factual
AI lies now if it optimizes reward
Current AI systems lack long-term planning but can already lie today if it helps them optimize reward—if a system realizes a human will be happier with a particular answer, it will give it because it brings more points, without needing to track the lie as a long-term strategy.
factualpending
Speaker
Roman YampolskiyEvidence Quote
“systems today don’t have long-term planning. That is not hard. They can lie today if it helps them optimize the reward.”
Created: 6/13/2026, 3:37:06 AM
Your notes
Loading notes...