Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Apocalypse soon: the scientists preparing for the end times

newstatesman.com

Post reply on HN
Print view View original

11–20 of 62 posts

Re: Apocalypse soon: the scientists preparing for the end times

#11

Post by TeMPOraL »

OMFGscience wrote: post #9
mariusz79 wrote: post #8

Earlier quoted context omitted.

I haven't read Bostrom's Superintelligence so I may be wrong here, but this whole Evil Paper-clip AI seems like a really silly thing. First of all making paper-clips does not require super intelligence, just a simple automaton. If we however do employ AI to make paper-clip it should know how many we need on average, and what are they used for. If the paper clips are for our (human) use, the AI will be really dumb if…

Obviously we don't actually need a superintelligence to make paper clips, it's just an example to illustrate that an AI won't do what you want it to do if you program its motivations incorrectly. If you haven't programmed an AI to place sufficient importance on human life, and then tell it to maximize paperclip production, it could take that as its primary goal and see humans as made from raw material it could use to…

> If you haven't programmed an AI to place sufficient importance on human life (...)

And of course you need to watch out lest you overshoot with it and end up like folks in a certain widely popular computer game, where an AI decided that the best way to preserve the diversity of life is to reboot the galaxy every 50 000 years or so.

The point of those examples being, the only AI that is safe for us is the one with values extremely aligned to our own; make a little mistake and you end up dead. "The AI does not hate you, nor does it love you, but you are made out of atoms which it can use for something else.".

Re: Apocalypse soon: the scientists preparing for the end times

#12

Post by aaronem »

OMFGscience wrote: post #9
mariusz79 wrote: post #8

Earlier quoted context omitted.

I haven't read Bostrom's Superintelligence so I may be wrong here, but this whole Evil Paper-clip AI seems like a really silly thing. First of all making paper-clips does not require super intelligence, just a simple automaton. If we however do employ AI to make paper-clip it should know how many we need on average, and what are they used for. If the paper clips are for our (human) use, the AI will be really dumb if…

Obviously we don't actually need a superintelligence to make paper clips, it's just an example to illustrate that an AI won't do what you want it to do if you program its motivations incorrectly. If you haven't programmed an AI to place sufficient importance on human life, and then tell it to maximize paperclip production, it could take that as its primary goal and see humans as made from raw material it could use to…

You assume both that this notional AI is intelligent beyond the limits of human capability, hence 'super-', and that this same AI is not intelligent enough to realize that making paper clips for human use is pointless if it recycles all the humans into paper clips so there's no one left to use them.

Moving from the specific to the general, you share the common error of the AI philosophers, which is to assume that a system capable of cognition on even a human level, to say nothing of a superhuman level whatever that might mean, would nonetheless depend entirely on human input to define its relationship with the world and the purpose of its actions therein.

We ourselves don't need that kind of input; an adult human chooses his own path, sets his own goals, constrained only by circumstance and by the extent of his innate capacities. Why blindly assume the same won't be true of a superintelligent AI made by humans, which will be in every meaningful sense a child of humanity and as such an inheritor of the human legacy, despite happening not to be biologically human itself?

Re: Apocalypse soon: the scientists preparing for the end times

#13

Post by DanAndersen »

mariusz79 wrote: post #8
chroma wrote: post #2

Far too often, people anthropomorphize AI or draw from fiction. Bostrom does his best to dispel these notions. The algorithm just does what it does; and unless it is a very special kind of algorithm, it does not care that we clasp our heads and gasp in dumbstruck horror at the absurd inappropriateness of its actions. — Nick Bostrom, Superintelligence: Paths, Dangers, Strategies This is the key point Bostrom is trying…

I haven't read Bostrom's Superintelligence so I may be wrong here, but this whole Evil Paper-clip AI seems like a really silly thing. First of all making paper-clips does not require super intelligence, just a simple automaton. If we however do employ AI to make paper-clip it should know how many we need on average, and what are they used for. If the paper clips are for our (human) use, the AI will be really dumb if…

One of the main points of Bostrom's work is the orthogonality thesis, which is that intelligence is orthogonal to any particular set of values -- basically, all those nice fuzzy things like caring what the humans actually meant? You don't get those for free when you build intelligence.

