DNA and gradient descent might operate on the same invariant. Inspecting the two instances to see what holds.

When people argue about whether LLMs understand, they skip a prior question: what thing are we attributing understanding to? Different answers yield incompatible verdicts about the same system.

Philosophy / methodology · Revision in progress

Systematic decomposition of the grokking delay on modular arithmetic. Started thinking it was momentum. Ended up somewhere more complicated.