LESSWRONG
LW

All of manuherran's Comments + Replies

Law of No Evidence
manuherran10

I have my own ranking of types of evidence, from most to least scientific, where "scientific" means "good", starting with induction (repeated observations, replicated experiments), logical deductions, interpolation, authority... and ending with popularity, intuition, superstition, dreams, faith... So, as long as some of these "evidences" can be found, instead of saying "there is no evidence" I say "there is little evidence" and avoid misconnotation while being precise with the denotation. No irony

Reply
MIRI announces new "Death With Dignity" strategy
manuherran10

Many thanks, Vaniver. Now I get it, and I really like it because "suffering" rings badly whereas s-risks seems like a more manageable concept to work with.

Reply
MIRI announces new "Death With Dignity" strategy
manuherran30

I agree that the problem of the alignment of human values with artificial intelligence values is in practice unsolvable. Except in a very particular case, that is when the artificial intelligence and the human are the same thing. That is, to stop developing AI on dry hardware and just develop it in wet brains, for what Elon Musk's Neuralink approach could be a step in the right direction.

Reply
8Rob Bensinger
Intelligence amplification (broadly construed) seems useful to me, because it might make smarter humans who can more efficiently solve the alignment problem. It doesn't obviate the need for a solution, because you'll still have people advancing AI in a world full of human intelligence amplification techniques, and the AI will still surpass human intelligence. (Fundamentally, because 'AI' is a much less constrained part of the solution space than 'enhanced human'; in searching for smarter 'AI', any design is on the table, whereas enhanced humans are exploring a very specific part of the tree of mind designs, and need to be perpetually cautious about any radical changes that might cause bad value drift.) But when I think of 'intelligence amplification', I'm mostly thinking of tweaking genes or biochemistry a bit to raise IQ. 'Develop AI inside human brains' seems far less promising to me, especially if people at Neuralink think that having the AI inside of you somehow ensures that it's aligned with the rest of you. For a proof of concept that 'X is a part of me' doesn't magically transmit alignment, consider pathogens, or cancers.
MIRI announces new "Death With Dignity" strategy
manuherran30

Rafael, many thanks for your answer. I like how you conceptualize the matter but I fight for understand the very last part of your comment. If we have a multidimensional space where the axes represent (let's say, for clarity, positive and negative values of) how certain values are satisfied, how is it possible that most places in space are indifferent?

Reply
3Rafael Harth
I think the idea is that most areas in the space contain barely any conscious experience. If you have some rogue AI optimizing all matter for some criterion x, there's no reason why the resulting structures should be conscious. (To what extent the AI itself would be is actually talked about in this other comment thread.) But the objection is good, I think "how well values are satisfied" was not the right description of the axes. Probably more like, if one of your values is y, like physical temperature to choose something mundane, then y can take different values but only a tiny subset of those will be to your liking; most would mean you die immediately. (Note that I'm only trying to paraphrase, this is not my model.) If most values work like this, you get the above picture. See also Value is Fragile.
MIRI announces new "Death With Dignity" strategy
manuherran20

In other contexts (for example, when talking about euthanasia), "dying with dignity" is simply equivalent to dying without great suffering. This is, it seems to me, because dying has a high correlation with suffering intensely, and with enough suffering, identity (or rather, the illusion of identity) is destroyed, since with enough suffering, anyone would betray their ideas, their family, their country, their ethics, etc. trying anything to relieve it, even if it doesn't help. With enough suffering nothing remains recognizable, either physically or mentall... (read more)

Reply
MIRI announces new "Death With Dignity" strategy
manuherran-10

I'm surprised that in a post about dying with dignity and its comments, the word suffer / suffering is found zero times. Can someone explain it?

Reply
7Vaniver
Yeah, you've got to check for abbreviations; s-risk shows up 14 times (not including this comment), mostly here and below.
2Rafael Harth
As I understand it, Eliezer generally thinks suffering risks are unlikely, basically because the situation is best viewed as, there is this incredibly high dimensional space of possible futures (where the dimensions are how much certain values are satisfied), and the alignment problem consists of aiming at an incredibly small area in this space. The area of really bad futures may be much larger than the area of good futures, but it's still so tiny that even the <1% chance of solving alignment probably dominates the probability of landing in the space of bad futures by accident, if we don't know what we're doing. 99.999999...% of the space neither has positive nor negative value.
How uniform is the neocortex?
manuherran10

Its interesting to note that only mammals have neocortex [1] and birds for instance don't even have cortex [2]. But since birds have sensory perception, cognition and language, and some of them are also very smart [3] [4] [5], it seems that, either sensory perception, cognition, and language are processed also (even mainly) in other parts of the brain, either birds and other animal species have structures equivalent to the cortex and neocortex and we should stop saying that "only mammals have neocortex" [6].

In the meantime, it sounds less wr... (read more)

Reply
4Steven Byrnes
It's certainly true that you can't slice off a neocortex from the rest of the brain and expect it to work properly by itself. The neocortex is especially intimately connected to the thalamus and hippocampus, and so on. But I don't think bringing up birds is relevant. Birds don't have a neocortex, but I think they have other structures that have a similar microcircuitry and are doing similar calculations—see this paper. You can arrange neurons in different ways without dramatically altering the connectivity diagram (which determines the algorithm). The large-scale arrangement in the mammalian neocortex (six-layered structure) is different than the large-scale arrangement in the bird pallium, even if the two are evolved from the same origin and run essentially the same algorithm using the same types of neurons connected in the same way. (...as far as I know, but I haven't studied this topic beyond skimming that paper I linked above.) So why isn't it called "neocortex" in birds? I assume it's just because it looks different than the mammalian neocortex. I mean, the people who come up with terminology for naming brain regions, they're dissecting bird brains and describing how they look to the naked eye and under a microscope. They're not experts on neuron micro-circuitry. I wouldn't read too much into it. I don't know much about fish brains, but certainly different animals have different brains that do different things. Some absolutely lack "higher-order functions"—e.g. nemotodes. I am comfortable saying that the moral importance of animals is a function F(brain) ... but what is that function F? I don't know. I do agree that F is not going to be a checklist of gross anatomical features ("three points for a neocortex, one point for a basal ganglia..."), but rather it should refer to the information-processing that this brain is engaged in. I haven't personally heard anyone suggest that all mammals are all more morally important than all birds because mammals have a