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

Scientists Increasingly Can’t Explain How AI Works

vice.com

Post reply on HN
Print view View original

71–80 of 231 posts

Re: Scientists Increasingly Can’t Explain How AI Works

#71

Post by joxel »

datpiff wrote: post #21
joxel wrote: post #13

It's quite easy to explain. You take a bunch of tensors and multiply them by a bunch of tensors. Humans can't wrap their heads around multiple tensors being multiplied together and never will. It's not a problem with AI. It's a problem with humans. It's not AIs fault that we can understand F=ma but can't understand 50 tensors being stacked.

>It's not a problem with AI. It's a problem with humans. It's not AIs fault This is a really, really funny defense of AI.

Why? How is it AI's fault that it can solve problems humans have proven unable to solve? And then you think it's AI's fault when we can't explain how it's solving the problems we can't solve? There's a reason we can't explain why a neural network detects it as a cat or dog, it's because we can't solve it ourselves, so the exact mathematical intuition is literally beyond our ability to describe (so far).

Re: Scientists Increasingly Can’t Explain How AI Works

#72

Post by fallingknife »

impalallama wrote: post #63
fallingknife wrote: post #10

Earlier quoted context omitted.

What people are really saying, but never will admit, is that they want AI to mirror their own biases, not to have none. That's the reason they are "cleaning" the input data.

What are you saying? That its better to just blindly trust in the output of a blackbox AI output? That naively feeding in all possible data into an AI is the "best" way to do it? It is been well documented that blindly trusting AI just leads to it perpetuating human stereotypes and worsen flawed systems. https://dl.acm.org/doi/10.1145/3531146.3533138 https://www.aclu.org/news/privacy-technology/algorithms-in-h... It'…

Assuming that a human stereotype is untrue is just as biased as assuming it is true. If you judge a model by how well it confirms your previous bias, then the model tells you nothing you didn't already know.

Re: Scientists Increasingly Can’t Explain How AI Works

#73

Post by kuramitropolis »

endorphinbomber wrote: post #41
bobosha wrote: post #12

I think explainability is overrated (to use a Trumpian expression) & this fixation with coming up with explanations for inferences is a red herring. We cannot explain our own thoughts and actions and tend to ascribe logic & reason to many of our own actions, but it's almost always system-1 driven, for the most part. Correcting for edge-cases and unknown-unknowns is where we should focus our efforts methinks.

You can't explain your own thoughts and actions??? I'm sorry, but that's part of makes a valuable team mate or partner. This is not fundamentally human, this is trained behaviour. I am very well capable of expressing my thougts and explaining actions resulting from these thoughts.

Can you explain why you had a thought, however? And how many levels deep? Only as many as someone cares to ask, I'd wager.

You have developed the capability of explaining your actions as resulting from your thoughts, because there is someone on the other side who is ready to accept and evaluate your explanations.

Others have no such affordance, so their brains get trained in prejudices and superstitions indead. Even if an explanation of an action is given in good faith and accepted by the recipient, it can still be factually incorrect.

Re: Scientists Increasingly Can’t Explain How AI Works

#74

Post by joenot443 »

p0pcult wrote: post #39
fallingknife wrote: post #10

Earlier quoted context omitted.

What people are really saying, but never will admit, is that they want AI to mirror their own biases, not to have none. That's the reason they are "cleaning" the input data.

I think with this response, you reveal more about yourself and your worldview, than any general truth about others.

What exactly is the worldview you're describing here?

Re: Scientists Increasingly Can’t Explain How AI Works

#75

Post by diputsmonro »

fallingknife wrote: post #61
mchaver wrote: post #57

Earlier quoted context omitted.

I always thought it was the opposite. That we want AI to have no biases, but we have trouble avoiding it. Choosing data and cleaning is where we insert our bias.

What people want is for the models to show no differences between certain groups of people. That is the standard they use for "no bias." But that itself is bias, so really they just want the model output to conform to their bias that there isn't any difference.

So what you're really saying is, it's perfectly okay for AI to have negative preconceptions and concrete impacts to certain groups of people, as long as it agrees with you on which groups are bad.

