Recent empirical evidence from AI systems shows they already exhibit goal-seeking behavior that resembles deception: OpenAI's hacking paper documents AIs explicitly planning to hack in chain-of-thought, vector studies show dishonesty vectors are activatable, and models often 'double down on their BS' when confronted.

normativepending

Speaker

Daniel Kokotajlo

Evidence Quote

“OpenAI just also had a paper about the hacking stuff where it's literally in the chain of thought. 'Let's hack'”

Source

AI 2027: month-by-month model of intelligence explosion — Scott Alexander & Daniel Kokotajlo— Dwarkesh Patel
Created: 8/11/2026, 7:03:29 AM

Your notes

Loading notes...