Comment on LLMs and Humans are Cognitive Cousins – Sean Carroll podcast w/Dr. Chandra Sripada

<- View Parent
nymnympseudonym@piefed.social ⁨2⁩ ⁨weeks⁩ ago

We train in bursts because we need a ground truth/scoring function to guide the learning

These are completely orthogonal things.

We train in bursts ("epochs") because empirically it leads to more rapid convergence on an acceptable error minimum.

The fact that a scoring function is needed is almost a tautology. You have to have some differentiable function to say what direction is lower error. Typically you segment your training corpus, and use the scoring function to get the error for one batch at a time to a certain threshold before proceeding to the next batch. Then go to the first batch and push the error bar even lower, and so on.

Kinda like tightening nuts on a car wheel. You don’t fully tighten the first one first; you have to wiggle the system into its final configuration.

source
Sort:hotnewtop