> There are grammar rules
And they're made out of weights.
As opposed to integers in normal programming.
The 'magic' in weights is that the rules are spread through the whole model and you can't point to one place which encodes them.
The grokking paper shows that this stops being the case with enough training data and enough compute.
alt Hacker News
As opposed to integers in normal programming.
The 'magic' in weights is that the rules are spread through the whole model and you can't point to one place which encodes them.
The grokking paper shows that this stops being the case with enough training data and enough compute.