AI Dynamics

Global AI News Aggregator

Understanding Giant Tensors and Writing Goodhart-Proof Objectives

It doesn't need to be representing new physics, for us to have trouble understanding what the giant inscrutable tensors mean — or writing airtight Goodhart-proof objectives that operate over them, a much higher requirement of proficiency than current interpretability efforts.

→ View original post on X — @esyudkowsky,

Commentaires

Leave a Reply

Your email address will not be published. Required fields are marked *