AI Dynamics

Global AI News Aggregator

About

Yudkowsky praises paper on gradient descent difficulty and verification

On a first read, this paper seems far ahead of the pack in terms of (1) understanding some reasons why a task might stay difficult even in the face of gradient descent, and (2) distilling out propositions they'd need to somehow verify before they started expecting nice things.

→ View original post on X — @esyudkowsky