Report

A formula could flag undesirable AI outputs before they happen

Live Science says the formula tracks an AI's internal “compass needle” to flag undesirable outputs before they happen.

1 Source, 20d ago, first seen 20d ago

TLDR

Live Science reports that physicists say simple math can predict when AI is about to “go rogue.” It describes a formula that tracks an AI's internal “compass needle” to flag undesirable outputs before they happen.

Today's Rank

—

Not ranked yet

Combined views

1.3K

1 Source, first seen 20d ago