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

Artificial Intelligence Is Already Weirdly Inhuman

nautil.us

Post reply on HN
Print view View original

61–70 of 84 posts

Re: Artificial Intelligence Is Already Weirdly Inhuman

#61

Post by teddyh »

chriswarbo wrote: post #23
white-flame wrote: post #15

I do have my doubts that plain neural networks will ever be able to achieve conceptual understanding. I have an affinity for classical, rational AI in that you can correct it and it will take that correction and instantly apply it to is knowledge base. It can also explain why it came to a conclusion. (though obviously this style has its very real limitations) NNs and other current statistical/connectionist approaches…

I'm a firm believer that it's a mistake to ask machines to do X in the hope that they'll do Y. We can't train an ANN to classify images then ask it to explain its reasoning; that's not the task we trained it for! How might we train an ANN to explain its reasoning? One approach would be to learn programs: have the ANN write programs which classify images. Then we have a classifier (run the program) and an explanation…

Even humans can’t explain their own reasoning. We can only rationalize our intuitive decisions after the fact, but it’s pure hokum – all decisions are made intuitively using no rational thought whatsoever, only afterward can we make up rationalizations for it.

It follows that it should be perfectly possible for an A.I. to do this, too.

(Edit: I now realize that this rationalization process was theorized by Douglas Adams in Dirk Gently’s Holistic Detective Agency, as described by Wikipedia:

“The story also mocks the corporate world with [the software] package called Reason, which inverts the idea of a decision-making program. Instead of proceeding from ideas and logic to a decision, it takes a decision that has already been made and creates a reasoned justification for it.”

­— https://en.wikipedia.org/wiki/Dirk_Gently%27s_Holistic_Detec... )

Re: Artificial Intelligence Is Already Weirdly Inhuman

#63

Post by ectoplasm »

teddyh wrote: post #61
chriswarbo wrote: post #23

Earlier quoted context omitted.

I'm a firm believer that it's a mistake to ask machines to do X in the hope that they'll do Y. We can't train an ANN to classify images then ask it to explain its reasoning; that's not the task we trained it for! How might we train an ANN to explain its reasoning? One approach would be to learn programs: have the ANN write programs which classify images. Then we have a classifier (run the program) and an explanation…

Even humans can’t explain their own reasoning. We can only rationalize our intuitive decisions after the fact, but it’s pure hokum – all decisions are made intuitively using no rational thought whatsoever, only afterward can we make up rationalizations for it. It follows that it should be perfectly possible for an A.I. to do this, too. (Edit: I now realize that this rationalization process was theorized by Douglas Ad…

Let's say you want as much money as you can get. This is probably not rational. Now let's say you have a choice of being given $5 or $10, which do you choose? Why was that not a rational choice? Because it's predicated on an irrational desire?

Re: Artificial Intelligence Is Already Weirdly Inhuman

#64

Post by simonh »

joshmarinacci wrote: post #2

I don't find this surprising. In fact, I would find the opposite surprising. It would be very surprising if AI was human-like. Human intelligence is designed to power a human body, with fingers of a certain length and eyes of a certain stereo field of view. I don't think we will ever develop a human like AI until we give it a human like body to live in.

> I don't think we will ever develop a human like AI until we give it a human like body to live in.

Perhaps, but also it doesn't automatically follow that if they look like us they must think like us, whatever Hollywood says.

Re: Artificial Intelligence Is Already Weirdly Inhuman

#66

Post by minikomi »

idlewords wrote: post #21
noir_lord wrote: post #5

We saw this in Chess engines about 20 years back (when they started getting seriously strong) they play Chess incredibly well but looks very little like what a human playing does. It was fascinating to watch the changes in chess theory through that period as the machines validated or invalidated concepts and ideas that GM's had posited but been unable to prove one way or the other. John Speelman wrote an intro to The…

This is particularly evident in endgames. Forced mates have been discovered that require hundreds of apparently random and pointless moves, until suddenly the king is cornered and mated. There's a nice discussion of some of these on Krabbé's chess blog: http://timkr.home.xs4all.nl/chess/perfect.htm

Wow.. do the games change when it's computer vs human as opposed to computer vs computer?

