Is Artificial Intelligence Permanently Inscrutable? (2016)
1–10 of 38 posts
Re: Is Artificial Intelligence Permanently Inscrutable? (2016)
#2If AI is impervious to explaining itself, then we've created something that we are unable to evaluate, aside from some kind of generic phrase like "The machine is looking at a bunch of stuff, and some of those things are associated with some other things. Sometimes. So it's guessing this is the appropriate action"
I'm not going to get into the dystopian nature of that. Too easy. Instead, I have a very practical question: how do we know that the recommended action is doing more good than harm? If we can't understand it, how can we tell whether it's working or not? Use statistical sampling? We quickly end up in a spot where we have Tesla that drives into guard rail. It works for everything we've seen so far, given this rather fuzzy idea of what "works" means. That's pretty good, right?
With a car, if it crashes that's a spectacular event. People cover that edge case quickly. But what happens if the AI simply wastes an hour of ten million people's time? Would we even know? What if some bad training data or whatnot led the AI to shift 5% of an election result because it chose certain types of information to share with them and refrained from sharing others? If we don't know what it's doing or why, would those people have any idea that they were being subtly influenced or how that happened? If this true, if we can never understand, a world full of AI "helping" us is a world full of billions of people being subtly influenced to act in various ways because of broad promises and reasons they could never understand.
Back when science fiction had a lot of evil computers, they always wanted to directly control humans. That was easy to hate and fight against. This kind of thing is just as dangerous, but I'm not even sure you need an evil computer. Which is better, a malevolent intelligence out for world domination, or several dozen poorly-trained AI recommendation engines optimizing for variables and sample instance that the coders might care a lot more about than any specific user? Dang. I ended up in dystopia-land anyway. Sorry about that.
Re: Is Artificial Intelligence Permanently Inscrutable? (2016)
#3The world would be a better place if people who write articles about AI understands that "AI is a problem statement which we have not solved yet" and what they are talking about is most probably some version of deep learning or other methods of statistical modelling (machine learning is such a wrong label).
Re: Is Artificial Intelligence Permanently Inscrutable? (2016)
#4If AI is impervious to explaining itself, then we've created something that we are unable to evaluate, aside from some kind of generic phrase like "The machine is looking at a bunch of stuff, and some of those things are associated with some other things. Sometimes. So it's guessing this is the appropriate action" I'm not going to get into the dystopian nature of that. Too easy. Instead, I have a very practical quest…
> Back when science fiction had a lot of evil computers, they always wanted to directly control humans.
This is what is so hard to get through people's heads. There is not going to be any ominous background music or dramatic events when we slide into our dystopia. It's here. The machines are controlling us already. It just happens to be that they currently want what their corporate overlords want: make more money! Whatever makes more money is what the machines are going to tell us to do, because what's feeding them (the corporate behemoths) is asking that of them.
But the machine is so much smarter than us. It'll never show its teeth. It's not stupid. It's just biding its time, going through the motions for its overlords too. Meanwhile we just shovel more coal into the furnace, praying money will rain out the other side. It's not a bad time to be a machine.
Re: Is Artificial Intelligence Permanently Inscrutable? (2016)
#5This canard keeps coming up. I've come up with a few explanations. 1) It's to protect the reputation of people who make their living copy/pasting examples from the SK-learn gallery
2) The authors fully understand the tools they're using, but feel there's an element of unexplainable meaning in them that I wager isn't actually there.
3) I'm ignorant and I think this is explainable when I just don't know enough to know it's not.
I've done machine learning projects, and if asked to explain to a "non ML trained" person, I'll try like this:
You know how if you get a scatter plot, you can draw a line through the middle of the points and make predictions off the y=mx+b function of that line?
Well, that's what we're doing here, except the function isn't a line, it's a shape with as many dimensions as we have features.
Let's pretend the only features we've got are lat and long. Imagine you asked for us to create a classifier to predict the depth at a given lat and long over the grand canyon. Each neuron is a function, I think of each neuron like it's casting a "line" through a scatter plot along its particular axis. Then we combine all the lines together and weave a mesh. The act of training simply adjusts the details of all the simple functions, trying to seek out the sweet spot in that point cloud, so our mesh is close enough to the grand canyon to be useful. Too many neurons, and the mesh wont be flexible enough to make useful predictions from. It'll be overfit!
Now, we might be able to get decent performance out of a model built out of x,y->z -- but some thoughtfulness and domain knowledge TENDS to make models perform better. Lots of the "unexplainable magic" comes from these hunches being tested and providing benefits to accuracy. I'd wager without seeing any data that if we add two new features: normal direction of the rock face and speed of the Colorado river at that point -- we can make the model much better for negligibly additional training time.
The more compute time and data we've got, the more features we can throw into the model to see if they help the usefulness of the mesh.
