All of Program Den's Comments + Replies

Regarding "all things being equal" / ceteris paribus, I think you are correct (assuming I'm interpreting this last bullet-point as intended) in that it "binds" a system in ways that "divorce it from reality" to some extent.

I feel like this is a given, but also that since the concept exists on a "spectrum of isolation", the ones that are closer to the edge of "impossible to separate" necessarily skew/divorce reality further.

I'm not sure if I've ever explicitly thought about that feature of this cognitive device— and it's worth explicitly thinking about! &nb... (read more)

I would probably define AGI first, just because, and I'm not sure about the idea that we are "competing" with automation (which is still just a tool conceptually right?).

We cannot compete with a hammer, or a printing press, or a search engine.  Oof.  How to express this?  Language is so difficult to formulate sometimes.

If you think of AI as a child, it is uncontrollable.  If you think of AI as a tool, of course it can be controlled.  I think a corp has to be led by people, so that "machine" wouldn't be autonomous per se…

Guess it's ... (read more)

Yes, it is, because it took like five years to understand minority-carrier injection.

lc
*1517

The transistor is a neat example.

No, it's not, because we have a pretty good idea of how transistors work and in fact someone needed to directly anticipate how they might work in order to engineer them. The "unknown" part about the deep learning models is not the network layer or the software that uses the inscrutable matrices, it's how the model is getting the answers that it does.

LOL!  Gesturing in a vague direction is fine.  And I get it.  My kind of rationality is for sure in the minority here, I knew it wouldn't be getting updoots.  Wasn't sure that was required or whatnot, but I see that it is.  Which is fine.  Content moderation separates the wheat from the chaff and the public interwebs from personal blogs or whatnot.

I'm a nitpicker too, sometimes, so it would be neat to suss out further why the not new idea that “everything in some way connects to everything else" is "false" or technically incor... (read more)

I love it!  Kind of like Gödel numbers!

I think we're sorta saying the same thing, right?

Like, you'd need to be "outside" the box to verify these things, correct?

So we can imagine potential connections (I can imagine a tree falling, and making sound, as it were) but unless there is some type of real reference— say the the realities intersect, or there's a higher dimension, or we see light/feel gravity or what have you— they don't exist from "inside", no?

Even imagining things connects or references them to some extent… that's what I meant about unknown ... (read more)

2Viliam
You seem enthusiastic about many things, but as you have probably noticed, this is not the right website for this type of debate. Please notice the negative numbers at some of your posts and comments, those are votes against having this type of content. What I wanted to do in the previous comment was mostly to nitpick on the logic "everything relates to something, therefore everything relates to everything" from the mathematical perspective. Technical correctness of ideas is considered important here. To get a better idea of what this website is about, you might want to read Rationality: From AI to Zombies (online, download EPUB, MOBI, PDF), A Map that Reflects the Territory (Amazon), or The Engines of Cognition (Amazon). Sorry for throwing a lot of text to you, but I cannot think of a simple way how to succintly explain the kind of debate that is appreciated at this website versus... uhm... writing many different ideas with question marks. So I am just pointing a finger and saying "something like that".

My point is that complexity, no matter how objective a concept, is relative.  Things we thought were "hard" or "complex" before, turn out to not be so much, now.

Still with me?  Agree, disagree?

Patterns are a way of managing complexity, sorta, so perhaps if we see some patterns that work to ensure "human alignment[1]", they will also work for "AI alignment" (tho mostly I think there is a wide wide berth betwixt the two, and the later can only exist after of the former).

We like to think we're so much smarter than the humans that came before us, and... (read more)

