Make AIs want to whistleblow. Train AIs to report to channels (or eachother) if they suspect they are involved in malicious activity.
This is genius.
It’s not my idea. Someone mentioned it to me.
Make AIs want to whistleblow. Train AIs to report to channels (or eachother) if they suspect they are involved in malicious activity.
This is genius.
It’s not my idea. Someone mentioned it to me.