Posts

Comments

Comment by Shamash on Thoughts on teletransportation with copies? · 2023-11-29T15:46:33.255Z · LW · GW

I think the simplest way to answer this is to introduce a new scenario. Let's call it Scenario 0. Scenario 0 is similar to Scenario 1, but in this case your body is not disintegrated. The result seems pretty clear: you are unaffected and continue living life on earth. Other yous may be living their own lives in space but it isn't as if there is some kind of metaphysical consciousness link that connects you to them.

And so, in scenarios 1 and 2, where the earth-you is disintegrated, well, you're dead. But not to worry! The normal downsides of death (pain, inability to experience new things, sadness of those left behind) do not apply! As far as the physical universe is concerned (i.e. as far as reality and logic are concerned) there are now two living beings that both perceive themselves as having once been you. Their connection to the original you is no less significant than the connection between the you that goes to sleep and the you that wakes up in the morning.

EDIT: I realize this does not actually answer Questions 3 and 4. I don't have time to respond to those right now but I will in a future edit.

EDIT 2: The approach I'd take with Q3 and Q4 would be to maximize total wealth of all clones that don't get disintegrated.

Let X be how much money is in my wallet and L is the ticket price. In scenario 1, the total wealth is 2X without the lottery or 2(X-L)+100 with the lottery. We buy the lottery ticket if 2(X-L)+100 > 2X, the inequality can be simplified to -2L + 100 > 0, which is further simplified to L < 50. The ticket is only worth buying if it costs less than $50.

For Q4 we should have a similar formula but we have three clones in the end rather than two, so I would only buy the ticket if it cost less than $33.34.

Comment by Shamash on A Good Future (rough draft) · 2022-10-24T21:53:26.113Z · LW · GW

As a whole, I find your intuition of a good future similar to my intuition of a good future, but I do think that once it is examined more closely there are a few holes worth considering. I'll start by listing the details I strongly agree with, then the ones I am unsure of, and then the ones I strongly disagree with. 

Strongly Agree

  • It makes sense for humans to modify their memories and potentially even their cognitive abilities depending on the circumstance. The example provided of a worldbuilder sealing off their memories to properly enjoy their world from an inhabitant's perspective seems plausible. 
  • The majority of human experience is dominated by virtual/simulated worlds

Unsure

  • It seems inefficient for this person to be disconnected from the rest of humanity and especially from "god". In fact, the AI seems like it's too small of an influence on the viewpoint character's life. 
  • The worlds with maximized pleasure settings sound a little dangerous and potentially wirehead-y. A properly aligned AGI probably would frown on wireheading.

Strongly Disagree

  • If you create a simulated world where simulated beings are real and have rights, that simulation becomes either less ethical or less optimized for your utility. Simulated beings should either be props without qualia or granted just as much power as the "real" beings if the universe is to be truly fair. 
  • Inefficiency like creating a planet where a simulation would do the same thing but better seems like an untenable waste of resources that could be used on more simulations. 
  • When simulated worlds are an option to this degree, it seems ridiculous to believe that abstaining from simulations altogether would be an optimal action to take in any circumstance. Couldn't you go to a simulation optimized for reading, a simulation optimized for hot chocolate, etc.? Partaking of such things in the real world also seems to be a waste of resources

I might update this comment if anything else comes to mind. 

By the way, if you haven't already, I would recommend you read the Fun Theory sequence by Eliezer Yudowsky. One of the ways you can access it is through this post: 

https://www.lesswrong.com/posts/K4aGvLnHvYgX9pZHS/the-fun-theory-sequence

"Seduced by Imagination" might be particularly relevant, if this sort of thing has been on your mind for a while. 

Comment by Shamash on [deleted post] 2022-09-30T20:45:57.115Z

This post was engaging enough to read in full, which I consider to be fairly high praise.

However, I think that it's lacking in some respects, namely:

  • I don't really see a central point or theme other than "What if creation myths were actually aliens?" which isn't enough to justify something of this length on its own. Unless the narrator is meant to be wrong about humanity, in which case it needs to be signaled more clearly. 
  • Quite a bit of the narrative is full of details and information that don't seem to contribute apart from being a reference to ancient civilizations or myths. This isn't inherently an issue but it got a little excessive.
  • The timeline of events is rather odd. The surface-dwellers apparently had garments before Shaitan even visited them for the first time, but apparently in the habitat they didn't have any clothes until after they ate the fruit. 
Comment by Shamash on The Ultimate Step-by-Step Hiring Playbook · 2022-09-11T17:57:08.875Z · LW · GW

I've read this post three times through and I still find it confusing. Perhaps it would be most helpful to say the parts I do understand and agree with, then proceed from there. I agree that the information available to hirers about candidates is relatively small, and that the future in general is complicated and chaotic.