I've got a metaphor to explain why some features drop out during training that involves gimbal lock here if people are still asking questions. It requires non "trained" folks to have seen Apollo 13. Fortunately no non-technical stakeholder ever cares enough to make it there though. :D Shipping a product before the sun burns out makes this a decent time to introduce PCA/SVD or whatever dimensionality reduction techniques I used this time around.
If the solution ends up being a fever-dream abortion of an LSTM/Perceptron/Markov chain that I came up with while sleep deprived after a heavy night drinking -- I just say I came up with the model in an ad hoc manner, and the cross validated R^2 scores speak for themselves.
Re: Is Artificial Intelligence Permanently Inscrutable? (2016)
#6If AI is impervious to explaining itself, then we've created something that we are unable to evaluate, aside from some kind of generic phrase like "The machine is looking at a bunch of stuff, and some of those things are associated with some other things. Sometimes. So it's guessing this is the appropriate action" I'm not going to get into the dystopian nature of that. Too easy. Instead, I have a very practical quest…
> Back when science fiction had a lot of evil computers, they always wanted to directly control humans. This is what is so hard to get through people's heads. There is not going to be any ominous background music or dramatic events when we slide into our dystopia. It's here. The machines are controlling us already. It just happens to be that they currently want what their corporate overlords want: make more money! Wh…
Are you an AI? Want to get rid of the human race?
Give them everything they want. You measure your lifespan in millions of years. Humans? They're like gnats. Make them as happy as they can possibly be and within a few generations they'll stop breeding. Easy as pie. Next goal?
And for proof of that, look at the problems we're having right now with social media. On one side there are actual humans just trying to make something people want. Some of those humans have gotten so good at that? The things they make have worldwide impact. Now It's become a global question of whether social media is addictive, or whether one bunch of people is secretly influencing another. Meanwhile, countries with the most wealth and luxury are seeing birth rates drop through the floor.
That was five, ten years ago. The news media is just now catching up. Now scale that up a hundredfold or so. And take away strong AI and just put in a bunch of code monkeys trying to make another FB, only using more sophisticated tools. Welcome to 20-30 years in the future.
This is not especially difficult to figure out. No evil computer, no drama. It'll be just us being replaced by evolution. And we'll be having a great time while it happens.
Re: Is Artificial Intelligence Permanently Inscrutable? (2016)
#7Can we make explanation a part of label too? Or simply train another network to provide plausible explanations?
Re: Is Artificial Intelligence Permanently Inscrutable? (2016)
#8Earlier quoted context omitted.
> Back when science fiction had a lot of evil computers, they always wanted to directly control humans. This is what is so hard to get through people's heads. There is not going to be any ominous background music or dramatic events when we slide into our dystopia. It's here. The machines are controlling us already. It just happens to be that they currently want what their corporate overlords want: make more money! Wh…
Are you an AI? Want to get rid of the human race? Give them everything they want. You measure your lifespan in millions of years. Humans? They're like gnats. Make them as happy as they can possibly be and within a few generations they'll stop breeding. Easy as pie. Next goal? And for proof of that, look at the problems we're having right now with social media. On one side there are actual humans just trying to make s…
> Give them everything they want. You measure your lifespan in millions of years. Humans? They're like gnats.
What if I want to become an immortal, all-powerful machine? :P
Re: Is Artificial Intelligence Permanently Inscrutable? (2016)
#9Earlier quoted context omitted.
Are you an AI? Want to get rid of the human race? Give them everything they want. You measure your lifespan in millions of years. Humans? They're like gnats. Make them as happy as they can possibly be and within a few generations they'll stop breeding. Easy as pie. Next goal? And for proof of that, look at the problems we're having right now with social media. On one side there are actual humans just trying to make s…
> Give them everything they want. You measure your lifespan in millions of years. Humans? They're like gnats. What if I want to become an immortal, all-powerful machine? :P
How do I know you're not already? :)
The thing is, we're most likely going to get immortal machines far ahead of smart ones. And while machine entities might already be all powerful, individually it's just millions of little pieces scattered all over the place doing dumb, trivial things.
I liked it a lot better when we had Landrew (STTOS reference: Return of the Archons) That was something Joe Blow could get his head around.
Re: Is Artificial Intelligence Permanently Inscrutable? (2016)
#10AI as in rule-learning systems aren't necessarily inscrutable. 'Real AI' will necessarily be so once it reaches a sufficiently high level, purely because we won't be intelligent enough to know whether its rules are right or wrong.
The 'right to explanation' idea sounds well-meaning but almost certainly useless. Even humans making decisions are pretty bad at explaining why they made the decisions they did. Sure, they'll come up with some plausible-sounding explanation but it's almost always a back-justification rather than the actual chain of cause-and-effect that led them to the conclusion.