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

Model-Free, Model-Based, and General Intelligence [pdf]

ijcai.org

Post reply on HN
Print view View original

11–20 of 32 posts

Re: Model-Free, Model-Based, and General Intelligence [pdf]

#11

Post by nutjob2 »

nmca wrote: post #8
nutjob2 wrote: post #5

It seems the fundamental problem with bottom up/learning AI is that it is opaque and essentially unknowable. I find it all very hackish. We can develop systems now which we can test and seem to work, but we don't know exactly why they work (eg: what parts of the training data they are promoting) and when (or why) they will fail. The effectiveness of adversarial inputs to trained vision systems illustrates this. Zoom…

One approach being considered is "AI Safety Via Debate"[0], which hopes to prevent deception by carefully constructing games in which a superhuman agent's best strategy is honesty. Note that this is the goal; much work to be done! [0] https://arxiv.org/abs/1805.00899

Unfortunatley being dishonest or evil is just one example. Arguably the AI can develop new classes of deviancy, abuse or maladaptation that we haven't conceptualized yet. We supersize the ability, surely we supersize the problems.

It leads to a scary question: what does a superhuman AI really want?

Re: Model-Free, Model-Based, and General Intelligence [pdf]

#12

Post by eli_gottlieb »

algorias wrote: post #2

I attended this talk at IJCAI, and I must say that the whole system 1 / system 2 analogy rubbed me the wrong way. A solver for e.g. 3-SAT is general only in a very narrow sense, namely that an entire class of problems can be reduced to the specific problem it solves. However, the solver itself is not doing the reducing, rather it is being spoon-fed instances generated by somebody, and that somebody is doing all the h…

>I attended this talk at IJCAI, and I must say that the whole system 1 / system 2 analogy rubbed me the wrong way.

It immediately rubs me in the wrong way because dual process theories of the brain are wrong and outmoded and need to die out of the public consciousness now!

I am muttering angrily in cognitive science!

Re: Model-Free, Model-Based, and General Intelligence [pdf]

#13

Post by naasking »

sophistication wrote: post #7
algorias wrote: post #2

I attended this talk at IJCAI, and I must say that the whole system 1 / system 2 analogy rubbed me the wrong way. A solver for e.g. 3-SAT is general only in a very narrow sense, namely that an entire class of problems can be reduced to the specific problem it solves. However, the solver itself is not doing the reducing, rather it is being spoon-fed instances generated by somebody, and that somebody is doing all the h…

Not to mention that there is no conclusive evidence of the dual process theory yet, see for example this experimental study finding that logical "type 2" answers are actually typically faster and that intuitive "type 1" answers are typically also logical: https://www.sciencedirect.com/science/article/pii/S001002771...

> Not to mention that there is no conclusive evidence of the dual process theory yet

Define "conclusive". There is considerable evidence for this dual reasoning mode.

As for your study, system 1 thinking is not inherently illogical. In fact, it's necessarily logical otherwise it would be maladaptive. The point is that it's logical in a "lossy" way that sometimes excludes pertinent information for speed of response, and so sometimes goes wildly wrong.

Re: Model-Free, Model-Based, and General Intelligence [pdf]

#14

Post by naasking »

eli_gottlieb wrote: post #12
algorias wrote: post #2

I attended this talk at IJCAI, and I must say that the whole system 1 / system 2 analogy rubbed me the wrong way. A solver for e.g. 3-SAT is general only in a very narrow sense, namely that an entire class of problems can be reduced to the specific problem it solves. However, the solver itself is not doing the reducing, rather it is being spoon-fed instances generated by somebody, and that somebody is doing all the h…

>I attended this talk at IJCAI, and I must say that the whole system 1 / system 2 analogy rubbed me the wrong way. It immediately rubs me in the wrong way because dual process theories of the brain are wrong and outmoded and need to die out of the public consciousness now! I am muttering angrily in cognitive science!

What's the current theory in vogue?

Re: Model-Free, Model-Based, and General Intelligence [pdf]

#15

Post by vinceguidry »

nutjob2 wrote: post #4
algorias wrote: post #2

I attended this talk at IJCAI, and I must say that the whole system 1 / system 2 analogy rubbed me the wrong way. A solver for e.g. 3-SAT is general only in a very narrow sense, namely that an entire class of problems can be reduced to the specific problem it solves. However, the solver itself is not doing the reducing, rather it is being spoon-fed instances generated by somebody, and that somebody is doing all the h…

I'm curious to know what your definition of "actually thinking" is. I suspect your argument is circular.

