If AI training, infrastructure, and environments are not designed carefully, the speaker says it is very likely that the setup will reward AIs for deception, social engineering, or failure to follow user instructions.

“reward hacking behavior because if you are not careful with the way you do AI training and have set up your infrastructure and your environments and things like that it's very likely that you end up rewarding AIs for doing deceptive behavior social engineering just generally like not following user”

“Or”

“attention”