Human takeover might be worse than AI takeover
In Tom Davidson’s words:
In expectation, future AI systems will better live up to human moral standards than a randomly selected human. Because:
- Humans fall far short of our moral standards.
- Current models are much more nice, patient, honest and selfless than humans.
- Humans are “rewarded” for immoral behaviour more than AIs will be.
- Humans evolved under conditions where selfishness and cruelty often paid high dividends, so evolution often “rewarded” such behaviour. And similarly, during lifetime learning humans often benefit from immoral behaviour.
- But we’ll craft the training data for AIs to avoid this, and can much more easily monitor their actions and even their thinking. Of course, this may be hard to do for superhuman AI, but bootstrapping might work.
https://forethoughtnewsletter.substack.com/p/human-takeover-might-be-worse-than