Yeah, I stated it badly. Should have postulated smaller divergence. But all of those problems are poking at the intuition of me expecting to be the original, so, it might be not relevant / interesting to you to begin with. Or maybe at all.
Another version:
You enter the copying machine and exit in a grey room. The room of original flashes green when the person enters it and the room of the copy doesn’t. The room flashes with a green light.
Then you get (imperfectly, but you can’t tell introspectively, you need fMRI) memory wiped, you no longer remember that flash of light. You now exit the room. Which room do you anticipate exiting from?
The intent of this is like, what if there is a copy of you, and you get modified to match it, then wouldn’t you expect future observations from either your POV or copy POV 50:50?
It would have to wipe the memory of everything from that time onward, not just memory of the flash itself. I would also need to be immobilized from before the flash to after the memory alteration otherwise I would almost certainly notice a difference in position, and also tamper with my time sense so that I don’t realize that my memory only covers 5 seconds since entering the room instead of 10 seconds or something. But yeah, someone who can make a basically perfect copy of me can reasonably do all these sorts of things as well.
Rationality (e.g. Bayesian updates etc) as usually defined doesn’t work in the presence of mind alterations (e.g. implanting updates that are not rational), so that makes it rather difficult to develop criteria for what one “should” expect.
If you define it as “winning”, then expecting always to be the original when one has no evidence to the contrary always wins for the original. The scenario only asks about the original, and so this is a winning strategy.
If you define it as “winning”, then expecting always to be the original when one has no evidence to the contrary always wins for the original. The scenario only asks about the original, and so this is a winning strategy.
Well, I don’t think this a correct way to define winning here. I think paperclipper outlook is better for that job, like is there an agent with your goals in the world? If yes, good enough.
But humans are a lot more indexically wired, like I ate that cookie because I like cookies, not because that how I would have wanted this meat puppet to act in such circumstances, my reasoning didn’t go through such path.
And the difficulty is in reconciling this outlook with other, more from ground up considerations, which is exactly what I’m trying to do in this post, in baby steps, starting from something I have good concepts for.
Yeah, I stated it badly. Should have postulated smaller divergence. But all of those problems are poking at the intuition of me expecting to be the original, so, it might be not relevant / interesting to you to begin with. Or maybe at all.
Another version:
You enter the copying machine and exit in a grey room. The room of original flashes green when the person enters it and the room of the copy doesn’t. The room flashes with a green light.
Then you get (imperfectly, but you can’t tell introspectively, you need fMRI) memory wiped, you no longer remember that flash of light. You now exit the room. Which room do you anticipate exiting from?
The intent of this is like, what if there is a copy of you, and you get modified to match it, then wouldn’t you expect future observations from either your POV or copy POV 50:50?
It would have to wipe the memory of everything from that time onward, not just memory of the flash itself. I would also need to be immobilized from before the flash to after the memory alteration otherwise I would almost certainly notice a difference in position, and also tamper with my time sense so that I don’t realize that my memory only covers 5 seconds since entering the room instead of 10 seconds or something. But yeah, someone who can make a basically perfect copy of me can reasonably do all these sorts of things as well.
Rationality (e.g. Bayesian updates etc) as usually defined doesn’t work in the presence of mind alterations (e.g. implanting updates that are not rational), so that makes it rather difficult to develop criteria for what one “should” expect.
If you define it as “winning”, then expecting always to be the original when one has no evidence to the contrary always wins for the original. The scenario only asks about the original, and so this is a winning strategy.
Well, I don’t think this a correct way to define winning here. I think paperclipper outlook is better for that job, like is there an agent with your goals in the world? If yes, good enough.
But humans are a lot more indexically wired, like I ate that cookie because I like cookies, not because that how I would have wanted this meat puppet to act in such circumstances, my reasoning didn’t go through such path.
And the difficulty is in reconciling this outlook with other, more from ground up considerations, which is exactly what I’m trying to do in this post, in baby steps, starting from something I have good concepts for.