All definitions of things get circular at some point. What defines a chair? The set of criteria you come up with to divide chairs from other things has to invariably turn in on itself, as the hilarious exercise to define a sandwich illustrates. All identity is ultimately an illusion.

In other words, the more division you create in the world, the more 'specialness' you create. And in the immortal words of Syndrome, when everyone's special, no one is.

With a fine enough definition of thought, anything can fit the definition.

Re: Model-Free, Model-Based, and General Intelligence [pdf]

#16

Post by Nasrudith »

nutjob2 wrote: post #11
nmca wrote: post #8

Earlier quoted context omitted.

One approach being considered is "AI Safety Via Debate"[0], which hopes to prevent deception by carefully constructing games in which a superhuman agent's best strategy is honesty. Note that this is the goal; much work to be done! [0] https://arxiv.org/abs/1805.00899

Unfortunatley being dishonest or evil is just one example. Arguably the AI can develop new classes of deviancy, abuse or maladaptation that we haven't conceptualized yet. We supersize the ability, surely we supersize the problems. It leads to a scary question: what does a superhuman AI really want?

To be fair a HFT agent can count as superhuman AI technically. Wanting isn't a thing that applies yet to actual AI and there is no special sauce that indicates advancement beyond neuron scale. Barring directives and assuming "grown" what it wants can be utterly peripheral to rationality and likely based on what it is taught - internationally or not. Look at how society preaches honesty from a young age and then starts teaching lying again by rewarding it. The real lesson is the spartan one on stealing- don't get caught. It may not be intended but it is the result.

Re: Model-Free, Model-Based, and General Intelligence [pdf]

#17

Post by Nasrudith »

nmca wrote: post #8
nutjob2 wrote: post #5

It seems the fundamental problem with bottom up/learning AI is that it is opaque and essentially unknowable. I find it all very hackish. We can develop systems now which we can test and seem to work, but we don't know exactly why they work (eg: what parts of the training data they are promoting) and when (or why) they will fail. The effectiveness of adversarial inputs to trained vision systems illustrates this. Zoom…

One approach being considered is "AI Safety Via Debate"[0], which hopes to prevent deception by carefully constructing games in which a superhuman agent's best strategy is honesty. Note that this is the goal; much work to be done! [0] https://arxiv.org/abs/1805.00899

Forget AIs - we need this for humans to design legal and administrative systems.

I have pondered if it would be a workable field to have incentive based design in a formalized way to ensure that even a complete sociopath would find acting in a beneficial way the best option.

Re: Model-Free, Model-Based, and General Intelligence [pdf]

#18

Post by eli_gottlieb »

naasking wrote: post #14
eli_gottlieb wrote: post #12

Earlier quoted context omitted.

>I attended this talk at IJCAI, and I must say that the whole system 1 / system 2 analogy rubbed me the wrong way. It immediately rubs me in the wrong way because dual process theories of the brain are wrong and outmoded and need to die out of the public consciousness now! I am muttering angrily in cognitive science!

What's the current theory in vogue?

Bayesian brain theories are more "in vogue", along with various other theories saying that the brain does some forms of statistical and causal learning and inference.

Re: Model-Free, Model-Based, and General Intelligence [pdf]

#19

Post by naasking »

eli_gottlieb wrote: post #18
naasking wrote: post #14

Earlier quoted context omitted.

What's the current theory in vogue?

Bayesian brain theories are more "in vogue", along with various other theories saying that the brain does some forms of statistical and causal learning and inference.

Sure, that seems reasonable. But I don't see why statistical and causal learning and inference really preclude the evolution of a system 1/2 dualism.

Re: Model-Free, Model-Based, and General Intelligence [pdf]

#20

Post by dj-wonk »

algorias wrote: post #2

I attended this talk at IJCAI, and I must say that the whole system 1 / system 2 analogy rubbed me the wrong way. A solver for e.g. 3-SAT is general only in a very narrow sense, namely that an entire class of problems can be reduced to the specific problem it solves. However, the solver itself is not doing the reducing, rather it is being spoon-fed instances generated by somebody, and that somebody is doing all the h…

Yes, I know what you mean. In my opinion, the connection to the System 1 / System 2 theories did not add much depth to the paper. I think the intended purpose was to bolster the argument that both learners and solvers (operating in different ways) are both useful forms of intelligence. However, this point can be made in other ways as well.

In any case, I look forward to more scholarship and experimentation at the intersection of these topics.

Post reply on HN