Knut Sondre Sæbø
@knut-sondre-saebo·Joined Sep 2024·Ideas
#4847·Tyler MillsOP, 27 days agoThis is a good point, related to Dirk's #4813. As far as the bounty goes, I think my response in #4823 applies here as well, however. To refine it:
Recognizing, criticizing, and being able to understand explanations could all be requisites for tractably synthesizing any possible explanation. The bounty regards whether the tractability requirement can be done without.It seems like a mind being able to create, recognize, understand and differentiate (etc.) good explanations are necessary but not sufficient criteria for personhood; if that process is intractable, then beyond a certain amount of current knowledge (considering that as the input to the process), the person effectively cannot continue with it... so that compromises the universality.
They must be able to create, recognize and understand any given explanation, and maintain that ability as their knowledge grows, ad infinitum...
By Tractible, do you mean "efficient relative to fixed task"?
#4260·Dennis HackethalOP, 3 months agoA concept or idea with no experiential grounding is meaningless.
Maybe, but that’s different from confusing a parochial factor for a fundamental one.
Could you elaborare? Is the point that physical experience, metaphors and other things that ground ideas don’t constrain the reach of ideas at all or only partially?
"Understanding" isn't just another way of saying "can explain." An RNG could by chance generate a good explanation, but it doesn't understand it, and therefore can't distinguish it from garbage. Understanding involves recognizing that something is a good explanation. It is conscious understanding that makes conjecture and criticism possible. Without it, you have no criticism, only random selection. What do you think of the suggestion that what's lacking from the explanatory universality definition, is an intelligent selection mechanism. A random program can generate any explanation given infinite time, but it will never select which explanation is good.
"Understanding" isn't just another way of saying "can explain.". Explaining follows from understanding, but isn't synonymous. An RNG could by chance generate a good explanation, but it doesn't understand it, and therefore can't distinguish it from garbage. Understanding involves recognizing that something is a good explanation. It is conscious understanding that makes conjecture and criticism possible. Without it, you have no criticism, only random selection. What do you think of the suggestion that what's lacking from the explanatory universality definition, is an intelligent selection mechanism. A random program can generate any explanation given infinite time, but it will never select which explanation is good.
#4808·Tyler MillsOP, about 1 month agoMaybe... but "understanding" is too vague, I think. Doesn't understanding mean: can explain? But then this is just "can create any explanation" again. I think the core question is why a random program generator isn't a person, coming from Deutsch's definition of a person as a program that has explanatory universality -- can create any explanation (my thought here is that this definition isn't good enough on its own, given the random generator point).
"Understanding" isn't just another way of saying "can explain." An RNG could by chance generate a good explanation, but it doesn't understand it, and therefore can't distinguish it from garbage. Understanding involves recognizing that something is a good explanation. It is conscious understanding that makes conjecture and criticism possible. Without it, you have no criticism, only random selection. What do you think of the suggestion that what's lacking from the explanatory universality definition, is an intelligent selection mechanism. A random program can generate any explanation given infinite time, but it will never select which explanation is good.
Does not understand explanatory knowledge seems like a better criterion
Understanding explanatory knowledge seems like a better criterion
#4781·Dirk Meulenbelt, about 1 month agoA random number generator does not create explanatory knowledge.
Does not understand explanatory knowledge seems like a better criterion
Those are still spatial metaphors. I'm not saying we can't extend our ideas through imagination, creativity etc. Only that the metaphors and concepts we use/have meaning for us, are constrained by the perspectives we can take as humans. When we try to explain how bats perceive through echolocation, we fall back on visual simulations, because sight is the only perceptual world we know.
Those are still spatial metaphors. I'm not saying we can't extend our ideas through imagination, creativity etc. Only that the metaphors and concepts we use/have meaning for us, are constrained by the perspectives we can take as humans. When we try to explain how bats perceive through echolocation, we fall back on visual simulations, because sight is the only perceptual world we know. Ideas have a similar limitation
Those are just spacial metaphors though. I'm not saying we can't extend our ideas through imagination, creativity etc. Only that the metaphors and concepts we use/have meaning for us, are constrained by the perspectives we can take as humans. Can you think of any ideas that isn't rooted in an experiential perspective?
