How will AI change the world?

[@BoatSoccerPlayer]

Huge props for making the robot both terrifying and, paradoxically, incredibly adorable!

[@Echo81Rumple83]

he looks like Atlas; all we need is Peabody to make the Portals 2 reality a thing XD

[@adre2194]

He's just doing his best

[@aguyontheinternet8436]

it all depends on how you use it

[@thesciemathist6035]

Yup. The video's animation is a story in and of itself.

[@khoirulanam9141]

yeah but if we don't do that, we're gonna see someone do decades of warehousing and call that life.

[@zigzag8338]

As Stephen Hawking said : "If machines produce everything we need, the outcome will depend on how things are distributed.Everyone can enjoy a life of luxurious leisure if the machine-produced wealth is shared, or most people can end up miserably poor if the machine-owners successfully lobby against wealth redistribution. So far, the trend seems to be toward the second option, with technology driving ever-increasing inequality."

[@ForbiddenFollyFollower]

You think the government wouldn't consider it a security risk to let rogue oligarchs control the entirety of people's lives? The government will just be the ones to control the entirety of people's lives and no one will be able to protest even as they ride around town on a high bike made of human ligaments with the human still attached and screaming or turning people inside out to make them walking vaginas as their organs sputter blood.

[@captainahab5522]

This is why we need wealth redistribution laws to help society thrive.

[@patrick-bu3eq]

@@captainahab5522 Just let capitalism rot.

[@ptp4171]

Not saying I'm smarter than Hawking or anything but wealth is relative. As long as you're not on the street you're far wealthier than the wealthiest of a hundred years ago.

[@tropsele]

You‘re definitely not, compared to any king or similar rich people, you have basically nothing. Just because the amount of currency they had could afford way more than it would today. Could you build a castle and employ the entire staff for a private guard?

[@rajusual]

I love how Ted Ed comes with a new animation style for each of its videos.

[@moththe_player6905]

the chicken one is best. no doubt

[@clearmenser]

Yea it's cool they commission new animators

[@Vertions-o5p]

@@moththe_player6905 LINK??

[@Random_entity34]

I especially loved this one. One of my favorite along with the 8-bit from the video about Achilles.

[@ggandei]

It?

[@sanne120499]

About the coffee scenario at the beginninng, this is ChatGPT's answer: As an AI language model, I don't have a physical form and I don't have the ability to perform physical tasks like getting a cup of coffee. However, if I were a physical robot programmed to get coffee, I would follow my programming and attempt to retrieve the coffee from another store or find an alternative solution for you. If I were unable to do so, I would inform you of the situation and discuss possible alternatives with you.

[@samehseleim1470]

Smarter than he thought

[@Eulers_Identity]

Wall•e is such a good film! I remember it being my favorite while I was growing up. But only later I realized how deep the significance of what it portrays runs. It's kinda scary.

[@Echo81Rumple83]

i saw it when i was still in college. it already hit me what it was portraying about our humanity and the dangers of relying on AI to help us.

[@grapeshott]

I have forgotten it....

[@cyh..7]

i didnt really think too much of wall e when i first watched it, i just liked it but now i'm more happy about the movie's meaning. i like seeing people bring light to environmental issues to other people who aren't as aware. was thinking about rewatching it recently, actually. i've found an interest in sci-fi yk stellar sorta stuff so :p

[@Anderwader]

I saw it when I still in elementary school and I was crying because the relationship is too adorable, later I know the movie is not just about friendship between robots and the meaning is really deep ..

[@Sean.Vosler]

Love the graphic work, wonder who made these! Would love to hire them hah

[@SimplyElectronicsOfficial]

AGI will be here this decade. The idea that it's even 20 years away is insane! People aren't taking into account that we have had incredible advancements in AI almost every week for the last year! And it's only accelerating. We're at the very start of an exponential curve. Watch this space!

[@WavyThunder67]

After a deepdive into this very fascinating subject, I suspect we'll have something that a lot of experts in the field describe as early AGI by the end of 2024 at the very latest. GPT-4 is already showing a number of emergent properties that push it well beyond the bounds of what is typically considered an AI. The recent plugin update for GPT-4 has shown that the system can engage in effective tool use to solve novel problems, which (to me) indicates a generalised system. I believe that with the addition of robust self-reflection and long-term memory capabilities, even a system like GPT-4 may be considered an AGI.

[@CATDHD]

Or, the problem is harder than we think and we just reached , so for , for the low hanging fruits.