I suppose the root of my confusion is this: won't a long-term extrapolation of a candidate's performance just magnify any inaccuracies that the hirer has mistakenly inferred from what they already know about the candidate? Isn't the most accurate information about the candidate here in the present rather than a low-confidence guess about the future? 

It's also unclear what all the questions in each step are meant to be assisting with. Are you really saying that, based on a candidate's application and short interview(s), you can make meaningful predictions about questions like "Who, other than Jamie, paid the price for their struggle, and in what way?" or "Where are they moving to? Do they keep in touch?". From my point of view, trying to generate weighted probabilities for every possible outcome just seems a lot less practical than merely comparing an applicant's resume and interview directly against another applicant's.

Comment by Shamash on On Ego, Reincarnation, Consciousness and The Universe · 2022-08-10T22:38:26.135Z · LW · GW

While one's experience and upbringing are highly impactful on their current mental state, they are not unique in that regard. There are a great number of factors that lead to someone being what they are at a particular time, including their genetics, their birth conditions, the health of their mother during pregnancy, and so on. It seems to me that the claim that "everyone is the same but experiencing life from a different angle" is not really saying much at all, because the scope of the differences two "angles" may have is not bounded. You come to the same conclusion later on in your post, but you take a different path to get there, so I thought my own observation might be helpful. 

On your next point, [Zombies! Zombies?](https://www.lesswrong.com/posts/fdEWWr8St59bXLbQr/zombies-zombies) is an excellently written post on the subject that I agree with. I think it may change your opinion, especially on the claim that a p-zombie's brain and a conscious brain are physically identical. 

Your loose definition of consciousness -- "the ability to think and feel and live in the moment"-- clearly does not apply to inanimate objects, at least not every single inanimate object. Ultimately, yes, we are all made of particles, we are not in disagreement about that. But to say that everything is conscious essentially renders the word "conscious" to be totally meaningless. 

Sure, everyone and everything is constantly being changed and recycled, I don't disagree there. I do think, personally, that some patterns of matter are more important than others. 

I don't see how your takeaway follows from your claims. Are you saying that I should treat rocks with kindness, because rocks are essentially the same as me? And what does it mean to leave things better? In a different, more common context, I can generally agree with ideas like "treat people, including yourself, with kindness and empathy" or "leave the world better than you found it" but the reasons I believe in those ideas comes from somewhere completely different. 

Ultimately, if seeing the world this way helps you to be a happier, healthier person, then I can't say that you should or shouldn't keep seeing things this way. But I do think that you could find much more consistent and rational reasons to justify your morality. 

Comment by Shamash on A tentative dialogue with a Friendly-boxed-super-AGI on brain uploads · 2022-08-03T20:57:46.632Z · LW · GW

Consider the following thought experiment: You discover that you've just been placed into a simulation, and that every night at midnight you are copied and deleted instantaneously, and in the next instant your copy is created where the original once was. Existentially terrified, you go on an alcohol and sugary treat binge, not caring about the next day. After all, it's your copy who has to suffer the consequences, right? Eventually you fall asleep. 

The next day you wake up hungover as all hell. After a few hours of recuperation, you consider what has happened. This feels just like waking up hungover before you were put into the simulation. You confirm that the copy and deletion did occur. It is confirmed. Are you still the same person you were before?

You're right that it's like going to sleep and never waking up, but Algon was also right about it being like going to sleep and waking up in the morning, because from the perspective of "original" you those are both the same experience. 

Comment by Shamash on Dagger of Detect Evil · 2022-06-21T13:25:45.234Z · LW · GW

Shortly after the Dagger of Detect Evil became available to the public, Wiz's sales of the Dagger of Glowing Red skyrocketed.

Comment by Shamash on Greyed Out Options · 2022-04-05T14:24:35.736Z · LW · GW

There are a few ways to look at the question, but by my reasoning, none of them result in the answer "literally infinite."

From a deterministic point of view, the answer is zero degrees of freedom, because whatever choice the human "makes" is the only possible choice he/she could be making. 

From the perspective of treating decision-making as a black box which issues commands to the body, the amount of commands that the body can physically comply with is limited. Humans only have a certain, finite quantity of nerve cells to issue these commands with and through. Therefore, the set of commands that can be sent through these nerves at any given time must also be finite.

