LLMs are intrinsically unsafe because they cannot close the gap between training error and test error—there is always a new prompt where they will do stupid things, unlike objective-driven world model systems which can enforce safety constraints by construction through cost functions.
causalpending
Speaker
Yann LeCunEvidence Quote
“LLMs are intrinsically unsafe...There's always going to be a prompt where the system is going to do really stupid things”
Created: 8/12/2026, 6:06:44 PM
Your notes
Loading notes...