Super goals implement basic strong AI’s desires.
There are many ~(1 … 100) super goals in strong AI.
Examples of possible basic desires:
Desire to read.
Desire to serve to operator.
Desire to serve to creator.
Desire to talk (chat).
Desire to earn money.
Desire to serve to the society.
Desire to avoid being turned off.
Super goal evaluates AI’s actions (is the specified action good or bad?). For more details see “How strong AI finds a way to satisfy super goal” below.
Super goals are programmed by creator.
Super goals cannot be created or modified by strong AI itself. That’s why super goal could be also named as a hardcoded goal.
Strong AI can create its own goals. I call such goals sub goals. There could be millions of sub goals in strong AI. There are usually just several super goals in strong AI.
The idea is simple: whatever satisfies super goal now -- most probably would satisfy the super goal in the future. In order to apply this idea, super goals must be programmed in a certain way. Every super goal itself must be able to distinguish what is good and what is bad.
Such approach makes super goal kind of “advanced sensor”. Actually not only “advanced sensor”, but also “desire enforcer”.
Here’s the example how it works:
Super goal’s objective: to be rich.
Super goal sensor implementation: check strong AI’s bank account for amount of money on it.
Super goal enforce mechanism: mark as “desirable” every concept (sub goal) which caused increase in the bank account balance. Mark as “not-desirable” every concept which caused decrease in the bank account balance.
Note: “mark concept as desirable/undesirable” doesn’t really work in “black & white” mode. Subtle super goal enforcement mechanism either increases or decreases desirability of every cause concept responsible for the change in the bank account balance.
Strong AI doesn’t schedule super goals directly. Instead strong AI schedules sub goals. To be more exact, super goals schedule sub goals by making them more/less desirable (see Reward distribution routine). The more desirable sub goal is – the higher probability is that this sub goal will be activated and executed.