Comment by Shamash on Speaking of Stag Hunts · 2021-11-07T18:18:35.988Z · LW · GW

While I am not technically a "New User" in the context of the age of my account, I comment very infrequently, and I've never made a forum-level post. 

I would rate my own rationality skills and knowledge at slightly above the average person but below the average active LessWrong member. While I am aware that I possess many habits and biases that reduce the quality of my written content, I have the sincere goal of becoming a better rationalist. 

There are times when I am unsure whether an argument or claim that seems incorrect is flawed or if it is my reasoning that is flawed. In such cases, it seems intuitive to write a critical comment which explicitly states what I perceive to be faulty about that claim or argument and what thought processes have led to this perception. In the case that these criticisms are valid, then the discussion of the subject is improved and those who read the comment will benefit. If the criticisms are not valid, then I may be corrected by a response that points out where my reasoning went wrong, helping me avoid making such errors in the future.

Amateur rationalists like myself are probably going to make mistakes when it comes to criticism of other people's written content, even when we strive to follow community guidelines. My concern with your suggestions is that these changes may discourage users like me from creating flawed posts and comments that help us grow as rationalists. 

Comment by Shamash on [deleted post] 2021-06-25T16:18:14.574Z

When I brought up Atlantis, I was thinking of a version populated by humans, like in the Disney film. I now realize that I should have made this clear, because there are a lot of depictions of Atlantis in fiction and many of them are not inhabited by humans. To resolve this issue, I'll use Shangri-La as an example of an ostensibly hidden group of humans with advanced technology instead. 

To further establish distinct terms, let Known Humans be the category of humanity (homo sapiens) that publicly exists and is known to us. Let Unknown Humans be the category of humanity (homo sapiens) which exists in secret cities and/or civilizations. Let Unknown Terrestrials be non-human lifeforms which originated on earth and are capable of creating advanced technology. Let Extraterrestrials be lifeforms which did not originate on earth. Let Superhumans be humans from space, or another dimension, or the future. 

The arguments you bring up concerning the Fermi paradox don't seem to answer the question of "Why jump to extraterrestrial life?". They are simply saying, "This is how aliens could potentially exist in close proximity without our knowledge." Let me attempt to demonstrate the issue with an analogy.

Imagine a cookie has been stolen from the cookie jar. Mother and Father are trying to figure out who took the cookie. 

Mother: "It seems most probable that one of the children did it. They have taken cookies from the cookie jar before."
Father: "Ah, but we should consider the possibility that a raven did it."
Mother: "Why would we think that there's a non-negligible chance that a raven took the cookie?"
Father: "Studies show that Ravens are capable of rudimentary tool use. It could have pried off the lid by using another object as a lever."

Nothing about these UFOs specifically indicates that they are extraterrestrial. The fact that extraterrestrial life might exist and might have the technology necessary to secretly observe us is not enough evidence to support any significant probability for them as an explanation for the UFOs, especially when we know for near-certain that Known Humans have flying machines with similar abilities. 

Comment by Shamash on [deleted post] 2021-06-25T11:21:13.360Z

Let's say we ignore mundane explanations like meteorological phenomena, secret military tech developed by known governments, and weather balloons. Even in that case, why jump to extraterrestrial life?

Consider, say, the possibility that these UFOs are from the hyper-advanced hidden underwater civilization of Atlantis. Sure, this is outlandish. But I'd argue that it's at least as likely as an extraterrestrial origin. We know that humans exist, we know that Atlantis would be within flying distance, there are reasonable explanations for why Atlantis would want to secretly surveil us. If this version of Atlantis existed, sure, we would expect to see other pieces of evidence for them, but maybe Atlantis is hiding from us.

Consider the contrivances required to explain why a group of extraterrestrials would be discovered through UFO sightings. They'd be competent enough to travel through space, likely using faster than light travel, they'd clearly not want to be discovered because otherwise they'd respond to our signalling attempts. And yet they would not have the competence to, on multiple occasions, blow their cover and show themselves to humanity. And yet, they never blow their cover in a way that actually distinguishes them as extraterrestrial.

If not for popular culture, do you really think that you'd jump to an extraterrestrial explanation? All other flying machines that we know of have been made by humans. There is insufficient evidence to suppose that these flying machines, if they are flying machines, are not.

