Ta Tsai
@yunta_tsai · 12 mars 2026
I am curious how many scaling laws are based on the ability to memorize in fixed epochs instead of grokking (generalization).
If grokking truly happened, you could use fewer parameters to achieve the same thing, but that requires a model to truly understand the problem in depth
Elon Musk
@elonmusk
🎯
15:10 · 12 mars 2026 · 72,8 k vues
95
48
908