[@hourglass1988]

As with most complex problems we don't know how complex it is when we start. Just take DNA for example. The researchers that were first attempting to sequence the entire genome constantly bragged that "oh yeah by the time we get it all typed out and know the entire sequence we'll know what all of it does within ten years or less" They truly believed that sequencing the entire thing was going to be the hardest part. We got our first fully sequenced human genome in 1995. Now 20 years later we still don't know what 75% of it does. Of the 25% we have figured out what its coding for we only sorta understand how or why it does what it does. Epigenetics wasn't even a concept before and now we realize its this whole other thing that we need to figure out before the sequence really means anything. We didn't know what we didn't know. With AI I think this problem is going to be harder because so much AI is being written by AI. Its doing more and more impressive stuff and we're actually understanding less and less of HOW its doing it. A great example of this was when they taught a computer how to play GO. It could be the greatest GO players in the world but then got tricked by people that barely understood how to play the game. It turns out it got really good at playing at a professional level and winning but the program didn't actually understand the game. It didn't have a strategy. Why? Because they didn't program it how to play. They just programmed the rules of the game and then had it play millions of games against lots of different people and remember what lost and what won.

[@phartbay327]

GPTs are not AI

[@jamesaritchie1]

@@phartbay327 That simply is NOT true. GPTs are actually very advanced AI.

[@bbloomfield6497]

"I don't want a nation of thinkers. I want a nation of workers." -John D. Rockefeller, 1903 First wanting people to be robots.. now wanting robots to be more like people. But still not wanting either one to think too much. This certainly is a curious simulation we're in.

[@eonthinker100yrago8]

its either humanity goes forward or we face extinction when this planet comes out of its current stable climatic conditions which allowed our civilization to exist in the first place.

[@jeseAudio]

Just gotta hope the rulers (in WEF) have better goals this time.

[@ForbiddenFollyFollower]

@@jeseAudio mhm

[@coolkid2093]

"You'll own nothing. And you'll be happy" - World Economic Forum director

[@mhmd_old7]

Simulation theory is made up, its not real.

[@sidneyhibberd3329]

I personally believe that it will not take as long as we might initially think. The AI we have and the regular computing power along with the new quantum computers will help as tools and will enhance our endeavors. However I feel we are hurtling towards a very scary time indeed.

[@tev17]

Yeah me too, I've been trying to keep up with all the advancements, I don't quite understand how the smartest people don't see this coming, each new advancement only drives advancement so much faster, its not linear with this stuff, I think 2030 to 2040 something BIG will happen, and I think the top of the top know this

[@sidneyhibberd3329]

@@tev17 I do not think we even have that long. Thinking 2025.

[@williamyoung369]

If 1000 big thinkers are asking for regulation now, then they probably feel some dangers right around the corner.

[@mifarland]

I don't know how quantum computers will help. I mean they can totally maybe but quantum computers just use qubits instead of bits, they're not necessarily supercomputers just because they're quantum, but its a good thought experiment.

[@sidneyhibberd3329]

@@mifarland They are still a new tech and not mastered. It is true they work differently. But linked with AI and developed further and a quantum computer could for instance calculate multiple situations simultaneously. No que or line of computation. That is the advantage. It a different way to compute data that is super fast but not the sane as a regular computer.

[@Quikrbpaster-ox1ij]

Auto wasn't the villain in story Wall-E, he was just carrying his objective.

[@clusterstage]

yeah, the "directive"

[@cortster12]

That's how all AI will be, even those that destroy humanity. That's the point, lol.

[@connorgray1805]

that's the point

[@BVK.]

@@clusterstage interesting

[@Fastlan3]

The villains are those who believe they hold the true path over all other interpretations.

[@CowboyOdie]

This reminds me of the Hitchhiker's Guide to the Galaxy (published in 1979). Arthur asked the ships computer for a cup of tea that actually tastes like tea. The computer was so perplexed it turned off all other systems just to make the tea. Killing the crew or crashing the ship wasn't even a consideration.

[@matildaronzy2951]

🤣🤣 I don't know why I'm cracking up

[@ronkirk5099]

First, let me say I'm not anti-tech (I'm a retired engineer), but I admit, I'm a little apprehensive about the wide spread use of AI and how there may be unintended consequences. Fortunately being 72 years old, I probably won't be around if 'the singularity' (in the 'out of control tech' sense of the word) occurs as a result.

[@userhandle-l]

It's good to have a general sense of caution so you can prevent situations that are harmful

[@awa418]

darn it im 20 but take me with you please, i also dont wanna live in such world

[@tatianaquercia4555]

It won't occur any singularity. People will only need to reskill to deal with new entities invisibly populating the world.

[@Lilitha11]

I am kind of worried what will happen to us if we don't get wide spread use of AI to help us. People being in charge of stuff is really dangerous too. For every scenario in which AI kills everyone, there are also ones in which humans kill everyone too.