3Viliam
Let's change the first statement into something from graph theory: "If a vertex is blue, it must be connected to some other blue vertex." (Vertices are all possible things, blue ones are those that actually exist.) This still allows the blue subgraph to consist of several disconnected parts. Maybe points 1, 2, and 3 are connected to each other, and then somewhere else there are points 4 and 5 connected to each other, but not connected to the former group. The statement that each blue vertex is connected to some other blue vertex is true (1 is connected to 2 and 3, 2 is to 1 and 3, 3 is to 1 and 2, 4 is to 5, and 5 is to 4), and yet not everything is connected to everything else, not even indirectly (1 is not connected to 4). Translated back: There could be several parallel realities; each of them existing from its own perspective, but not existing from the perspective of the remaining ones. (Problem is that we, being a part of one of those realities, would have no way to prove that it is so, as by definition we would not be connected, even indirectly, to the remaining realities.) From the perspective of modern physics, even the transitivity of "things being connected" could be challenged. Suppose that you live in an expanding universe. One day you get a message from God saying that if you travel to north at almost the speed of light, after 100 subjective years you will see the light coming from a star X. But if you instead travel to south at almost the speed of light, after 100 subjective years you will see the light coming from a star Y. The universe is expanding, and whichever option you choose, it will be too late to turn back and try to see also the other star; it has already disappeared from your light cone. In this scenario, your home planet is connected to both the star X and the star Y, but the stars X and Y are not connected to each other. From the perspective of time: the present is connected to several possible futures. But those futures are not con

For something to "exist", it must relate, somehow, to something else, right?

If so, everything relates to everything else by extension, and to some degree, thus "it's all relative".

Some folk on LW have said I should fear Evil AI more than Rogue Space Rock Collisions, and yet, we keep having near misses with these rocks that "came out of nowhere".

I'm more afraid of humans humaning, than of sentient computers humaning.

Is not the biggest challenge we face the same as it has been— namely spreading ourselves across multiple rocks and other places in space, so al... (read more)

2Viliam
The latter doesn't logically follow from the former.

It's a weird one to think about, and perhaps paradoxicle.  Order and chaos are flip sides of the same coin— with some amorphous 3rd as the infinitely varied combinations of the two!

The new patterns are made from the old patterns.  How hard is it to create something totally new, when it must be created from existing matter, or existing energy, or existing thoughts?  It must relate, somehow, or else it doesn't "exist"[1].  That relation ties it down, and by tying it down, gives it form.

For instance, some folk are mad at computer-assisted ... (read more)

1[anonymous]
Complexity is objectively quantifiable. I don't think I understand your point. This is an example of where complexity is applied to specific domains.

Contributes about as much as a "me too!" comment.

"I think this is wrong and demonstrating flawed reasoning" would be more a substantive repudiation with some backing as to why you think the data is, in fact, representative of "true" productivity values.

This statement makes a lot more sense than your "sounds like cope" rejoinder brief explanation:

Having a default base of being extremely skeptical of sweeping claims based on extrapolations on GDP metrics seems like a prudent default.

You don't have to look far to see people, um, not exactly satisfied with how... (read more)

Illustrative perhaps?

Am I wrong re: Death?  Have you personally feared it all your life?

Frustratingly, all I can speak from is my own experience, and what people have shared with me, and I have no way to objectively verify that anything is "true".

I am looking at reality and saying "It seems this way to me; does it seem this way to you?"

That— and experiencing love and war &c. — is maybe why we're "here"… but who knows, right?

Signals, and indeed, opposites, are an interesting concept!  What does it all mean?  Yin and yang and what have you…

Would you agree that it's hard to be scared of something you don't believe in?

And if so, do you agree that some people don't believe in death?

Like, we could define it at the "reality" level of "do we even exist?" (which I think is apart from life & death per se), or we could use the "soul is eternal" one, but regardless, it appears to me that lots of people don't believe they will die, much less contemplate it.  (Perhaps we... (read more)

1M. Y. Zuo
I presume these questions are rhetorical?

"sounds like cope"?  At least come in good faith!  Your comments contribute nothing but "I think you're wrong".

Several people have articulated problems with the proposed way of measuring — and/or even defining — the core terms being discussed.

(I like the "I might be wrong" nod, but it might be good to note as well how problematic the problem domain is.  Econ in general is not what I'd call a "hard" science.  But maybe that was supposed to be a given?).

Others have proposed better concrete examples, but here's a relative/abstract bit via ... (read more)

2DragonGod
"I think this is wrong and demonstrating flawed reasoning" is actually a contribution to the discourse. I gave a brief explanation over the rest of the comment on how it came across to me like cope.

I'm familiar with AGI, and the concepts herein (why the OP likes the proposed definition of CT better than PONR), it was just a curious post, what with having "decisions in the past cannot be changed" and "does X concept exist" and all.