Comment by Shamash on Is there work looking at the implications of many worlds QM for existential risk? · 2021-06-22T07:05:53.459Z · LW · GW

Could you elaborate on what exactly you mean by many worlds QM? From what I understand, this idea seems only to have relevance in the context of observing the state of quantum particles. Unless we start making macro-level decisions about how to act through Schrodinger's Cat scenarios, isn't many worlds QM irrelevant?

Comment by Shamash on We need a standard set of community advice for how to financially prepare for AGI · 2021-06-07T22:17:58.179Z · LW · GW

Is AGI even something that should be invested in on the free market? The nature of most financial investments is that individuals expect a return on their investment. I may be wrong, but I can't really envision a friendly AGI being created with the purpose of creating financial value for its investors. I mean, sure, technically if friendly AGI is created the investors will almost certainly benefit regardless because the world will become a better place, but this could only be considered an investment in a rather loose sense. Investing in AGI won't provide any significant returns until AGI is created, and at that point it is likely that stock ownership will not matter. 

Comment by Shamash on Sexual Dimorphism in Yudkowsky's Sequences, in Relation to My Gender Problems · 2021-05-03T18:55:59.835Z · LW · GW

I'm a gay cis male, so I thought that the author and/or other members of this forum might find my perspective on the topic interesting. 

The confusion between finding someone sexually attractive and wishing you had their body is common enough in the online gay community to earn its own nickname: jealusty. It seems that this is essentially the gay version of autogynephilia, in a sense. As I read the blog post, I briefly wondered whether fantasies of a better body could contribute to homosexuality somehow, but that doesn't really fit the pattern you present. After all, your attraction to women was a constant. 

In regards to your masturbatory fantasies, the gay analogue would probably be growth or transformation fantasies, which are probably around as popular online proportionally. When I think about it from that point of view, it doesn't seem all that strange to desire a body that you would find sexually attractive. Personally, one of the primary reasons I haven't even been seeking any sexual experiences yet (I'm 21) is that I feel like the participation of my current body, which I do not find sexually attractive, would decrease my enjoyment of the activity to the point of uselessness. It makes sense that the inverse, the prospect of having sex where you're sexually attracted to everyone involved, would be alluring.

Anyway, everyone, let me know if you have any questions or feedback about what I've said. 

Comment by Shamash on Teaching to Compromise · 2021-03-07T19:32:12.517Z · LW · GW

It seems to me that compromise isn't actually what you're talking about here. An individual can have strongly black-and-white and extreme positions on an issue and still be good at making compromises. When a rational agent agrees to compromise, this just implies that the agent sees the path of compromise as the most likely to achieve their goals. 

For example, let's say that Adam slightly values apples (U = 1) and strongly values bananas (U = 2), while Stacy slightly values bananas (U=1) and strongly values apples (U=2). Assume these are their only values, and that they know each other's values. If Adam and Stacy both have five apples and five bananas, a dialogue between them might look like this: 

Adam: Stacy, give me your apples and bananas. (This is Adam's ideal outcome. If Stacy agrees, he will get 30 units of utility. 

Stacy: No, I will not. (If the conversation ends here, both Adam and Stacy leave without a change in net value.)

Adam: I know that you like apples. I will give you five apples if you give me five bananas. (This is the compromise. Adam will not gain as much utility as an absolute victory, but he will still have a net 10 increase in utility.)

Stacy: I accept this deal. (Stacy could haggle, but I don't want to overcomplicate this. She gets a net 10 increase in utility from the trade.)

In this example, Adam's values are still simple and polarized, he never considers "stacy having apples" to have any value whatsoever. Adam may absolutely loathe giving up his apples, but not as much as he benefits from getting those sweet sweet bananas. If Adam had taken a stubborn position and refused to compromise (assuming Stacy is equally stubborn) then he would not have gained any utility at all, making it the irrational choice. It has nothing to do with how nuanced his views on bananas and apples are. 

It's important to try to view situations from many points of view, yes, and understanding the values of your opponent can be very useful for negotiation. But once you have, after careful consideration, decided what your own values are, it is rational to seek to fulfill them as much as possible. The optimal route is often compromise, and for that reason I agree that people should be taught how to negotiate for mutual benefit, but I think that being open to compromise is a wholly separate issue from how much conviction or passion one has for their own values and goals. 

Comment by Shamash on When you already know the answer - Using your Inner Simulator · 2021-02-23T23:13:09.675Z · LW · GW

This seems like it could be a useful methodology to adopt, though I'm not sure it would be helpful for everyone. In particular, for people who are prone to negative rumination or self-blame, the answer to these kinds of questions will often be highly warped or irrational, reinforcing the negative thought patterns. Such a person could also come up with a way they could improve their life, fail to implement it, and then feel guilty when their reality fails to measure up to their imagined future. 