Those are still spatial metaphors. I'm not saying we can't extend our ideas through imagination, creativity etc. Only that the metaphors and concepts we use/have meaning for us, are constrained by the perspectives we can take as humans. When we try to explain how bats perceive through echolocation, we fall back on visual simulations, because sight is the only perceptual world we know.
#3769·Dennis HackethalOP, 4 months agoHumans use flight-related words even though we can’t fly. From ChatGPT:
- Elevated (thinking, mood, language)
- High-level (ideas, overview)
- Soar (ambitions, prices, imagination)
- Take off (projects, careers)
- Grounded (arguments, people)
- Up in the air (uncertain)
- Overview (“over-see” from above)
- Perspective (originally spatial vantage point)
- Lofty (ideals, goals)
- Aboveboard (open, visible)
- Rise / fall (status, power, ideas)
- Sky-high (expectations, costs)
- Aerial view (conceptual overview)
- Head in the clouds (impractical thinking)
Those are just spacial metaphors though. I'm not saying we can't extend our ideas through imagination, creativity etc. Only that the metaphors and concepts we use/have meaning for us, are constrained by the perspectives we can take as humans. Can you think of any ideas that isn't rooted in an experiential perspective?
#3768·Dennis HackethalOP, 4 months agoI think that depends on the "embodiment" of the AGI; that is, what it's like to be that AGI and how its normal world appears.
Yeah maybe but again (#3693), those are parochial factors, starting points. Ideas are more important. AGI could just switch bodies rapidly anyway.
We explain the world by postulating invisible things, but we can only understand those abstractions through concrete metaphors rooted in our physical experience. A concept or idea with no experiential grounding is meaningless.
#3705·Dennis HackethalOP, 4 months agoIsn't every theory infinitely underspecified ?
This stance is presumably a version of the epistemological cynicism I identify here.
Maybe scepticism is fallibilism taken too far?
I think that depends on the "embodiment" of the AGI; that is, what it's like to be that AGI and how its normal world appears. A bat (if it were a person) would probably prefer different metaphors than a human would. Humans are very visual, which makes spatial features very salient to us. Metaphors work because they leverage already-salient aspects of experience to illuminate other things. So to train an AGI, I would think it's more useful for that AGI to leverage the salient aspects that are pre-given.
I think that depends on the "embodiment" of the AGI; that is, what it's like to be that AGI and how its normal world appears. A bat (if it were a person) would probably prefer different metaphors than a human would. Humans are very visual, which makes spatial features very salient to us. Metaphors work because they leverage already-salient aspects of experience to illuminate other things. So to train an AGI, I would think it's more useful for that AGI to leverage the salient aspects that are pre-given.
#3752·Knut Sondre Sæbø revised 4 months agoI think that depends on the "embodiment" of the AGI; that is, what it's like to be that AGI and how its normal world appears. A bat (if it were a person) would probably prefer different metaphors than a human would. Humans are very visual, which makes spatial features very salient to us. Metaphors work because they leverage already-salient aspects of experience to illuminate other things. So to train an AGI, I would think it's more useful for that AGI to leverage the salient aspects that are pre-given.
If this is the case, it would make sense to make AGI as similar to ourselves as possible, so AGI can use our pre-existing knowledge more directly.
I think that depend on the "embodiment" of the AGI. That is how it is like to be that AGI, and how it's normal world looks like. A bat (If they where people) would probably prefer different metaphors than for a human. Humans are very visual, which makes spacial feutures very salient for us. Metaphors are useful because they take advantage of already salient aspects for a person to view other things. So things that is are immidately salient for the person, has more potency as a metaphor.
I think that depends on the "embodiment" of the AGI; that is, what it's like to be that AGI and how its normal world appears. A bat (if it were a person) would probably prefer different metaphors than a human would. Humans are very visual, which makes spatial features very salient to us. Metaphors work because they leverage already-salient aspects of experience to illuminate other things. So to train an AGI, I would think it's more useful for that AGI to leverage the salient aspects that are pre-given.
I think that depends on the "embodiment" of the AGI; that is, what it's like to be that AGI and how its normal world appears. A bat (if it were a person) would probably prefer different metaphors than a human would. Humans are very visual, which makes spatial features very salient to us. Metaphors work because they leverage already-salient aspects of experience to illuminate other things. So to train an AGI, I would think it's more useful for that AGI to leverage the salient aspects that are pre-given.
