AI Safety - Computerphile 

That's why his channel us my main source

One problem that I've encountered while trying to discuss these sorts of topics with other people is that some people firmly believe that the human brain *is* actually magic, that there's something unmeasurable about it which, for whatever reason, can't be recreated with computers. And if I try to challenge these beliefs, it is unthinkable to them because it would upturn the very foundation of their philosophies. We're going to encounter these sorts of problems on grander, more tangible scales in the near future, and it will be critical that the side of AI safety comes out on top.

***** Thanks.

+CatnamedMittens “Michael Bialas” thanks

+CatnamedMittens „Michael Bialas“ First Thooorin, then Computerphile. Next time we meet in the comments of some beauty vlog, I suppose? ;)

Marius Hamacher Let's not get carried away.

+CatnamedMittens “Michael Bialas” Could watch these all day

That whole video was sensational vague drivel.

Robert Swift Well, I've already made my response to you clear on your comment thread (;

Chronosaur I chatted in length on the subject on another thread already. I like the subject though. You have an opportunity to give your own argument. Do the leg work and Build up some talking points.

I am a programmer, so this wasn't new to me, but I didn't know moderacy was a word until now. We are all learning things!

+Doug Soutar I like him a lot too

+Doug Soutar Tom Scott 4lyfe

MLGBanterVids Yeah, hes awesome. He has his own channel tho

+Doug Soutar Agreed, Rob Miles is awesome.

+Deer Viehch Link? It's not in description or search results.

+E SC He went from Moss to Danny Sexbang

+AnOddScot NSP!

+E SC they get bigger thruout whole video

English Mac DeMarco

I've got my own channel you know

I mean, Asimov himself subverted his laws with edge cases even more than he exemplified why they exist. And positronic brains were made manually, not optimized by optimizers

@@gabrote42 This. So many people swear by the laws without even stopping to consider that even in the original, they were broad guidelines at best.

@@codrincx and harmful overheat crashers at worst

+Steam1901 i dont have money to buy it

pirate it

@@SilvioPorto KickassTorrents is my new favorite website for acquiring more knowledge I couldn't get otherwise lol

At some point they will be able to model every neuron and connection in the brain at an atomic level, and then its simply a matter of connecting up the brain in a jar to inputs and outputs.

+BattousaiHBr That's the nature of religious beliefs. Your logic or facts will make no difference. They are expressing beliefs about a highly technical field of which they know little (Dunning Kruger Effect) and they will just not listen to anyone who tells them that they are wrong.

+BattousaiHBr It sounds like the god of the gaps. You say they don't understand the brain. And also that they don't think it is possible that computer may reach a similar status. They probably have more affinity understanding computers than brains. So they perceive them as fundamentally different. If you try to inquire in what is the difference, they may say it is god / magic / nature / quantum physics (or some other thing that is generally considered beyond comprehension from their point of view). What I say is that they hold their belief that the brain is somehow impossibly special and amazing, because they don't even understand the basic principles behind the human brain. You are not winning this argument in the abstract, examples of "smart" computers (which is what I understand you mean by real life examples) risk being seen as cute things somebody programmed - the smart part came from the programer, not the computer. Instead dig a level down, the brain is neurons, veins, arteries, chemicals... if the universe is deterministic at that level, it can be modeled in a computer. If the universe is not deterministic at that level, we could incorporate that in computers. Try that argument, if they say if we do that it isn't a computer, but a brain... well, it falls to semantics, have then express what makes a brain a brain. Now you can work out some examples to address what they come up with.

***** thanks to everyone for your input. to address your question, by "real life examples" i was actually referring to how humans actually do things. i always try to make inquiries to make them think how our brain actually works to see their answer, and when they get it right i immediately make the same question about how a computer would do such a thing. for instance, they claim computers have to be programmed to do everything and we dont, so i ask "how exactly do you know how to move your muscles? or how to see?". it usually takes repeating the question many times in many different ways, but sometimes they get it right, and immediately after i switch the same question but replacing human with computer. even when the connection becomes apparent they still refuse to acknowledge it.

BattousaiHBr I see, that makes sense. Since they say that computer needs to be programed to do something. to get AI across, you need to tackle the problem of learning. What does "lean" means? How do you learn? What if you program the computer to learn? There are three approaches to learning to consider: - learn by instruction: it would devolve into natural language and kownledge representation. Those areas are still in development. - learn by example: this is the case of surpervised learning. - learn by experimentation: this is the case of unsupervised learning. If you avoid "learn by instruction", you are on better grounds. --- Regardless of all the discussion, we don't have computers smarter than humans. At least not smarter in all the measures of the word. Yet, the thing is they don't believe that machine learning exists. Yet, we have examples of machine learning, you could try to find one you can show. At the end some people won't get it until they do it themselves. it's easy to say that a software learned if it solves a problem that the author don't know how to solve. In particular if they are the author. --- I want to recommend the book "Artificial Intelligence: A Modern Approach". I have the second edition. The book is university level. It has a lengthy introduction, the frist two chapters (ie. part I) are - imho - accesible for everybody. From chapter 3 (ie. part II) it gets quite technical. With some programming background, you could apply some of the stuff from the book. Part V and VI are the real deal. Part V talks about missing information. Part VI talks about learning. The second edition still holds today, idk what's new in the third one tho.

void future = now(now)

exactly AI will need to be regulated by AI - the question is how to include or make humanity as a priority.