I think maybe we shouldn't muddy the waters more than we already have with "AI" (like AGI is probably a better term for what was meant here— or was it?  Are we talking about losing millions of call center jobs to "AI" (not AGI) and how that will impact the economy/whatnot?  I'm not sure if that's transformatively u... (read more)

LOL!  Yeah I thought TAI meant 

TAI: Threat Artificial Intelligence

The acronym was the only thing I had trouble following, the rest is pretty old hat.

Unless folks think "crunch time" is something new having only to do with "the singularity" so to speak?

If you're serious about finding out if "crunch time" exists[1] or not, as it were, perhaps looking at existing examples might shed some light on it?

  1. ^

    even if only in regards to AGI

I'd toss software into the mix as well.  How much does it cost to reproduce a program?  How much does software increase productivity?

I dunno, I don't think the way the econ numbers are portrayed here jive with reality.  For instance: 

"And yet, if I had only said, “there is no way that online video will meaningfully contribute to economic growth,” I would have been right."

doesn't strike me as a factual statement.  In what world has streaming video not meaningfully contributed to economic growth?  At a glance it's ~$100B industr... (read more)

2SomeoneYouOnceKnew
It's details like these that you point out here, which make me SUPER hesitant when reading people making claims about correlating GDP/economy-based metrics with anything else. What's the original charts base definitions, assumptions, and their error bars? What's their data sources, what assumptions are they making? To look at someone's charts over GDP and then extrapolate and finally go "tech has made no effect", feels naive and short-sighted, at least, from a rational perspective- we should know that these charts tend not to convey as much meaning as we'd like. Having a default base of being extremely skeptical of sweeping claims based on extrapolations on GDP metrics seems like a prudent default.
2plex
Agree with Jim, and suggest starting with some Rob Miles videos. The Computerphile ones, and those on his main channel, are a good intro.
8jimrandomh
TAI = Transformative AI I think you're missing too many prerequisites to follow this post, and that you're looking for something more introductory.

Traditionally it's uncommon (or should be) for youth to have existential worries, so I don't know about cradle to the grave[1], tho external forces are certainly "always" concerned with it— which means perhaps the answer is "maybe"?

There's the trope that some of us act like we will never die… but maybe I'm going too deep here?  Especially since what I was referring to was more a matter of feeling "obsolete", or being replaced, which is a bit different than existential worries in the mortal sense[2].

I think this is different from the Luddite feelings b... (read more)

1M. Y. Zuo
There's the superficial appearance of that. Yet in fact it signals the opposite, that the fear of death has such a vicegrip on their hearts to the point it's difficult to not psychoanalyze the writer when reading through their post history.

It seems like the more things change, the more they stay the same, socially.

Complexity is more a problem of scope and focus, right?  Like even the most complex system can be broken down into smaller, less complex pieces— I think?  I guess anything that needs to take into consideration the "whole", if you will, is pretty complex.

I don't know if information itself makes things more complex.  Generally it does the opposite.
As long as you can organize it I reckon! =]

1[anonymous]
Some things change, some things don't change much. Socially, people don't really change much. What changes more often is the environment because of ideas, innovation, and inventions. These things may create new systems that we use, different processes that we adopt, but fundamentally, when we socialize in these context as individuals, we rely on our own natural social instincts to navigate the waters. If you think of this as a top down perspective, some layers change more often than others. For example, society as a whole stays more or less the same, but on the level of corporations and how work is done, it has changed dramatically. On the individual level, knowledge has expanded but how we learn doesn't change as much as what we learn. Complexity deals mostly with the changing parts. They wouldn't be complex if they didn't change and people have had time to learn and adapt. New things added to an existing system also makes the system more complex.

No, people are not always existentially worried.  Some are, sometimes.
I guess it ebbs and flows for the most part.

1M. Y. Zuo
I didn't mean it as literally every second of the day. 

It's neat that this popped up for me! I was just waxing poetic (or not so much) about something kind of similar the other day.

The words we use to describe things matter.  How much, is of course up for debate, and it takes different messages to make different people "understand" what is being conveyed, as "you are unique; just like everyone else", so multiple angles help cover the bases :)

I think using the word "reward" is misleading[1], since it seems have sent a lot of people reasoning down paths that aren't exactly in the direction of the meaning in... (read more)

Bwahahahaha!  Lord save us! =]

I get the premise, and it's a fun one to think about, but what springs to mind is

Phase 1: collect underpants
Phase 2: ???
Phase 3: kill all humans

As you note, we don't have nukes connected to the internet.

