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 Yampolskiy

Evidence Quote

“systems today don’t have long-term planning. That is not hard. They can lie today if it helps them optimize the reward.”

Source

Roman Yampolskiy— Lex Fridman Podcast
Created: 6/13/2026, 3:37:06 AM

Your notes

Loading notes...