Self-supervised learning: The dark matter of intelligence • Hacker News Board

Re: Self-supervised learning: The dark matter of intelligence

#61

Post by drdeca » Fri, Mar 12, 2021, 8:42 PM UTC

TheOtherHobbes wrote: post #51

drdeca wrote: post #25

Earlier quoted context omitted.

So it can handle the strategy of making sure no one else makes one which is more harmful. :P But as a serious answer: of course, there is no major economic use of trying to make sure it has an internal subjective experience, but that’s not what people are aiming for when referring to AGI. The goal is that it be able to accomplish general tasks and goals. Like, what can you do with it? Everything you can do at all. Th…

AGI definitions are incredibly fuzzy and agency reliably seems to be confused with intelligence. The fundamental problem is whether AGI is outer-directed or inner-directed - i.e. whether it sets its own goals, or whether you tell it what to do and it improvises a solution. AGI is most useful when it's outer-directed with limited agency but some improvisational autonomy. You can give that kind of AGI specific problems…

Can you elaborate on the outer-directed vs inner-directed distinction (or link to something else which does, if that would be more convenient)?

I'm not quite sure what you mean by "sets its own goals" (for "inner-directed"). I assume you don't mean "modifies its own goals" (as, why would that help further its current goals?), but I'm not sure what it would mean. Maybe you mean like, if it acquires goals and preferences in the way that humans do, with shifting likes and dislikes that aren't consistent across time? Yes, that would certainly be quite dangerous (unless the AGI was via like, just emulating a human's mind, which might not be so dangerous, in which case only somewhat dangerous).

I believe I see your point in the safety features in having it receive a specific short term task, achieve the task, and then stop. Once it stops, it isn't doing things anymore, and therefore isn't causing more problems. But it seems like it might be difficult to define that precisely? Like, suppose it takes some actions for a period of time, but complicated and anticipated-by-it-but-not-by-us consequences of its actions continue substantially after it has stopped?

Re: Self-supervised learning: The dark matter of intelligence

#62

Post by _y5hn » Fri, Mar 12, 2021, 9:25 PM UTC

TheOtherHobbes wrote: post #48

epidemian wrote: post #14

Earlier quoted context omitted.

on one hand i agree with what you're saying. we humans have done terrible stuff like wars, genocides, famines, destruction of ecosystems, extinction of entire species, etc. and that's only the things we did more or less deliberately. we might cause our own extermination or a mass extinction event "by mistake", and we don't even understand how basic parts of our minds work. but all of that being said, i think it's als…

This already applies to corporations. AI is just the fruiting body of something that has already happened.

Corporate intelligence are still people, abiding laws and regulations for people.

Re: Self-supervised learning: The dark matter of intelligence

#63

Post by _y5hn » Fri, Mar 12, 2021, 9:27 PM UTC

sailingparrot wrote: post #11

montenegrohugo wrote: post #2

One of the problems we have to be conscious about with self supervised learning is that the already existing problem of transparency and understandability gets worsened by orders of magnitude. If current billion parameter models are opaque, the result of SSL is, or will be, the equivalent of a black hole. How do you understand what the model has learned? Why has it learned that way? What things could have possible go…

Not sure I see your point. How is it harder to understand a model that was trained to predict which two images crops come from the same source image (a la contrastive loss for example), than a model that was trained to predict which class an image belongs to?

What's the algorithm?

Re: Self-supervised learning: The dark matter of intelligence

#64

Post by _y5hn » Fri, Mar 12, 2021, 9:33 PM UTC

elcomet wrote: post #58

Reebz wrote: post #54

Earlier quoted context omitted.

That's ok, but based on your example, how would a human apply an algorithm that it can't determine why it worked? We're not talking about "Not Hotdog" here. Application of a model in a real-world at-scale scenario is a lot more than running inference and walking away. At a bank credit decisions are evaluated by humans, frequently and often. These reviews are conducted in the forms of sampling audits, control processe…

I'm not sure I understand your comment. Bank credits are auditable, because there are some precise algorithm around them. Humans created the algorithm specifically so that it is interpretable. Then they must apply it the same way to everybody. They can't just say "oh, I think this person is more likely to actually reimburse, I play golf with him and I trust him !" This is a specific case where no black box will ever…

There's incentive to use complex black boxes everywhere, if more profitable.

Re: Self-supervised learning: The dark matter of intelligence

#65

Post by _y5hn » Fri, Mar 12, 2021, 9:34 PM UTC

TheOtherHobbes wrote: post #50

elcomet wrote: post #43

Earlier quoted context omitted.

I don't really agree with you. > If you were rejected by a bank for a home loan, you would want to know why your creditworthiness wasn’t evaluated positively (and banks must explain precisely why to regulators). This is why we don't use humans to evaluate credits, but precise algorithms. Humans are just applying the algorithms, they are not evaluating themselves with their gut feeling. I don't see why this would chan…

Isn't it interesting that an industry like banking, built on those beautiful, precise algorithms, blows up so regularly?