But we do use systems to determine when to launch nukes, and our senses/sensors are fallible, etc., which we've (barely— almost suspiciously "barely", if you catch my drift[1]) managed to not interpret in a manner that caused us to change the season to "winter: nuclear style".

Really I'm doing the same thing as the alignment debate is on about, but about the... (read more)

Do we all have the same definition of what AGI is?  Do you mean being able to um, mimic the things a human can do, or are you talking full on Strong AI, sentient computers, etc.?

Like, if we're talking The Singularity, we call it that because all bets are off past the event horizon.

Most the discussion here seems to sort of be talking about weak AI, or the road we're on from what we have now (not even worthy of actually calling "AI", IMHO— ML at least is a less overloaded term) to true AI, or the edge of that horizon line, as it were.

When you said "the ... (read more)

Saying ChatGPT is "lying" is an anthropomorphism— unless you think it's conscious?

The issue is instantly muddied when using terms like "lying" or "bullshitting"[1], which imply levels of intelligence simply not in existence yet.  Not even with models that were produced literally today.  Unless my prior experiences and the history of robotics have somehow been disconnected from the timeline I'm inhabiting.  Not impossible.  Who can say.  Maybe someone who knows me, but even then… it's questionable.  :)

I get the idea that "Real ... (read more)

I like that you have reservations about if we're even powerful enough to destroy ourselves yet.  Often I think "of course we are!  Nukes, bioweapons, melting ice!", but really, there's no hard proof that we even can end ourselves.

It seems like the question of human regulation would be the first question, if we're talking about AI safety, as the AI isn't making itself (the egg comes first).  Unless we're talking about some type of fundamental rules that exist a priori. :)

This is what I've been asking and so far not finding any satisfactory an... (read more)

It must depend on levels of intelligence and agency, right?  I wonder if there is a threshold for both of those in machines and people that we'd need to reach for there to even be abstract solutions to these problems?  For sure with machines we're talking about far past what exists currently (they are not very intelligent, and do not have much agency), and it seems that while humans have been working on it for a while, we're not exactly there yet either.

Seems like the alignment would have to be from micro to macro as well, with constant communica... (read more)

3Matt Goldenberg
Well, the same alignment issue happens with organizations, as well as within an individual with different goals and desires. It turns out that the existing "solutions" to these abstractly similar problems look quite different because the details matter a lot. And I think AGI is actually more dissimilar to any of these than they are to each other.

Right?  A lack of resilience is a problem faced currently.  It seems silly to actually aim for something that could plausibly cascade into the problems people fear, in an attempt to avoid those very problems to begin with.

It might be fun to pair Humankind: A Hopeful History with The Precipice, as both have been suggested reading recently.

It seems to me that we are, as individuals, getting more and more powerful.  So this question of "alignment" is a quite important one— as much for humanity, with the power it currently has, as for these hypothetical hyper-intelligent AIs.

Looking at it through a Sci-Fi AI lens seems limiting, and I still haven't really found anything more than "the future could go very very badly", which is always a given, I think.

I've read those papers... (read more)

It seems to me that a lot of the hate towards "AI art" is that it's actually good.  It was one thing when it was abstract, but now that it's more "human", a lot of people are uncomfortable.  "I was a unique creative, unlike you normie robots who don't do teh art, and sure, programming has been replacing manual labor everywhere, for ages… but art isn't labor!" (Although getting paid seems to plays a major factor in most people's reasoning about why AI art is bad— here's to hoping for UBI!)

I think they're mainly uncomfortable because the math works... (read more)

1M. Y. Zuo
Aren't people always existentially worried, from cradle to grave?

Oh snap, I read and wrote "sarcasm" but what I was trying to do was satire.

Top-down control is less fragile than ever, thanks to our technology, so I really do fear people reacting to AI the way they generally do to terrorist attacks— with Patriot Acts and other "voluntary" freedom giving-ups.

