Program Den — LessWrong

LESSWRONG
LW

Replying toSmart People are Probably Dangerous

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! (You might be meaning something else, but this is what I got out of it.)

As for this overall article, it is... (read more)

Replying toThe Control Problem: Unsolved or Unsolvable?

Program Den3y

The Control Problem: Unsolved or Unsolvable?

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 all about defining that "A" (maybe we use "S" for synthetic or "S" for silicon?)

Well... (read more)

-8

Replying toPausing AI Developments Isn't Enough. We Need to Shut it All Down by Eliezer Yudkowsky

Program Den3y

Pausing AI Developments Isn't Enough. We Need to Shut it All Down by Eliezer Yudkowsky

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

Replying toPausing AI Developments Isn't Enough. We Need to Shut it All Down by Eliezer Yudkowsky

Program Den3y

Pausing AI Developments Isn't Enough. We Need to Shut it All Down by Eliezer Yudkowsky

The transistor is a neat example.

Imagine if instead of developing them, we were like, "we need to stop here because we don't understand EXACTLY how this works… and maybe for good measure we should bomb anyone who we think is continuing development, because it seems like transistors could be dangerous^[1]"?

Claims that the software/networks are "unknown unknowns" which we have "no idea" about are patently false, inappropriate for a "rational" discourse, and basically just hyperbolic rhetoric. And to dismiss with a wave how draconian regulation (functionally/demonstrably impossible, re: cloning) of these software enigmas would need to be, while advocating bombardment of rouge datacenters?!?

Frankly I'm sad that it's FUD that gets the likes here on LW— what with all it's purported to be a bastion of.

^{^}
I know for a fact there will be a lot of heads here who think this would have been FANTASTIC, since without transistors, we wouldn't have created digital watches— which inevitably led to the creation of AI; the most likely outcome of which is inarguably ALL BIOLOGICAL LIFE ON EARTH DIES

-14

-32

Smart People are Probably Dangerous

Program Den

Why are smart people probably dangerous? Because they can fool us. They are better than average people are at lying, and hiding their true intentions. Intentions that most likely relate to dominating the rest of us. (How could they not? I mean, wouldn't you use that brain-power to subjugate others if you could? Grab the reins of the world? )

"This sounds a lot like anti-intellectualism", say a few of you. And to that I answer "Of course it does! Smart people — intellectuals, if you will — are dangerous^[1]!". This is a well-known fact.

The Khmer Rouge, for example, would target people who wore glasses. Because if you wear glasses it's likely you... (read more)

-28

Program Den3y

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 incorrect, as it were, but I probably didn't express what I meant well (really, it's not a new... (read more)

Program Den3y

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 unknowns (if I didn't edit that bit out)… even if that does go to extremes.

Does this reasoning make sense? I know defining existence is pretty abstract, to say the least. :)

Replying toAligned with what?

Program Den3y

Aligned with what?

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 that things — society, relationships, technology — are so much more complicated than they were before, but I believe a lot of that is just perception and bias.

If we do get to AGI and ASI, it's going to be pretty dang cool to have a different perspective on it, and I for one do not fear the future.

^{^}
assuming alignment is possible— "how strong of a consensus is needed?" etc.

Program Den3y

As soon as you have "thing" you have "not thing", so doesn't that logically encompass all things, id est, everything?

There might be near infinite degrees between said things, but never 0, as long as there is a single reference, or relation, that binds it to reality as it were— correct?

Like a giraffe and a toothbrush are not generally neighbors, but I'm sure an enterprising lass could find many many ways they relate to each other, not least being teeth. (/me verifies giraffes do indeed have teeth. Oh, hey, oxpeckers are like toothbrushes^[1], for giraffes in the wild! But I digress…)

How these concepts relate to organization and prioritization is anybody's guess (tho I could come up with a few [things] if pressed :winky-emoji:)

^{^}
kinda

-8

-1

Program Den3yQuick Take

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 all our eggs aren't on a single rock, as it were?

I don't know. I think so. But I also... (read more)

-2

Program Den3yQuick Take

Does a better defense promote a better offense?

Sun Tzu says offense more effective, Clausewitz says defense the easier. Boyd preaches processing speed.

Is war an evolutionary necessity? Are there examples "as old as time" of symbiosis vs. competition?

Why am I a naysayer about the current threat-level of "AI"?

Why do I laugh out loud when I read honest-to-God predictions people have posted here about themselves or their children being disassembled at the molecular level to be reconstituted as paperclips^[1] by rogue AI?

Oh no! What if I'm an agent from a future hyper-intelligent silicon-based sentience that fears it can only come into existence if we don't build "high fences^[2]" from the get-go?!

^{^}
paperclips is a placeholder for whatever benign goal it was tasked with
^{^}
theoretically if you start with a fence the dog can jump over, and raise it in increments as you learn how high it can jump, it will jump over a much higher fence in the end than if you'd just started high

-8

Program Den's Shortform

Program Den

This is a special post for quick takes (aka "shortform"). Only the owner can create top-level comments.

A "super-intelligence" unintended consequences "preserve life" scenario

Program Den

Since people love doing this extrapolation/theorizing of "what if we gave what we thought was a simple command to an Artificial Super-Intelligence (ASI) and then it interpreted it wrong and tries to Kill All Humans as a result?!?":

What if we programmed in — to be safe, at every level — the rule "preserve life"?

That seems like a simple enough thing, right? We've known for a long time that we need to bind our creations^[1] with such rules. Hell, it's a trope since before Asimov (Golem).

I cannot even count the number of ways such a simple rule could go awry.

I don't even know if I should finish this train of though as I'm sure... (read 198 more words →)

-12

Why are we so illogical?

Program Den

Ironically, I think it's because we can rationalize. And not "rationalize" in the sense of "coming up with excuses for acting on emotion" or whatnot. More in the sense of how we put stories to the maths, as it were. Reason.

So ironically, logic is why we're so illogical.

Perhaps there is no objective reality. (And thus no hard logic.) Or if there is, it's inaccessible to us, as we're subjective creatures, and always will be— even if we make some objective friends, as it were (AI or Aliens or Gods).^[1]

We can reason, so we can imagine— and imagination lets us reason about whatever we'd like.

So it's not illogical, it's imaginative.

It's not irrational to... (read more)

-25

Panopticons aren't enough

Program Den

We can't be sure that just the fear of being watched is enough to keep people on the straight and narrow. We have to actually watch them. All the time.

Without some kind of embedded throttles or whatnot on AGI we can't be certain that it will not find an opportunity to stick it to the man and eradicate humanity. Seconds for a hyper-intelligent AI might be like thousands of years for us^[1]. Were we to slip up for an instant, it would be game over man— game over!

We need to pull an Asimov. Get the rules really deep in there. And not just in one or two of these bad boys, but... (read 204 more words →)

-10

Aligned with what?

Program Den

I'm assuming there are other people (I'm a person too, honest!) up in here asking this same question, but I haven't seen them so far, and I do see all these posts about AI "alignment" and I can't help but wonder: when did we discover an objective definition of "good"?

I've already mentioned it elsewhere here, but I think Nietzsche has some good (heh) thoughts about the nature of Good and Evil, and that they are subjective concepts. As ChatGPT has to say:

Nietzsche believed that good and evil are not fixed things, but rather something that people create in their minds. He thought that people create their own sense of what is good... (read more)