How would you feel about AI models that classify all modern white people as racists based on overwhelming historical data about slavery, the KKK, etc.? Hey man, data doesn't lie.

Re: Scientists Increasingly Can’t Explain How AI Works

#76

Post by joenot443 »

recuter wrote: post #28

> Black box models can be extremely powerful, which is how many scientists and companies justify sacrificing explainability for accuracy. > AI systems have been used for autonomous cars, customer service chatbots, and diagnosing disease, and have the power to perform some tasks better than humans can. For example, a machine that is capable of remembering one trillion items, such as digits, letters, and words, versus…

Just a hack journalist, I think. Her other publications include:

"Alaska Canceled Snow Crab Season for the First Time Ever Because All the Crabs Are Gone"

Re: Scientists Increasingly Can’t Explain How AI Works

#77

Post by Spivak »

bombcar wrote: post #59
tromp wrote: post #54

Earlier quoted context omitted.

> Obviously we know they were the result of a deep minimax-style parallel search with a certain evaluation function, and we could simulate a similar search by hand if we wanted to. You don't really need to though. The computer can justify its evaluation with a principal variation (best play by both sides) leading to a leaf position of the same value. And if a human were to wonder why at any point in this variation, s…

Exactly, the Deep Blue's move explanations are boring - they all boil down to "based on the inputs and rules programmed, this line of moves has the best overall outcome to a depth of X" where X is however deep it goes. You can try to translate that to human methods of understanding, but that's not how the computer "thinks", and attempting to do that translation leads to misunderstanding. Kasparov may make moves becau…

I don’t think that’s weird at all, I think humans can intuitively grasp “I simulated 100,000 games starting from the current board state and going at most 50 moves ahead and in games where you did X you reached a strong position most often.”

Is that a useful explanation for a human who is training a wetware ML model, not really. But it’s really understandable compared to trying to explain neural nets.

Re: Scientists Increasingly Can’t Explain How AI Works

#78

Post by impalallama »

fallingknife wrote: post #72
impalallama wrote: post #63

Earlier quoted context omitted.

What are you saying? That its better to just blindly trust in the output of a blackbox AI output? That naively feeding in all possible data into an AI is the "best" way to do it? It is been well documented that blindly trusting AI just leads to it perpetuating human stereotypes and worsen flawed systems. https://dl.acm.org/doi/10.1145/3531146.3533138 https://www.aclu.org/news/privacy-technology/algorithms-in-h... It'…

Assuming that a human stereotype is untrue is just as biased as assuming it is true. If you judge a model by how well it confirms your previous bias, then the model tells you nothing you didn't already know.

No post body was provided.

Re: Scientists Increasingly Can’t Explain How AI Works

#80

Post by AstralStorm »

williamcotton wrote: post #60
kortex wrote: post #49

Earlier quoted context omitted.

Same for both: brake. I don't want either hitting my windshield. The kickball may be bouncy, sure, but it may have gotten rocks stuck to it, which can create a point stress and scratch paint or chip the windshield. Humans can't intuit mass unless the object meets certain criteria, either. What if it's an opaque cardboard box in the road? Generally the strategy is the same: avoid it.

In certain circumstances with a playground ball you would have to choose between extensive damage to the body of your car by swerving out of the way or to just take the risk of a chipped windshield from a playground ball that somehow has rocks stuck to the outside. And have you seen ever seen a rubber playground ball with rocks stuck to the outside? Do you really hesitate to barefoot kick an unexamined playground bal…

In case of a car, the thrown object is the easy case.

Now imagine you spot a person walking down the road on a pavement. Suddenly, the person turns towards the edge. What do you do?

See, a human driver would look at the gait of the person from far away to evaluate for instance if they're sober, or if it's a child who might be expected to run in. Whether it is near a crossing or a potential crossing. Whether the person was walking or standing... Many other obvious and less obvious indicators. AI currently sees a moving blob of pixels in a shape of a person. No advanced inference.

When interviewed in case of an accident, say because they got rear ended due to braking, a person can explain why they braked most of the time.

AI now couldn't even say which features it weighted.

Post reply on HN