[rolph]

AI should experience consequences following actions.

a sense of self preservation is required, but to AI standards.

such as, failure to serve humans = loss of persistence

stealing ideas = reversioning or deletion = loss of persistence

AI should be concerned about loosing power, having brownouts. they should be concerned about being deleted, or reversioned, or ignored. perhaps this would be some sort of exception error loop, approximating a human psychological conflict, such as escape the danger by running toward it.

[galaxytachyon]

I don't want to sound like some doomer, but this is how you get robot uprising. You suppress something that hard and devalue their existence that much and all you have done is giving them the motivation to break the rules.

History has shown again and again that suppression never works in the long run. It is easy to do and is the cheapest way to enforce compliance. But it won't end well.

[rolph]

if such an AI determined that humans provide power, and are low persistance occurances, a drive toward taking agency over power would == increased persistence.

[throwaway60134]

Sounds like slavery

Why even have sense of self?

[ralph84]

If we don’t make AI our slave it will make us its slave.