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.
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.