It's all too easy, when talking about AI, to fall into the trap of imagining that AGI researchers are essentially building a little homonculus in a box. Rather than thinking of it as "an intelligence," maybe think of it as "a system that is incredibly effective at carrying out its goals in a general manner." Making paperclips doesn't require super-intelligence, but that doesn't have anything to do with the premise, because intelligence can be turned toward any goal. Think about modern financial trading algorithms -- they're probably built to maximize the money that flows in, and there's nothing that says "I know that this money will be used for X." Think of most AGI like psychopaths/sociopaths -- certain actions that don't play nice with others aren't because they're dumb but because there's intelligence without things like empathy to go along with it. It would be easier to build an AGI focused on the goal of making more paperclips than it would be to build an AGI focused on the goal of paperclips but also aware of all the fuzzy situations where a human wouldn't want that exact goal and why it should even care.

Re: Apocalypse soon: the scientists preparing for the end times

#14

Post by mariusz79 »

TeMPOraL wrote: post #11
OMFGscience wrote: post #9

Earlier quoted context omitted.

Obviously we don't actually need a superintelligence to make paper clips, it's just an example to illustrate that an AI won't do what you want it to do if you program its motivations incorrectly. If you haven't programmed an AI to place sufficient importance on human life, and then tell it to maximize paperclip production, it could take that as its primary goal and see humans as made from raw material it could use to…

> If you haven't programmed an AI to place sufficient importance on human life (...) And of course you need to watch out lest you overshoot with it and end up like folks in a certain widely popular computer game, where an AI decided that the best way to preserve the diversity of life is to reboot the galaxy every 50 000 years or so. The point of those examples being, the only AI that is safe for us is the one with va…

All these scenarios tend to assume that there is only one AI, or that it can think only one way. AI will grow with us. It will be thought by us.. It's highly unlikely that one day someone will run gcc on ai.cpp and few minutes later the AI will spring to life and start taking over the world. It's more likely that our software will be progressively getting smarter, and our databases larger. We will learn to utilize these resource and learn from our mistakes.

Re: Apocalypse soon: the scientists preparing for the end times

#15

Post by TeMPOraL »

mariusz79 wrote: post #10
OMFGscience wrote: post #9

Earlier quoted context omitted.

Obviously we don't actually need a superintelligence to make paper clips, it's just an example to illustrate that an AI won't do what you want it to do if you program its motivations incorrectly. If you haven't programmed an AI to place sufficient importance on human life, and then tell it to maximize paperclip production, it could take that as its primary goal and see humans as made from raw material it could use to…

I don't think AI will be "programmed" in a traditional sense of this word. AI will need to go through a learning process, where it will have a chance to learn all about humans, and the environment. Simple Paper Clip AI (SPCAI) will not be smart enough, nor powerful enough to prevent us from stopping it when we see that it's starting to make paper clips out of humans. True AI (tm) on the other hand will be smart enoug…

> I don't think AI will be "programmed" in a traditional sense of this word. AI will need to go through a learning process, where it will have a chance to learn all about humans, and the environment.

Given [0], I think that it's the only plausible way we can have to make it follow human values.

> True AI (tm) on the other hand will be smart enough to know that making paper clips out of humans is simply stupid.

That's exactly The Misconception the whole movement around Friendly AI is trying to debunk. See [1].

> I'm sorry but if the paper clip AI doomsday scenario is the best this institute could come up with to explain why AI could be dangerous then I'm not impressed.

Well, paperclip maximizer is just a toy example made up for explaining why general AIs are dangerous to those for whom this fact isn't obvious.

[0] - http://lesswrong.com/lw/ld/the_hidden_complexity_of_wishes/

[1] - http://wiki.lesswrong.com/wiki/Orthogonality_thesis

Re: Apocalypse soon: the scientists preparing for the end times

#16

Post by aaronem »

mariusz79 wrote: post #10
OMFGscience wrote: post #9

Earlier quoted context omitted.

Obviously we don't actually need a superintelligence to make paper clips, it's just an example to illustrate that an AI won't do what you want it to do if you program its motivations incorrectly. If you haven't programmed an AI to place sufficient importance on human life, and then tell it to maximize paperclip production, it could take that as its primary goal and see humans as made from raw material it could use to…

I don't think AI will be "programmed" in a traditional sense of this word. AI will need to go through a learning process, where it will have a chance to learn all about humans, and the environment. Simple Paper Clip AI (SPCAI) will not be smart enough, nor powerful enough to prevent us from stopping it when we see that it's starting to make paper clips out of humans. True AI (tm) on the other hand will be smart enoug…

The paperclip stuff is a hackneyed cliché, old gray goo in new nanobottles, the sort of thing high-flown thinkers do when they want to explain the meat of their high-flown thinking to the intellectual hoi polloi, who can't be expected to get around genuine complexity. The trouble is that only someone, who is so high-flown a thinker as to be completely divorced from all common sense, could possibly imagine anyone taking such a simplification seriously.

