If we can predict to how an AI would modify itself, why don’t we just write an already modified AI?
Because the point of a self-modifying AI is that it will be able to self-modify in situations we don’t anticipate. Being able to predict its self-modification in principle is useful precisely because we can’t hard-code every special case.
If we can predict to how an AI would modify itself, why don’t we just write an already modified AI?
Because the point of a self-modifying AI is that it will be able to self-modify in situations we don’t anticipate. Being able to predict its self-modification in principle is useful precisely because we can’t hard-code every special case.