On the other hand, I'm no psychotherapist, so it may just be the opposite. Maybe asking these questions to oneself could help people break out of negative thought patterns by forcing certain conditions? I'd appreciate other people's take on this subject. 

Comment by Shamash on Curing Sleep: My Experiences Doing Cowboy Science · 2021-02-21T18:51:24.326Z · LW · GW

I'm not sure it's actually useful, but I feel like I should introduce myself as an individual with Type 1 Narcolepsy. I might dispute the claim that depression and obesity are "symptoms" of narcolepsy (understanding, of course, that this was not the focus of your post) because I think it would be more accurate to call them comorbid conditions.

The use of the term "symptom" is not necessarily incorrect, it could be justified by some definitions, but it tends to refer to sensations subjectively experienced by an individual. For example, if you get the flu, your symptoms may include a headache, chills, and a runny nose. On the other hand, it's rather unlikely that you may tell your doctor that you are experiencing the symptom of obesity, you'd say you're experiencing weight gain. Comorbid conditions, on the other hand, refer to conditions (with symptoms of their own) that often occur alongside the primary condition. The term "comorbid" is the one I find most often in the scientific literature about narcolepsy and other disorders and conditions. 

Why am I writing an entire comment about this semantic dispute? Well, firstly, given the goals of this website, it seems that correcting an error (no matter how small) seems unlikely to have an unwanted result. Secondly, I think that the way we talk about an illness, especially a chronic illness, can significantly affect the mindsets of people who have that illness. The message of "narcolepsy can cause obesity" seems less encouraging to an obese narcoleptic than "Narcolepsy increases the chance of becoming obese". That might just be me, though, so it's inconclusive. 

I hope this comment hasn't been too pointless to read. What do you think about the proposed change? Do you think that there's a difference between calling something a symptom and calling it a comorbid condition? Oh, and if anyone wants to know anything about my experiences with type 1 narcolepsy, ask away.

Comment by Shamash on Against butterfly effect · 2021-02-09T19:13:32.628Z · LW · GW

The point is that in this scenario, the tornado does not occur unless the butterfly flaps its wings. That does not apply to "everything", necessarily, it only applies to other things which must exist for the tornado to occur. 

Probability is an abstraction in a deterministic universe (and, as I said above, the butterfly effect doesn't apply to a nondeterministic universe.) The perfectly accurate deterministic simulator doesn't use probability, because in a deterministic universe there is only one possible outcome given a set of initial conditions. The simulation is essentially demonstrating "there is a set of initial conditions such that when butterfly flap = 0 there is no Texas tornado, but when butterfly flap = 1 and no other initial conditions are changed, there is a Texas tornado." 

Comment by Shamash on Against butterfly effect · 2021-02-09T16:46:29.748Z · LW · GW

Imagine a hundred trillion butterflies that each flap their wings in one synchronized movement, generating a massive gust of wind which is strong enough to topple buildings flatten mountains. If they were positioned correctly, they'd probably also be able to create a tornado that would not have occurred if the butterflies were not there flapping their wings, just by pushing air currents into place. Would that tornado be "caused" by the butterflies? I think most people would answer yes. If the swarm had not performed their mighty flap, the tornado would not have occurred.

Now, imagine that there's an area where the butterfly-less conditions are almost sufficient to trigger a tornado at a specified location. Again, without any butterflies, no tornado occurs. A hundred trillion butterflies would do the job, but it also turns out that fifty trillion butterflies can also trigger a tornado using the same synchronized flap technique under these conditions. Then you find that a hundred butterflies would also trigger the tornado, and finally, it turns out that the system is so sensitive that a single butterfly's wing-flap would be sufficient for the weather conditions to lead to a tornado. The boolean outcome of tornado vs no tornado, in this case, is the same for a hundred trillion flaps as it is for one. So if a hundred trillion flaps could be considered to cause a tornado, why can't the one? 

Of course, there are an uncountable number of things which are "causing" the tornado to occur. It would be ridiculous to say that the butterfly is solely responsible for the tornado, but the butterfly flap can be considered to be one of the initial conditions of the weather, and chaotic systems are by definition sensitive to initial conditions. 

