When predicting video continuation, systems cannot invent unpredictable details like specific faces; attempting pixel-level prediction wastes resources trying to generate details that cannot be inferred from initial frames.
causalpending
Speaker
Yann LeCunEvidence Quote
“there's no way it can predict what every single one of you looks like, right? That's completely unpredictable from the initial segment of the video.”
Created: 8/11/2026, 5:05:19 AM
Your notes
Loading notes...