I've had people I respect literally say "maybe we need to monitor all compute resources, Because AI".  Suggest we need to register all GPU and TPU chips so we Know What People Are Doing With Them.  Somehow add watermarks to all "AI" output.  Just nuts s... (read more)

3JBlack
The main problem with satire is Poe's Law. There are people sincerely advocating for more extreme positions in many respects, so it is difficult to write a satirical post that is distinguishable from those sincere positions even after being told that it is satire. In your case I had to get about 90% of the way through before suspecting that it was anything other than an enthusiastic but poorly written sincere post.
3the gears to ascension
seems like a very reasonable concern to me. how do you an anti-authority voluntarist information sharing pattern? it does seem to me that a key part of ai safety is going to be the ability to decide to retain strategic ambiguity. if anything, strongly safe ai should make it impossible for large monitoring networks to work, by construction!

I think the human has to have the power first, logically, for the AI to have the power.

Like, if we put a computer model in charge of our nuclear arsenal, I could see the potential for Bad Stuff.  Beyond all the movies we have of just humans being in charge of it (and the documented near catastrophic failures of said systems— which could have potentially made the Earth a Rough Place for Life for a while).  I just don't see us putting anything besides a human's finger on the button, as it were.
 

By definition, if the model kills everyone instea... (read more)

4gbear605
The feared outcome looks something like this: * A paperclip manufacturing company puts an AI in charge of optimizing its paperclip production. * The AI optimizes the factory and then realizes that it could make more paperclips by turning more factories into paperclips. To do that, it has to be in charge of those factories, and humans won’t let it do that. So it needs to take control of those factories by force, without humans being able to stop it. * The AI develops a super virus that will be an epidemic to wipe out humanity. * The AI contacts a genetics lab and pays for the lab to manufacture the virus (or worse, it hacks into the system and manufactures the virus). This is a thing that already could be done. * The genetics lab ships the virus, not realizing what it is, to a random human’s house and the human opens it. * The human is infected, they spreads it, humanity dies. * The AI creates lots and lots of paperclips. Obviously there’s a lot of missed steps there, but the key is that no one intentionally let the AI have control of anything important beyond connecting it to the internet. No human could or would have done all these steps, so it wasn’t seen as a risk, but the AI was able to and wanted to. Other dangerous potential leverage points for it are things like nanotechnology (luckily this hasn’t been as developed as quickly as feared), the power grid (a real concern, even with human hackers), and nuclear weapons (luckily not connected to the internet). Notably, these are all things that people on here are concerned about, so it’s not just concern about AI risk, but there are lots of ways that an AI could lever the internet into an existential threat to humanity and humans aren’t good at caring about security (partially because of the profit motive).

I haven't seen anything even close to a program that could say, prevent itself from being shut off— which is a popular thing to ruminate on of late (I read the paper that had the "press" maths =]).

What evidence is there that we are near (even within 50 years!) to achieving conscious programs, with their own will, and the power to affect it?  People are seriously contemplating programs sophisticated enough to intentionally lie to us.  Lying is a sentient concept if ever there was one!

Like, I've seen Ex Machina, and Terminator, and Electric Dreams,... (read more)

2[anonymous]
What evidence is there that we are near (even within 50 years!) to achieving conscious programs, with their own will, and the power to affect it?  People are seriously contemplating programs sophisticated enough to intentionally lie to us.  Lying is a sentient concept if ever there was one!   ChatGPT lies right now.  It's doing this because it has learned humans want a confident answer with logically correct but fake details over "I don't know".     Sure, it isn't aware it's lying, it's just predicting which string of text to create, and the one with bullshit in it it thinks has a higher score than the correct answer or "I don't know".   This is a mostly fixable problem but the architecture doesn't allow a system where we know it will never (or almost never) lie, we can only reduce the errors.   As for the rest - there have been enormous advances in the capability for DL/transformer based models in just the last few months.  This is nothing like the controllers for previous robotic arms, and none of your prior experiences or the history of robotics are relevant.     See: https://innermonologue.github.io/ and https://www.deepmind.com/blog/building-interactive-agents-in-video-game-worlds These are using techniques that both work pretty well, and I understand no production robotics system currently uses.

Oh, hey, I hadn't noticed I was getting downvoted.  Interesting!

I'm always willing to have true debate— or even false debate if it's good. =]

I'm just sarcasming in this one for fun and to express what I've already been expressing here lately in a different form or whatnot.