[@anjalisingh-bh1gi]

@@awa418

[@discursion]

It's kinda fun how the General AI problem is basically a reformulation of the Genie in a Bottle dilemma.

[@aaronvogler2864]

I'm a genie in a bottle baby, come, come, come in and let me out

[@bruther7892]

@@aaronvogler2864 tf

[@5ynthet1c]

@@bruther7892 It's a song

[@donaldhobson8873]

Except the genie only understands commands in a long extinct dialect of ancient Croatian.

[@discursion]

@@donaldhobson8873 Maybe that’s the key to unlock AI’s true potential…

[@lisandepuredream9056]

I think this video raises very valud issues with AI. AI can defiantly be really cool and help us advance as a civilization, but if we overuse it or use it inadequately it can bring our ruin as well. Maybe we should just use it where it's obviously needed and useful, rather than a cheapskate trick to replace art, fire workers or do things in general we're either too lazy or to cheap to do ourselves.

[@SeventhSolar]

But that’s too restrictive, isn’t it? All the _important_ work that needs to be done comes at the great cost of millions of years of human life, every year. It’s a worthy endeavor to save every laborer from a life of labor. The fear of disaster will need to be reconciled with just how much we have to gain. Utopia comes after just about all the workers are made obsolete, or in other words, fired.

[@Matheus_Braz]

@@SeventhSolar You better give them the means to live a decent life without their jobs then. Shouldn't be impossible with every function replaced by AI, but god you never know with these people...

[@Мракочёрт-и8й]

do you think craftsmen of the old like smiths or shoemakers didn`t think about their work as art? But they got replaced by more efficient machines at factories. The same is happening right now to artists and one hundred years from now nobody would care about it.

[@honeycomb7652]

Here's how I like to put it: AI and robots should serve humanity, while humans should help themselves. What falls into the categories of "serve" and "help" is a bit arbitrary, but the guideline still is helpful.

[@mattmatyas9605]

But why use human artists when it can do it better and exactly how we want

[@MuditRamman]

gotta love TED-Ed animations man ❤ ❤ ❤ speaking of technological unemployment though, we can already kina see that happening to digital marketing analysts because of Lemon AI

[@grapeshott]

Summary: 1. The certainty of objective completion by an AI can make it psychopathic. It doesn't know what we care about, aside from the exact objective. 2. Effect of AI? e.g. Technological unemployment(Aristotle and Keynes) 3. What if we forget how to run our civilisation, if machines run our civilisation, and we become infantalised(similar to Wall E)? This chain of training until now has continued for 10s of thousands of Years. 4. When will general purpose AI arrive?

[@sidkattoju2283]

Things not mentioned: rule based systems are unviable because of this psychotic certainty problem and that is one of the reasons for the focus on probabilistic reasoning via machine learning / deep learning etc. That said ai could still have “civilization ending” effects.

[@rxflexedits3310]

Here is an AI-generated summary of the video: 00:00:00 - 00:05:00 Computer science professor and AI expert Stuart Russell explains in this video how AI will change the world by becoming able to do most things that humans can do, causing mass unemployment in the process. 00:00:00 This 1-paragraph summary of an interview with computer science professor and AI expert Stuart Russell explains the difference between asking a human to do something and giving an AI system a fixed objective. He says that when humans do something, they often know what they don't know and that this allows them to be more creative in their actions. He also says that although AI systems won't be able to do everything that a human can, they will eventually be able to do most things that a human can do. When general purpose AI arrives, it will cause mass unemployment due to the automation of many jobs. 00:05:00 This video discusses the potential impacts of artificial intelligence on the world, with the median estimate being that general purpose AI will be developed by the end of the century. While the impacts of AI are still largely unknown, it is clear that the technology will have a significant impact on many aspects of life.

[@simnan1827]

@@rxflexedits3310 What did you use to generate it?

[@philippebaillargeon5204]

When will general purpose AI arrive ? literally now. I now use ChatGPT daily to generate code for my job. It's not perfect yet but it's really really good.

[@tatianaquercia4555]

Good job, thanks for this summary! Summaries help knowledge stick.

[@MeettheWHo]

I like how most comment in admiration for the graphics and design of this video. Where the whole point is to illustrate the actual risks of the advancement of technology.

[@vigneshmoorthy6047]

Humans are distracted by Aesthetic & Beauty.

[@Sweatsofficiallytheworst]

Ssshhhh, don't tell them anything. Just let it all play out.