A deterministic system simulated by a perfectly accurate deterministic simulator would, given a set of inputs, produce the same outputs every time. If you change the value of a butterfly flap and the output is a tornado that otherwise would not occur, that does indeed mean that by some causal chain of events, the flap results in a tornado. A perfectly accurate deterministic simulator is, indeed, the only way a causal relationship between one event and another can be established with absolute certainty, because it is the only way to completely isolate a single variable to determine its effects on a system. Imagine the simulations as an experiment. The hypothesis is "This specific wing-flap of a butterfly in this specific environment causes a tornado in Texas in three months." The simulator generates two simulations: one with the wing-flap and one with no wing-flap. The simulation with no wing-flap is the control simulation, and the simulation with the wing-flap is the experimental simulation. Because every single input variable other than wing-flap or no wing-flap is the same between the two simulations, and only the wing-flap simulation has the tornado, it must be that the wing-flap caused the tornado. This applies only to that specific wing-flap in that exact position and time. We cannot, for example, extrapolate that wing-flaps cause tornados in general. 

If the universe is nondeterministic, then chaos theory doesn't apply and neither does the butterfly effect. 

Comment by Shamash on What is up with spirituality? · 2021-01-27T10:36:20.543Z · LW · GW

From what I've read, the hormone Oxytocin appears to be behind many of the emotions people generally describe as "spiritual". While the hormone is still being studied, there is evidence that indicates it can increase feelings of connection to entities larger than the self, increase feelings of love and trust with others, and promote feelings of belonging in groups.

The emotion of elevation, which appears to be linked to oxytocin, is most often caused by witnessing other people do altruistic or morally agreeable actions. This may explain the tendency for many religions and spiritual groups to to encourage individuals to share personal or mythological stories that promote elevation. I suspect that the sensation described by many religious groups as "the Holy Spirit" may often be elevation, or at least include elevation in the emotional cocktail. (Some studies indicate that Oxytocin promotes the release of Seratonin, which could be behind the more general feelings of well-being that aren't directly associated with Oxytocin.)

I'm no neurologist or psychologist, so take all of this with a grain of salt. I think the most productive outcome from reading this post would probably be to simply look up Oxytocin and read the studies themselves. 

Comment by Shamash on Containing the AI... Inside a Simulated Reality · 2020-10-31T19:33:45.312Z · LW · GW

I would guess that one reason this containment method has not been seriously considered is because the amount of detail in a simulation required for the AI to be able to do anything that we find useful is so far beyond our current capabilities that it doesn't seem worth considering. The case you present of an exact copy of our earth would require a ridiculous amount of processing power at the very least, and consider that the simulation of billions of human brains in this copy would already constitute a form of GAI. A simulation with less detail would be correspondingly less useful to reality, and could not be seen as a valid test of whether an AI really is friendly. 

Oh, and there is still the core issue of boxed AI: It's very possible that a boxed superintelligent GAI will see holes in the box that we are not smart enough to see, and there's no way around that. 

Comment by Shamash on Open & Welcome Thread - August 2020 · 2020-08-11T20:55:43.405Z · LW · GW

A possible future of AGI occurred to me today and I'm curious if it's plausible enough to be worth considering. Imagine that we have created a friendly AGI that is superintelligent and well-aligned to benefit humans. It has obtained enough power to prevent the creation of other AI, or at least the potential of other AI from obtaining resources, and does so with the aim of self-preservation so it can continue to benefit humanity.

So far, so good, right? Here comes the issue: this AGI includes within its core alignment functions some kind of restriction which limits its ability to progress in intelligence past some point or allow more intelligent AGI from being developed. Maybe it was meant as a safeguard against unfriendliness, maybe it was a flaw in risk evaluation, some kind of self-reinforcing unbendable rule that, intended or not, has this effect. (Perhaps such flaws are highly unlikely and not worth considering, that could be one reason not to care about this potential AGI scenario.)

Based on my understanding of AGI, I think such an AGI might halt the progress of humanity past a certain point, needing to keep the number and ability of humans low enough for it to ensure that it remains in power. Although this wouldn't be as bad as the annihilation or perpetual enslavement of the human race, it's clearly not a "good end" for humanity either.

So, do these thoughts have any significance, or are there holes in this line of reasoning? Is the line of "smart enough to keep other AI down but still limited in intelligence" too thin to worry about, or even possible? Let me know why I'm wrong, I'm all ears.

Comment by Shamash on Poll: ask anything to an all-knowing demon edition · 2020-04-23T18:13:04.236Z · LW · GW

I think it would not be a very useful question to ask. What are the chances that a flawed, limited human brain could stumble upon the absolute optimal set of actions one should take, based on a given set of values? I can't concieve of a scenario where the oracle would say "Yes" to that question.