@M I don't know, based on the experience of human businesses and governments, relying on entities self-regulating themselves is always a bad idea.

@Horny Fruit Flies Relying on groups humans self-regulating is a bad idea. Most computer entities are more reasonable than humans. It's not even that high of a bar.

@@ekki1993 IMO the largest issue with self-regulating corporations is that they are pretty rational and reasonable. They're incentivized to pursue maximum profit for shareholders - this is the way it's taught in business classes and generally the objective that companies are structured to support. As a result, e.g. if you have environmental regulations and breaking them results in a fine, then as the head of a company you're incentivized to treat the issue as one of trade-offs - obtain greater profits and treat the fines as business costs. The same generally goes with other more blatantly criminal activity: completely rational in pursuit of the objective. And I guess that would bring us back to the core of the problem - how do we build an AI to watch an AI and ensure that both are in line with our interests as a species? We'd have to instill the same values we have into our watchdog AI, which is really just kicking the can down the road. Anything less, and in all probability the watchdog AI would find a way to achieve its objective in a manner detrimental to humans.

@@adhoc75 Exactly. My use of reasonable wasn't very clear. Corporations may be very "reasonable" in the pursuit of money/power but it's clear how they can also be very detrimental for humans, yet we as humans keep relying on them and justifying their actions.

Please don't.

+TheNefari Bots Rights! Let them form their own ethical identities!

NickCybert lol ok

+NickCybert Oh no, its the BRM again.

Laharl Krichevskoy I don't believe you understand artificial intelligence.

AI wont always be at risk of being shut down if its powerful enough. It will first come up with a plan to prevent that, and will always be able to do so better than us due to its vast intelligence. And AI will know our values, but it will only care about them if it interferes with its main goal. As soon as it no longer has a need to care about our values, it wont. If it needs to trick us in order to survive, it will continue to "care" about our values, but it will always be looking for actions it can take to ensure its own survival is secured so that it can implement some extreme optimization of its true goal. And BECAUSE its so intelligent, it will almost always succeed at such a thing.

Something that I feel gets left out of the AI's theorized logic process frequently is that they will know that we have survived for a tremendous length of time, and were able to create them. That provides a stability for future existence of more, better, and different AI for it to know or become that as a young AI it cannot guarantee for itself.

Probably a pretty good model for exactly what a human being does, now that I think of it. Maybe it's not that complicated after all.

I also want to say that emotions are more than just "feelings" they involve complex neurochemical responses to complex neurochemical responses to stimuli and so on, and behind it all is something quite clear and obvious, brain activity and the glucose that fuels it. You can have an excess of brain activity which can cause wear on the hardware of the brain, this is called "stress". A computer should be able to understand this quite easily. So if you program a computer to consider the physical well being of people's brains you kind of automatically account for stress and therefore many types of harmful and or dangerous situations which would cause stress to a human being.

+richard506rb the best definition I've heard for friendly is 'Having goals that maximize the happiness of the maximum number of people at any one time, along with a greater concern for those around, then one's self." That's all I've got, that's the best I've yet heard.

This topic excites me too! Just for the heck of it, here are the thoughts I've had on the subject: I believe consciousness is all things that are a part of our experience, and it doesn't really emerge at a point. To me, computers are already a part of our consciousness (or we are of them, depending on perspective). I would also say there is no one solution to turning what AI capabilities we have into a single "general intelligence". The reason for this is like how we find primes. The most straightforward and obvious way would be to check every nuber sequentially, and verify if it is prime by seeing if it divides evenly into any number between one and itself. This would be equivalent to writing a program that iterates through creating every possible program (less than a certain number of bytes) to see if a solution to general intelligence appears in some amount of time. Of course, this would be extremely impractical, so it's off the table. Like with prime numbers, we don't check every number the way described above. We only check odd numbers that don't end in 0 or 5, and we don't divide every number into it, just primes less than its square root. (there are better ways I'm sure, and lots of other tricks too). Similarly, to obtain a general intelligence, we would discover tricks that would allow us to more easily find new, better programs that simulate intelligence* better than the last. *To me, if something acts like a person, it's a person as much as anyone else. I don't believe in "philosophical zombies". In this case, I would say if we have made a machine that simulates intelligence, we have an intelligent machine.

+Craparella Smørrebrød what is that?

+R9000 Did you here what he said? We're probably just as far from a solution as we are from actual AI. The answer is probably extremly technical and anyone who isn't a PhD in a related field is wasting their time thinking about the solution

+Delta X Dude, I study this stuff. If we don't start thinking about it now, then when will we? Don't discourage people from research, non-PhDs can come up with ideas too.