The strong proof is what I'm after, for sure, and more interesting/exciting to me than just bypassing the hard questions to rehash the same old same old.

Imagine what AI is going to show us about ourselves.  There is nothing bad or scary there, unless we find "the truth" bad and ... (read more)

Since we're anthropomorphizing[1] so much— how to we align humans?

We're worried about AI getting too powerful, but logically that means humans are getting too powerful, right?  Thus what we have to do to cover question 1 (how), regardless of question 2 (what), is control human behavior, correct?

How do we ensure that we churn out "good" humans?  Gods?  Laws?  Logic?  Communication?  Education?  This is not a new question per se, and I guess the scary thing is that, perhaps, it is impossible to ensure that literally ev... (read more)

3Matt Goldenberg
This is also a good question and one that's quite important! If humans get powerful enough to destroy the world before AI does, even more important. One key difference of course is that we can design the AI in a way we can't design ourselves.
2gbear605
One of the big fears with AI alignment is that the latter doesn't logically proceed from the first. If you're trying to create an AI that makes paperclips and then it kills all humans because it wasn't aligned (with any human's actual goals), it was powerful in a way that no human was. You do definitely need to worry about what goal the AI is aligned with, but even more important than that is ensuring that you can align an AI to any human's preferences, or else the worry about which goal is pointless.

Perspective is powerful.  As you say, one person's wonderful is another person's terrible.  Heck, maybe people even change their minds, right?  Oof!  "Yesterday I was feeling pretty hive-mindy, but today I'm digging being alone, quote unquote", as it were.

Maybe that's already the reality we inhabit.  Perhaps, we can change likes and dislikes on a whim, if we, um, like.

Holy molely! what if it turns out we chose all of this?!?  ARG!  What if this is the universe we want?!
-             -   ... (read more)

I guess what I'm getting at is that those tracks are jumping the gun, so to speak.

Like, what if the concept of alignment itself is the dangerous bit?  And I know I have seen this elsewhere, but it's usually in the form of "we shouldn't build an AI to prevent us from building an AI because duh, we just build that AI we were worried about"[1], and what I'm starting to wonder is, maybe the danger is when we realize that what we're talking about here is not "AI" or "them", but "humans" and "us".

We have CRISPR and other powerful tech that allow a single "m... (read more)

3[anonymous]
I guess what I'm getting at is that those tracks are jumping the gun, so to speak.   How so?  We have real AI systems right now we're trying to use in the real world.  We need an actionable design to make them safe right now. We also have enormously improved systems in prototype form - see Google's transformer based robotics papers like GaTo, variants on Palm, and others - that should be revolutionary as soon as they are developed enough for robotics control as integrated systems.  By revolutionary I mean they make the cost to program/deploy a robot to do a repetitive task a tiny fraction of what it is now, and they should obsolete a lot of human tasks.   So we need a plausible strategy to ensure they don't wreck their own equipment or cause large liabilities* in damage when they hit an edge case right now.   This isn't 50 years away, and it should be immediately revolutionary just as soon as all the pieces are in place for large scale use. *like killing human workers in the way of scoring slightly higher on a metric

Nice!  I read a few of the stories.  

This is more along the lines I was thinking.  One of the most fascinating aspects of AI is what it can show us about ourselves, and it seems like many people either think we have it all sorted out already, or that sorting it all out is inevitable.

Often (always?) the only "correct" answer to a question is "it depends", so thinking there's some silver bullet solution to be discovered for the preponderance of ponderance consciousness faces is, in my humble opinion, naive.

Like, how do we even assign meaning t... (read more)

