Previous high level projects have tried to define concepts like “trustworthiness” (or the closely related “truthful”) and motivated the AI to follow them. Here we will try the opposite: define “betrayal”, and motivate the AIs to avoid it.
Why do you think the betrayal approach is more tractable or useful? It’s not clear from the post.
Why do you think the betrayal approach is more tractable or useful? It’s not clear from the post.