R9000 Like if you're doing cutting edge research directly focused on AI then sure. But I'm sorry, some schmuck on RU-vid coming up with ideas when he doesn't even understand the problem is of no value. Talking about the problem on a high level like this is all that most of us can do. So yeah, you don't have to be a PhD, but anyone who is not actively in working in research and development in this area doesn't have anything to say about the details of the solution

Delta X How can you say that though? It's an ethical problem as much as a technical one. And even if you don't want to look into it yourself, you should at least be pushing or supporting research towards it, not complaining and scaremongering as per my first post.

Sure, but the simple fact that people would still disagree to this day their interpretation of basic human values when we use much more intuitive tools like words and we as a species have been tackling the problem for thousands of years meant that it's not a thing likely to be formalized before the emergence of AGI.

@@9308323 No, disagreement does not imply that there are no objective and unchanging human values, that can be proven. Words are not intuitive, they are deceptive. Words are perhaps the worst tools to understand concepts and ideas with. Words can mean more than one thing simultaneously, which causes confusion, and makes much of modern debate futile. Artificial general intelligence is only impossible because of people like you and the guy in this video, who are injecting their own personal fallacious beliefs into their understanding of ai, which makes it appear like agi is impossible. You need to stop believing that disagreement, and difficulty matter when trying to discover what is true.

This is of course we know that the basic task is something we even Can give them without being fooled into thinking it will do the task.

+TheJaredtheJaredlong , I think many Computer Science student do take General AI as a challenge but later it dawn upon them they couldn't make it happen. Typically they thought intelligence can be copied from investigation into logics (ie: dissecting their own mind), but this isn't enough for a General AI.

xponen I get the feeling you actually know something about computer sciences (I don't), is it possible for a computer to be programmed in such a way that it could re-program itself? I understand the goal of general AI as a system that can learn to do any function. That level of flexibility requires a lot of adaptability and autonomy. So the abstract solution seems to be a program that can change itself, but is that even possible?

+TheJaredtheJaredlong I don't have a PhD on the topic but I can safely say that the learning aspect is not the problem. Writing an AI that learns from mistakes is not hard, and it's quite powerful. You might have heard about how Google's AI recently beat a Go (one of the hardest games we came up with) Champion consistently - it did that by learning from a bunch of practice matches using neural networks. So indeed, it is possible to make computers adapt. I think the problem lies more in the 'general' aspect. Right now, AIs can basically (and please do correct me if I am wrong) only learn what you tell them to learn. Google's AI might be excellent at playing Go, but tell it to learn to speak French and it will fail miserably. To solve the problem of general AI, we would need some kind of way to let computers figure out on their own what it is they need to learn. But that's very difficult.

***** chaotic in the: stop working way, or chaotic in the: programmers can't follow what's going on anymore way?

+TheJaredtheJaredlong Program that changes own code is possible to be done using metaprogramming (example... using JavaScript).

so basically the character "Ethan" from the show "Extant"

+Novashadow115 I'm usually wary of using fiction-based analogies, but yes, in a way.

Fabio P Well, that fiction is merely a projection of someones imagination. All innovation is initially the product of someones imagination. In this instance, the fiction nailed it. The AI developed a model of reality by being raised much akin to a human child. It learned as we did when it came to ethics

***** i was saying that it wouldn't be afraid at all, and likely wouldn't care whether or not it was shut off, since if it had a desire to not be shut off, it would very likely have a fear of being shut off

Since it is likely that we can't stop it from happening, and it might be pretty soon, I think that we should probably try to do something about it. The most promising thing to do would be to try to spawn an AI that protects us. Even that is pretty dangerous. We should be taking this serious NOW though. (In all likely we are doomed though.)

+Sarah Szabo I think you make an excellent point, while also disagreeing with the assertion that we can't make "safe AI"; although, I think all of those solutions rely on treating the AI with respect, teaching it the value of respecting other life, and not needlessly torturing it. All of which are amazingly difficult problems to solve in and of themselves. I think a lot more general AI programmers should have a strong background in ethics and philosophy in general.

+Sarah Szabo You basically make the same argument as David Deutsch, so you're not in bad company there.

+Sarah Szabo well we can allways try to hardcode some rules into the AI. But maybe if you make an AI it can go around those rules. But maybe we can give it a conscience that it could break but will not? Maybe all that won't be a problem because we will have learned to upgrade our brains enough that an ai will not be better in all aspects.

Kitt Schlatter Totally agree.

Sarah Szabo you might be able to lock the AI behind a wall that checks if the action it is trying to do will harm the a human directly or something similar to keep chains on the ai.But probably would just try to find a way around it.

+Samm Just It's a pretty popular theory.

+Samm Just LITERALLY magic!

+edrudathec The most popular theory, sadly

+edrudathec Also a theory that should not be taken seriously if your scientificly minded. Science do not deal in magic after all. If science can explain it then is not magic. Also Science assumes that nothing is magic. Though things may be unexplained at current level of understanding. Of course science might be wrong in that regard. But if your are a Scientist you should always assume it is not magic no matter how much evidences there is for it being magic. Else your just a lazy Scientist (or should I even say your a lazy Pseudo Scientist.)

+Cythil I don't follow. Science is a particular method (or collection of methods) of trying to determine things. I don't see any reason why some things that would be called "literally magic" would be inherently incompatible with those methods.

Indeed