6Netcentrica
Yes I agree that AI will show us a great deal about ourselves. For that reason I am interested in neurological differences in humans that AI might reflect and often include these in my short stories. In response to your last paragraph while most science fiction does portray enforced social order as bad I do not. I take the benevolent view of AI and see it as an aspect of the civilizing role of society along with its institutions and laws. Parents impose social order on their children with benevolent intent. As you have pointed out if we have alignment then “good” must be defined somewhere and that suggests a kind of “external” control over the individual but social norms and laws already represent this and we accept it. I think the problem stems from seeing AI as “other”, as something outside of our society, and I don’t see it that way. This is the theme of my novella “Metamorphosis And The Messenger” where AI does not represent the evolutionary process of speciation but of metamorphosis. The caterpillar and the butterfly are interdependent. However even while taking the benevolent side of the argument, the AI depicted in my stories sometimes do make decisions that are highly controversial as the last line of “The Ethics Tutor” suggests; “You don’t think it’s good for me to be in charge? Even if it’s good for you?” In my longer stories (novellas) the AI, now in full control of Earth and humanity’s future, make decisions of much greater consequence because “it’s good for you”. With regard to your suggestion that - “maybe that level of control is what we need over one another to be "safe" and is thus "good” - personally I  think that conclusion will  come to the majority in its own time due to social evolution. Currently the majority does not understand or accept that while previously we lived in an almost limitless world, that time is over. In a world with acknowledged limits, there cannot be the same degree of personal freedom. I use a kind of mashup of Buckmin

Thanks for the links!

I see more interesting things going on in the comments, as far as what I was wondering, than what is in the posts themselves, as the posts all seem to assume we've sorted out some super basic stuff that I don't know that humans have sorted out yet, such as if there is an objective "good", etc., which seem rather necessary things to suss before trying to hew to— be it for us or AIs we create.

I get the premise, and I think Science Fiction has done an admirable job of laying it all out for us already, and I guess I'm just a bit confused as to if we're writing fiction here or trying to be non-fictional?

6Matt Goldenberg
One way to break down the alignment problem is between "how do we align the AI" and "what should we align it to". It turns out we don't have agreement on the second question and don't know how to do the first. Even granted that we don't have an answer to the second question it ses prudentto be able to answer the first? By the time we answer the second it may be too late to answer the first.

How do we ensure that humans are not misaligned, so to speak?

The crux, to me, is that we've developed all kinds of tech that one person alone can use to basically wipe out everyone.  Perhaps I'm being overly optimistic (or pessimistic, depending on perspective), but no one can deny that the individual is currently the most powerful individuals have ever been, and there is no sign of that slowing down.

Mostly I believe this is because of information.

So the only real solution I can see, is some type of thought police, basically, be it for humans or AI.[1... (read more)

I don't see how we could have a "the" AGI.  Unlike humans, AI doesn't need to grow copies.  As soon as we have one, we have legion.  I don't think we (humanity as a collective) could manage one AI, let alone limitless numbers, right?  I mean this purely logistically, not even in a "could we control it" way.  We have a hard time agreeing on stuff, which is alluded to here with the "value" bit (forever a great concept to think about), so I don't have much hope for some kind of "all the governments in the world coming together to mana... (read more)

Ironically this still seems pretty pessimistic to me.  I'm glad to see something other than "AHHH!" though, so props for that.

I find it probably more prudent to worry about a massive solar flare, or an errant astral body collision, than to worry about "evil" AI taking a "sharp turn".

I put quotes around evil because I'm a fan of Nietzsche's thinking on the matter of good and evil.  Like, what, exactly are we saying we're "aligning" with?  Is there some universal concept of good?

Many people seem to dismiss blatant problems with the base premis... (read more)

3Zac Hatfield-Dodds
https://theprecipice.com/faq has a good summary of reasons to believe that human-created risks are much more likely than naturally-occuring risks like solar flares or asteroid or cometary impacts. If you'd like to read the book, which covers existential risks including from AI in more detail, I'm happy to buy you a copy. Specific to AI, Russel's Human Compatible and Christian's The Alignment Problem are both good too. More generally it sounds like you're missing the ideas of the orthogonality thesis and convergent instrumental goals.

So can you control emotion with rationality, or can't you?  "There's more fish in the sea" seems like classic emotion response control.  Or maybe it's that "emotion" vs. "feelings" idea— one you have control of, and one you do not?  Or it's the reaction you can control, not the emotion itself?

Having to "take a dream out behind the woodshed", as it were, is part of becoming a whole person I guess, but it's, basically by definition, not a pleasant experience.  I reckon that's by design, as sometimes, reality surprises you.

I think it boils... (read more)

I'm going to guess it's like mumble Resource Organization, something you'd like "farm out" some work to rather than have them on payroll and in meetings as it were.  Window Washers or Chimney Sweeps mayhap?

Just a guess, and I hope I'm not training an Evil AI by answering this question with what sprang to mind from the context.