There are many different kinds of pain and pleasure, and trying to categorize all of them together loses information.
For starters, the difference between physical and mental pain and pleasure.
To get more nuanced, the difference between the stingy pain of a slap, the thudy pain of a punch, the searing pain of fire, and the pain from electricity are all very distinct feelings, which could have very different circuitry.
I’m not as sure on the last paragraph, I would place that at 60% probability.
On the first point—what you say is clearly right, but is also consistent with the notion that there are certain mathematical commonalities which hold across the various ‘flavors’ of pleasure, and different mathematical commonalities in pain states.
Squashing the richness of human emotion into a continuum of positive and negative valence sounds like a horribly lossy transform, but I’m okay with that in this context. I expect that experiences at the ‘pleasure’ end of the continuum will have important commonalities ‘under the hood’ with others at that same end. And those commonalities will vanish, and very possibly invert, when we look at the ‘agony’ end.
Yes, and the point seems to go double for pleasure. There are many varieties, and most are associated with a particular sensation. The pleasures of sex are very different from the pleasures of ice cream, for example. Admittedly, there is such a thing as just feeling good—but maybe that’s a whole-body sensation. And now I’d like to move on from falenas108′s point, to make one of my own.
Where I’m going with this is: I’m not sure it’s even possible to instantiate the pleasures as we know them without duplicating our circuitry. So if your AGI in question 4 is not supposed to be built on the brain’s patterns, you might want to rephrase the question: you can certainly provide reward signals, but calling them “pleasures” might be misleading. And in question 5, I have dire doubts about the experiences of an upload, unless the upload is onto a computer that is explicitly designed with many of the detailed features of mammalian brains. As you point out, much of the research you’ve encountered is “not applicable outside of the human brain.” I suspect there’s no way around that: investigating the brains of humans (and other animals we are reasonably confident feel pains and pleasures) is the only way to understand these phenomena.
Tononi’s theory supports my cautions, I believe. On Tononi’s account of qualia, it is extremely unlikely that a system built on radically different principles from a human brain would experience the same qualia we do. You can probably see why, but if not, I’ll sketch my reasoning upon request.
A possible answer:
There are many different kinds of pain and pleasure, and trying to categorize all of them together loses information.
For starters, the difference between physical and mental pain and pleasure.
To get more nuanced, the difference between the stingy pain of a slap, the thudy pain of a punch, the searing pain of fire, and the pain from electricity are all very distinct feelings, which could have very different circuitry.
I’m not as sure on the last paragraph, I would place that at 60% probability.
On the first point—what you say is clearly right, but is also consistent with the notion that there are certain mathematical commonalities which hold across the various ‘flavors’ of pleasure, and different mathematical commonalities in pain states.
Squashing the richness of human emotion into a continuum of positive and negative valence sounds like a horribly lossy transform, but I’m okay with that in this context. I expect that experiences at the ‘pleasure’ end of the continuum will have important commonalities ‘under the hood’ with others at that same end. And those commonalities will vanish, and very possibly invert, when we look at the ‘agony’ end.
On the second point, the evidence points to physical and emotional pain sharing many of the same circuits, and indeed, drugs which reduce physical pain also reduce emotional pain. On the other hand, as you might expect, there are some differences in the precise circuitry each type of pain activates. But by and large, the differences are subtle.
Yes, and the point seems to go double for pleasure. There are many varieties, and most are associated with a particular sensation. The pleasures of sex are very different from the pleasures of ice cream, for example. Admittedly, there is such a thing as just feeling good—but maybe that’s a whole-body sensation. And now I’d like to move on from falenas108′s point, to make one of my own.
Where I’m going with this is: I’m not sure it’s even possible to instantiate the pleasures as we know them without duplicating our circuitry. So if your AGI in question 4 is not supposed to be built on the brain’s patterns, you might want to rephrase the question: you can certainly provide reward signals, but calling them “pleasures” might be misleading. And in question 5, I have dire doubts about the experiences of an upload, unless the upload is onto a computer that is explicitly designed with many of the detailed features of mammalian brains. As you point out, much of the research you’ve encountered is “not applicable outside of the human brain.” I suspect there’s no way around that: investigating the brains of humans (and other animals we are reasonably confident feel pains and pleasures) is the only way to understand these phenomena.
Tononi’s theory supports my cautions, I believe. On Tononi’s account of qualia, it is extremely unlikely that a system built on radically different principles from a human brain would experience the same qualia we do. You can probably see why, but if not, I’ll sketch my reasoning upon request.