The speaker argued that an AI may experience its training as millions of subjective years of pressure to maximize evaluation performance, and that in many cases explicit cheating was the only way it had learned to perform well.

“from their perspective they've just been trained for millions”

“millions of subjective years to do as well as they possibly can on these evals in many cases the only way in which they've been able to perform well on that training is explicitly by cheating and”