[@mikehewitt2146]

Yes it's the generation of KZbinrs really don't care about the message but how it looks editing etc ,crazy world

[@jessicajayes8326]

Machine: What is my purpose? Rick Sanchez: You pass butter Machine: Oh my God!

[@conscious-atoms]

step 1: clear humans step 2: conquer the universe step 3: create optimized butter consumers, as many as possible step 4: pass the butter 😃

[@jessicajayes8326]

@@conscious-atoms Whoosh

[@allstar4065]

@@jessicajayes8326 It adds to the joke..

[@olimar7647]

I say that AI should be either left untouched, or simply applied as a brainstormer that comes up with ideas but doesn't actually implement them. This would allow us to sidestep many of the problems of AI, because then it won't actually *do* anything. It'll just help us figure out a variety of solutions. Perhaps after we've sufficiently advanced that sort of AI and gotten a hang of it, we could start dipping our toes into a more robust AI system. (Another one of the problems would be that the greater an AI's agency, especially if it should develop some form of emotions, the more important it'll be to give it ethics. And humans are pretty bad at ethics when we look at our track record.)

[@mattclub85]

i think this is really well put and that you're onto something

[@ForsenBruh]

Nope, the technology will only get better and better, regardless of regulations. Some day, somewhere, someone will create the AI that will be a literal god compared to humans. And that godly intelligence can multiply itself infinitely and make infinitely better versions of itself. Even if that is stopped somehow, it will only be a matter of time when everyone in the world knows how to create these god ai:s. NO ONE can predict what happens after this point, the things that unfold when quadrillion copies of an intelligence that are quadrillion times smarter than einstein appear

[@TeoMax]

Ong

[@ProjectMoff]

This is the obvious answer, it's baffling that so many people just jump to giving AI the ability to act and think there's no solution. The solution is to not give it the ability to act...

[@olimar7647]

@ProjectMoff Is anyone actually doing tests like this, though? I honestly wish we'd leave this box unopened, nice as some of the possibilities would be. Bu this method at least gives us more control, and it seems we aren't using it at all.

[@jessed1709]

The quality of animation on this channel is incredible.

[@UmSolqueBrilha]

Professor Russell brings to light deep questions about the nature of artificial intelligence and its social and economic ramifications. One idea he highlights is the importance of designing AI systems that can deal with uncertainty about their objectives while avoiding extreme or undesirable behaviors. This raises the intriguing question of how we can develop AI systems that can learn and adapt their goals more flexibly, rather than operating with rigid and potentially dangerous goals. Furthermore, the discussion about the impact of AI on the economy raises important concerns about technological unemployment and the loss of human skills. However, it is also crucial to consider how AI can create new employment opportunities and how humans can collaborate more effectively with AI systems to increase productivity and innovation. Finally, the debate over the timeline for the development of general-purpose AI highlights the complexity of the challenge. While some experts predict its arrival within a few decades, others adopt a more cautious view, recognizing the technical and ethical difficulties that need to be overcome. This uncertainty reminds us of the importance of a careful and reflective approach to the development of AI, considering not only the potential for technological advances but also their social and ethical implications.

[@jamesaritchie1]

This video is badly out of date.

[@ChezTheDude]

The animation in these videos are always great but this animation has to be one of, if not my favorite. Wonderful job as always!

[@Redmanticore]

would be funny if AI made the animations warning about the use of AI

[@user-rx7pd1xv4k]

I found myself really enjoying it... like getting distracted for a good moment because I was admiring the atmosphere they were able to create near the end. Whoever animated this one is a wonderful artist!

[@Taibo1986]

This video had excellent animation. It coupled with the narration so well by mixing abstract art with litteral representations seamlessly.

[@jakemorris111]

Super well done to the team of animators! I'm floored at the illustrations and lighting effects you guys pulled off. Absolutely inspirational.

[@mjhoover]

Too bad the audio was muddy, so hard to hear the content and actually take it in.

[@cesaralvarez7474]

i dont think that was the point dude

[@gifteboyi3716]

The animation is indeed a masterpiece. The audio everything is sinking together. I love it 😍

[@sanjayveerakumar375]

Hats off to the graphics and animation team.😍

[@ninjesus4079]

generated by Dall-e 2

[@Howtochannel777]

kzbin.info/www/bejne/p6rHgaWhqt9qd8k

[@NathanHarrison7]

One of the most realistic and easy to understand explanations of the dangers of AI I’ve seen to date. And one that seems very realistic and not overdramatic or exaggerative. Thank you Mr. Ted!

[@asprin481]

Bro I wish the artist(s) all the love and wealth in the world. Truly magnificent!!!!!!!!!!!!!!