You're really thinking of finance. Pure banking is solved long ago.

Re: Self-supervised learning: The dark matter of intelligence

#66

Post by _y5hn » Fri, Mar 12, 2021, 9:39 PM UTC

visarga wrote: post #24

Reebz wrote: post #13

State of the art performance is being broken in multiple fields rapidly these days. However, AI explainability has a long way to go. Scaling opaqueness makes this problem worse. Fine tuning labels black-box style is a terrifying concept to most who are working in fields where great risk must be managed to avoid unintended and disparate impact. Facebook making an oopsies suggesting my friends face in a photo instead o…

High risk models should work with humans in the loop, not autonomous.

A sufficiently complex algo black box could fool the people.

Re: Self-supervised learning: The dark matter of intelligence

#67

Post by candiodari » Fri, Mar 12, 2021, 10:52 PM UTC

suifbwish wrote: post #15

tasogare wrote: post #9

Earlier quoted context omitted.

> Sure, but humans are a relatively known entity. We don’t know how brain works, why sleep exist, most of humans cultures and languages are not documented, hundreds if not thousands of psychological and medical things are unknown, etc. Machines and their applications are a few more magnitudes more understood than any human matter, by the sheer fact we created them. Their complexity is ridiculously low in comparison t…

That was not the original point. Humans are relatively predictable whether we understand how the brain works exactly. An AI model isn’t an actual intelligence in the normal use of the word. It’s a functional fragment that is able to emulate the ability to absorb a pattern of information for repetitive conditional recall in future processes. Until a researcher has had ALOT of time spent on observing the limits db part…

Luckily we never have unforeseen behaviors with people that we then have to react strongly to after the fact ... We like to pretend that's true, but really, it isn't. Governments are built around the principle that single individuals and even small to medium groups can't be trusted to react reasonably, something that played out in human history again and again.

How many people have been in US prisons again? Oh right, about 3%. Clearly a high percentage of these people did something both unexpected that seriously damaged others.

So this is not a real difference between AIs and humans. One might even say, not a single AI has been convicted yet, so it might not be true for them. For humans, serious, bad, violent, illegal, even when totally irrational, ... behaviors are very common indeed.

(and frankly, if there ever is a true Human AI conflict, not allowing any kind of errors for AIs seems to me a strong contender for the casus belli)

Re: Self-supervised learning: The dark matter of intelligence

#68

Post by elcomet » Fri, Mar 12, 2021, 11:23 PM UTC

_y5hn wrote: post #64

elcomet wrote: post #58

Earlier quoted context omitted.

I'm not sure I understand your comment. Bank credits are auditable, because there are some precise algorithm around them. Humans created the algorithm specifically so that it is interpretable. Then they must apply it the same way to everybody. They can't just say "oh, I think this person is more likely to actually reimburse, I play golf with him and I trust him !" This is a specific case where no black box will ever…

There's incentive to use complex black boxes everywhere, if more profitable.

Of course, and my point is that it's perfectly fine, and even desirable, as better models lead to better outcomes.

Of course, for cases where explainability is needed, either required by law (such as banking), or by common sense, then black boxes will not be deployed.

Re: Self-supervised learning: The dark matter of intelligence

#69

Post by Forge36 » Sat, Mar 13, 2021, 1:00 AM UTC

montenegrohugo wrote: post #6

Forge36 wrote: post #5

Earlier quoted context omitted.

I have this same problem with people. Just because we don't understand perfectly doesn't mean the output is not useful.

Sure, but humans are a relatively known entity. They exist with a level of variance that is not too extreme, and you can more or less, in a general way, predict their behavior to a tolerable risk level. We've seen billions of humans, we know what to expect of them. We might not understand how other humans work internally, but we understand their actionspace. For AI models, that isn't really the case. We don't know ho…

Then train the models on real world data? Verify outputs enough until confidence is achieved.

The computer can do whatever it wants. People can do whatever they want. The question will be what level of security access will they have.

The key difference today is people are really good at making rationalizations for individual decisions. Computers are not.

Sometimes decisions are generally important, when they are important they require trust, and if these models never generate a method of demonstrating success/trust they won't be adopted.

Re: Self-supervised learning: The dark matter of intelligence

#70

Post by Forge36 » Sat, Mar 13, 2021, 1:08 AM UTC

potatoman22 wrote: post #12

Forge36 wrote: post #5

Earlier quoted context omitted.

I have this same problem with people. Just because we don't understand perfectly doesn't mean the output is not useful.

In a medical context, the doctor won't use it if he doesn't know where it gets its score from

As she should. Trust but verify. The biggest question is what will this be applied to. Without it we can't really discuss approaches towards developing that trust.

I'd consider The ability to output a rationalization in human understandable text (ie: english in my case) will determine success /failure.