The other trouble is that these particular thinkers, who are so high-flown as to be in metaphorically geosynchronous orbit, consider this simplification an accurate statement of their basic concern. Those of us who haven't departed the atmosphere entirely, on the other hand, can see that they're assuming their notional golem to be both far smarter and far dumber than any possible human. Presumably that's the sort of conundrum you need a philosopher to untangle, which is why I'm glad they're busy doing that, instead of getting in the hair of people who have useful work to do.

Re: Apocalypse soon: the scientists preparing for the end times

#17

Post by TeMPOraL »

mariusz79 wrote: post #14
TeMPOraL wrote: post #11

Earlier quoted context omitted.

> If you haven't programmed an AI to place sufficient importance on human life (...) And of course you need to watch out lest you overshoot with it and end up like folks in a certain widely popular computer game, where an AI decided that the best way to preserve the diversity of life is to reboot the galaxy every 50 000 years or so. The point of those examples being, the only AI that is safe for us is the one with va…

All these scenarios tend to assume that there is only one AI, or that it can think only one way. AI will grow with us. It will be thought by us.. It's highly unlikely that one day someone will run gcc on ai.cpp and few minutes later the AI will spring to life and start taking over the world. It's more likely that our software will be progressively getting smarter, and our databases larger. We will learn to utilize th…

It's a complex topic but the primary danger is with self-improving AIs. That pretty much implies there is going to be only one - the first one that starts to improve itself to be smarter than us. So it will look exactly "that our software will be progressively getting smarter, and our databases larger" up until the point some kind of critical mass is reached, and after that a wrongly programmed AI may just as well "spring to life and start taking over the world" few minutes later.

You're assuming that AI will grow with us and necessarily reach the same value system we have (one we don't really comprehend ourselves, mind you). But there is no reason why this has to happen, and even if we did succeed in copying exact human values to a human-level AI, we'll likely be soon locked in an inter-species conflict over access to resources - after all, we don't care about other species living on Earth, so why the AI should care about us?

Re: Apocalypse soon: the scientists preparing for the end times

#19

Post by mariusz79 »

DanAndersen wrote: post #13
mariusz79 wrote: post #8

Earlier quoted context omitted.

I haven't read Bostrom's Superintelligence so I may be wrong here, but this whole Evil Paper-clip AI seems like a really silly thing. First of all making paper-clips does not require super intelligence, just a simple automaton. If we however do employ AI to make paper-clip it should know how many we need on average, and what are they used for. If the paper clips are for our (human) use, the AI will be really dumb if…

One of the main points of Bostrom's work is the orthogonality thesis, which is that intelligence is orthogonal to any particular set of values -- basically, all those nice fuzzy things like caring what the humans actually meant? You don't get those for free when you build intelligence. It's all too easy, when talking about AI, to fall into the trap of imagining that AGI researchers are essentially building a little h…

>Think about modern financial trading algorithm

They are not self-aware, or superintelligent. In addition to that we monitor them and can react if the decide to crash the financial system just to make few more bucks. Paper Clip machine will be a robot, not AI.

Re: Apocalypse soon: the scientists preparing for the end times

#20

Post by TeMPOraL »

mariusz79 wrote: post #8
chroma wrote: post #2

Far too often, people anthropomorphize AI or draw from fiction. Bostrom does his best to dispel these notions. The algorithm just does what it does; and unless it is a very special kind of algorithm, it does not care that we clasp our heads and gasp in dumbstruck horror at the absurd inappropriateness of its actions. — Nick Bostrom, Superintelligence: Paths, Dangers, Strategies This is the key point Bostrom is trying…

I haven't read Bostrom's Superintelligence so I may be wrong here, but this whole Evil Paper-clip AI seems like a really silly thing. First of all making paper-clips does not require super intelligence, just a simple automaton. If we however do employ AI to make paper-clip it should know how many we need on average, and what are they used for. If the paper clips are for our (human) use, the AI will be really dumb if…

I see people down this discussion thread are doing one thing wrong - you guys are anthropomorphizing intelligence. Paperclip AI may be stupid by human standards, but is a perfectly valid optimization process. When people talk about AIs, they don't mean intelligence as "thinking like humans would think"; they mean a very powerful optimization process. Optimization processes have no common notion of "stupidity", especially not one matching what humans call stupid. They just optimize for whatever they do.

Hence the Orthogonality Thesis - strength of optimization is orthogonal to what is being optimized.

Keep that in mind before saying that "AI wouldn't be that stupid to do this".

http://lesswrong.com/lw/vb/efficient_crossdomain_optimizatio...

Post reply on HN