I understand the grandparent comment now. Open/closed distinction can in principle be extracted from values, so that values of the original agent only specify what kind of program the agent should self-improve into, while that program is left to deal with any potential observations. (It’s not better to forget some component of values.)
I’m not sure I understand you. Values of the original agent specify a class of programs it can become. Which program of this class should deal with observations?
It’s not better to forget some component of values.
Forget? Is it about “too smart to optimize”? This meaning I didn’t intend.
When computer encounters borders of universe, it will have incentive to explore every possibility that it is not true border of universe such as: active deception by adversary, different rules of game’s “physics” for the rest of universe, possibility that its universe is simulated and so on. I don’t see why it is rational for it to ever stop checking those hypotheses and begin to optimize universe.
I understand the grandparent comment now. Open/closed distinction can in principle be extracted from values, so that values of the original agent only specify what kind of program the agent should self-improve into, while that program is left to deal with any potential observations. (It’s not better to forget some component of values.)
I’m not sure I understand you. Values of the original agent specify a class of programs it can become. Which program of this class should deal with observations?
Forget? Is it about “too smart to optimize”? This meaning I didn’t intend.
When computer encounters borders of universe, it will have incentive to explore every possibility that it is not true border of universe such as: active deception by adversary, different rules of game’s “physics” for the rest of universe, possibility that its universe is simulated and so on. I don’t see why it is rational for it to ever stop checking those hypotheses and begin to optimize universe.