#3733·Dennis HackethalOP, 4 months agoOr it might, who knows? An AGI, just like humans, would move around in the world and discover that metaphors are useful, so it might as well use spatial metaphors. If it did, that would be due to convergent evolution of ideas. And even if it didn’t, that could just be because the ideas didn’t converge, not because AGIs don’t have brains.
I think that depend on the "embodiment" of the AGI. That is how it is like to be that AGI, and how it's normal world looks like. A bat (If they where people) would probably prefer different metaphors than for a human. Humans are very visual, which makes spacial feutures very salient for us. Metaphors are useful because they take advantage of already salient aspects for a person to view other things. So things that is are immidately salient for the person, has more potency as a metaphor.
I think that depends on the "embodiment" of the AGI; that is, what it's like to be that AGI and how its normal world appears. A bat (if it were a person) would probably prefer different metaphors than a human would. Humans are very visual, which makes spatial features very salient to us. Metaphors work because they leverage already-salient aspects of experience to illuminate other things. So to train an AGI, I would think it's more useful for that AGI to leverage the salient aspects that are pre-given.
One part of my question was whether a formal criterion can be applied universally. If the citerion itself must be chosen, like for instance what brings more fun, meaning, practical utility, then by what criterion do we choose the criterion? Or is the answer simply to apply the same process of critical examination to everything that arises, until a coherent path emerges?
The other part was how you actually critize an implicit or unconcious idea. If you have an unconcious idea that gives rise to a conflicting feeling for instance, how do you critisize a feeling?
One part of my question was whether a formal criterion can be applied universally. If the citerion itself must be chosen, like for instance what brings more fun, meaning, practical utility, then by what criterion do we choose the criterion? Or is the answer simply to apply the same process of critical examination to everything that arises, until a coherent path emerges?
The other part was how you actually critize an implicit or unconcious idea. If you have an unconcious idea that gives rise to a conflicting feeling for instance, how do you critisize a feeling?
That was autocorrect from my cellphone. Mye means alot in Norwegian. Not a good idea to have autocorrect on when you're writing in two languages..
One part of mye question was whether a formal criterion can be applied universally. If the citerion itself must be chosen, like for instance what brings more fun, meaning, practical utility, then by what criterion do we choose the criterion? Or is the answer simply to apply the same process of critical examination to everything that arises, until a coherent path emerges?
The other part was how you actually critize an implicit or unconcious idea. If you have an unconcious idea that gives rise to a conflicting feeling for instance, how do you critisize a feeling?
One part of my question was whether a formal criterion can be applied universally. If the citerion itself must be chosen, like for instance what brings more fun, meaning, practical utility, then by what criterion do we choose the criterion? Or is the answer simply to apply the same process of critical examination to everything that arises, until a coherent path emerges?
The other part was how you actually critize an implicit or unconcious idea. If you have an unconcious idea that gives rise to a conflicting feeling for instance, how do you critisize a feeling?
#3682·Dennis HackethalOP, 4 months agothe other alters
This part sounds redundant (‘other others’). Also, ‘alter’ can’t be used as a noun, only as a verb (meaning ‘to change’).
Just referring here to alters as the clinical word for 'the other dissociated personalities
It seems more plausible to me that this actually is more like the division of a mind. They often recall meeting each other in dreams (seeing the other alters from their local perspective within the dream). So it seems that the split goes further, and actually gives rise to different experiences within a mind. They live and experience from different perspectives, and start communicating with each other more like distinct minds. In split-brain patients, the left and right hemispheres can disagree on what clothing to wear in the morning, and physically fight over wearing a tie or not.
It seems more plausible to me that associative identity disorder actually is more like the division of a mind. They often recall meeting each other in dreams (seeing the other alters from their local perspective within the dream). So it seems that the split goes further, and actually gives rise to different experiences within a mind. They live and experience from different perspectives, and start communicating with each other more like distinct minds. In split-brain patients, the left and right hemispheres can disagree on what clothing to wear in the morning, and physically fight over wearing a tie or not.
Has anyone explored whether the collection of ideas in a person's mind must have a specific structure?