Re: Artificial Intelligence Is Already Weirdly Inhuman

#67

Post by eru »

Quanticles wrote: post #13

This article relies on carefully constructed images that maximize one particular outcome by summing up lots of small errors into it. For it to work, the pixels have to be very accurately tweaked. If the tweaks were off by one pixel, the whole thing would fall apart. The assumption is that this cannot be done to a person. But there is no way to put in a pixel-level "exploit of sorts" into a person to test that theory.…

From the article:

Such screwy results can’t be explained away as hiccups in individual computer systems, because examples that send one system off its rails will do the same to another. After he read “Deep Neural Networks Are Easily Fooled,” Dileep George, cofounder of the AI research firm Vicarious, was curious to see how a different neural net would respond. On his iPhone, he happened to have a now-discontinued app called Spotter, a neural net that identifies objects. He pointed it at the wavy lines that Clune’s network had called a starfish. “The phone says it’s a starfish,” George says.

Spotter was examining a photo that differed from the original in many ways: George’s picture was taken under different lighting conditions and at a different angle, and included some pixels in the surrounding paper that weren’t part of the example itself. Yet the neural net produced the same extraterrestrial-sounding interpretation. “That was pretty interesting,” George says. “It means this finding is pretty robust.”

In fact, the researchers involved in the “starfish” and “ostrich” papers made sure their fooling images succeeded with more than one system. “An example generated for one model is often misclassified by other models, even when they have different architectures,” or were using different data sets, wrote Christian Szegedy, of Google, and his colleagues.4 “It means that these neural networks all kind of agree what a school bus looks like,” Clune says. “And what they think a school bus looks like includes many things that no person would say is a school bus. That really surprised a lot of people.”

Re: Artificial Intelligence Is Already Weirdly Inhuman

#68

Post by eru »

kordless wrote: post #43

What if you showed the algorithm/network/whatever itself? You could 'take a picture of it' and then train it to know that's itself, which would then change what it looks like. Keep doing that until it doesn't change or you fail trying.

You could get into a loop. Though, what are you trying to accomplish here?

Re: Artificial Intelligence Is Already Weirdly Inhuman

#69

Post by teddyh »

ectoplasm wrote: post #63
teddyh wrote: post #61

Earlier quoted context omitted.

Even humans can’t explain their own reasoning. We can only rationalize our intuitive decisions after the fact, but it’s pure hokum – all decisions are made intuitively using no rational thought whatsoever, only afterward can we make up rationalizations for it. It follows that it should be perfectly possible for an A.I. to do this, too. (Edit: I now realize that this rationalization process was theorized by Douglas Ad…

Let's say you want as much money as you can get. This is probably not rational. Now let's say you have a choice of being given $5 or $10, which do you choose? Why was that not a rational choice? Because it's predicated on an irrational desire?

No, that is not what I meant – the choice itself is not made rationally, even though a theoretical rational actor might have made the same choice.

The most we humans can do it to make an intuitive choice, allow the post-hoc rationalization to occur and then check its rationality by analyzing its logic. If the logic is bad, we go back and try another intuitive choice.

Re: Artificial Intelligence Is Already Weirdly Inhuman

#70

Post by minthd »

white-flame wrote: post #15

I do have my doubts that plain neural networks will ever be able to achieve conceptual understanding. I have an affinity for classical, rational AI in that you can correct it and it will take that correction and instantly apply it to is knowledge base. It can also explain why it came to a conclusion. (though obviously this style has its very real limitations) NNs and other current statistical/connectionist approaches…

>>> Neural net ... "I dunno, it feels like it's an ostrich"

I don't think this applies to deep-learning. Because with deep learning , the lower layers will will say "this has long neck", "this has legs" , etc... and that will help the higher layers to to understand "it's an ostrich".

Post reply on HN