When discussing virtues, you seem to suggest a hierarchical organization of ideas, as opposed to ideas competing horizontally for attention and salience. It appears that ideas organize vertically in a hierarchy, where activating "higher-level" ideas automatically resolves conflicts among lower-level ones. For example, if a snake suddenly appears next to you, all previous internal conflicts dissolve because self-preservation is among the most dominant (highest) ideas in their value structure.
However, individuals can construct even higher-order values that override self-preservation. The structure seems hierarchical: when a top-level idea is activated, there seems to be some alignment in lower level ideas.
Interesting! Getting ideas to jibe/cohere seems like a more and more fundamental idea the more I think about it. Has anyone explored whether the collection of ideas in a person's mind must have a specific structure?
When discussing virtues, you seem to suggest a hierarchical organization of ideas, as opposed to ideas competing horizontally for attention and salience. It appears that ideas organize vertically in a hierarchy, where activating "higher-level" ideas automatically resolves conflicts among lower-level ones. For example, if a snake suddenly appears next to you, all previous internal conflicts dissolve because self-preservation is among the most dominant (highest) ideas in their value structure.
However, individuals can construct even higher-order values that override self-preservation. The structure seems hierarchical: when a top-level idea is activated, there seems to be some alignment in lower level ideas.
#3699·Dennis HackethalOP revised 4 months agoThanks for asking good questions.
Is it accurate to view reason more as a process than a static state?
Yes.
Where the process might be summed up by
1. Being open to criticism
2. Truth-seeking (commitment to getting ideas to jibe)Yes. Aka ‘common-preference finding’ aka ‘fun’.
Some of the virtues that @benjamin-davies* has put together are part of it, too.
Has anyone explored whether the collection of ideas in a person's mind must have a specific structure?
When discussing virtues, you seem to suggest a hierarchical organization of ideas, as opposed to ideas competing horizontally for attention and salience. It appears that ideas organize vertically in a hierarchy, where activating "higher-level" ideas automatically resolves conflicts among lower-level ones. For example, if a snake suddenly appears next to you, all previous internal conflicts dissolve because self-preservation is among the most dominant (highest) ideas in their value structure.
However, individuals can construct even higher-order values that override self-preservation. The structure seems hierarchical: when a top-level idea is activated, there seems to be some alignment in lower level ideas.
#3696·Dennis HackethalOP, 4 months agoMaybe I don’t understand the question, but I don’t think there’s a one-size-fits-all criterion to use for that scenario. It depends on the content of the ideas and how they conflict exactly.
All I can say without more info is that we can try to criticize ideas and adopt the ones with no pending criticisms. That’s true for any kind of idea – explicit, inexplicit, conscious, unconscious, executable, etc. See #2281.
One part of mye question was whether a formal criterion can be applied universally. If the citerion itself must be chosen, like for instance what brings more fun, meaning, practical utility, then by what criterion do we choose the criterion? Or is the answer simply to apply the same process of critical examination to everything that arises, until a coherent path emerges?
The other part was how you actually critize an implicit or unconcious idea. If you have an unconcious idea that gives rise to a conflicting feeling for instance, how do you critisize a feeling?
#3692·Dennis HackethalOP, 4 months agoWhy would an AGI use spacial metaphors like understand, arrive, close to understand ideas?
Because it would be a product of our culture and speak English.
Aah, then I agree. I thought you meant AGI would develop the same metaphors independently.
It seems more plausible to me that this actually is a division of a mind. They often recall meeting each other in dreams (seeing the other alters from their local perspective within the dream). So it seems that the split goes further, and actually gives rise to different experiences within a mind. They live and experience from different perspectives, and start communicating with each other more like distinct minds. In split-brain patients, the left and right hemispheres can disagree on what clothing to wear in the morning, and physically fight over wearing a tie or not.
It seems more plausible to me that this actually is more like the division of a mind. They often recall meeting each other in dreams (seeing the other alters from their local perspective within the dream). So it seems that the split goes further, and actually gives rise to different experiences within a mind. They live and experience from different perspectives, and start communicating with each other more like distinct minds. In split-brain patients, the left and right hemispheres can disagree on what clothing to wear in the morning, and physically fight over wearing a tie or not.