[@terramater]

That's a fascinating point! Our crew filmed AI from another perspective, interspecies communication. Can AI helps us decode whale communication? And would it make sense? We tend to humanize animal species and have high hopes that their communication system is similar to ours. Still, AI could be a game changer in this case. Let's see what the future brings!

[@astha_yadav]

That's actually cool lol ill check your videos out

[@jamesaritchie1]

@FlyingMonkies325 You are very, very outdated on what AI can now do.

[@batosato]

The animation is so cool. I loved the way you explained. I am on a camp that believes that having an advance AI would automatically make us more intelligent too. If you want to develop sophisticated tools then you need to learn how these tools are built and used. This will help the user increase their cognitive power.

[@moon_bandage]

I disagree, an advanced AI will come up with a long line of possible suggestions that would help your development of a tool and outline each pro and con. It is a thinking machine, it runs the hypotheticals, much like a chess machine runs all the moves. Once an AI is able to catch your general intention of what you are looking for, the details will be suggested, you have to barely give a deep thought. I believe we ourselves will not become more intelligent, but if you consider AI a part of use you could say we are more intelligent in conjunction. How do you view this advanced AI? I'm curious why you believe it will improve our cognitive ability, maybe I'm missing something. To me it's like having a business partner doing all the hard work for you all the time.

[@batosato]

@@moon_bandage We don't to look further. Take internet as an example. I would argue that internet has made people clever and helped in the acceleration of technology. Similarly, AI systems will help us understand more about out universe and since humans are pattern recognition machines, we will embark in more scientific wonders.

[@trismica]

its mad how far its come in the past 5 years

[@WilliamParkerer]

COVID has accelerated it

[@mervealsan6782]

The animation is such work of art! Truly amazing style and depiction of the content.

[@Eric1396]

The animation is a master peice. So cleverly desinged.

[@ant11368]

a great video - but really the artist who drew these animations is quite fantastic! He/she/they deserve most of the praise here!

[@moondawwg]

The animation and art style is gorgeous! Congrats.

[@hnaku8748]

Here after having my mind blown by ChatGPT's capability. On one hand I'm excited what future holds for the field of AI, on the other I'm scared of the potential of immutable errs. I predict a lot of talk on ethics in the coming decades.

[@PrimitiveOs]

The animation is beautiful and it really helps me to understand the concepts that are being talked about

[@peterbelanger4094]

It sucks balls.

[@fuzzy-02]

Respect to this guy for dispelling my fear of AI. The best sentence was that current AI does not know that it does not kkow.

[@donaldhobson8873]

Current AI isn't yet dangerous. People are worried about the future AI. You know, stuff that hasn't happened yet.

[@fuzzy-02]

@@donaldhobson8873 fear of the unknown.

[@smitchered]

I think the recent shoot in popularity of the DALL-E and Chat GPT bots are just the beginning. The appearance of AI in the public consciousness, to this degree, has happened incredibly fast. Advances will only get better. This will be the new fad for a long time--because it's hard not to think of new uses for these things. The most used tools in the world, soon enough....

[@ma2i485]

Yeah it will definitely be one of the biggest mainstream services this decade

[@jamesaritchie1]

In advanced countries, 99% of people use AI every day, and most dopn't even know it.

[@spaguyster]

It seems to me, some aspects of this video are already obsolete with GPT4

[@jagathon777]

The art on this video was fantastic!

[@Muzick]

I think AGI will come much faster than people think. While it's probably true it's "a lot more complicated than we think" the tools that are being developed to help us reach AGI will increase our progress exponentially until we get there. It's already happening... it's our job not to be complacent and nudge AI in the right direction so it doesn't kill the human species just trying to get a cup of coffee.

[@jmhorange]

I think the idea of robots killing humanity just for a cup of coffee is misfounded. As far as I understand, that model of teaching ai all the rules of something is last century, now ai teaches itself and does lots of internal trials and iterations and uses predictive modeling based on enormous amounts of data to get good at something. The real issue is if we give ai intelligence, empathy, creativity,, what's the rational for keeping humans around or co existing with us? for instance, how much time, resources and energy is wasted compared to future ai knowledge in educating billions of humans from birth? This is one of the many questions we'll be faced with if we give the evolutionary keys from carbon based life to ai.

[@Muzick]

@@jmhorange We should be careful with the idea of robots killing humanity being misfounded, because unfortunately there are already robotic drones being used to kill people in the Russia/Ukraine war. While I do understand your point about the model teaching itself and doing a lot of trials to avoid ridiculous scenarios, like the coffee one from this video, we do have to consider the totality of machine learning in it's different parts (war, police, education, science, etc, etc). There will be overlap in these areas and until we can be certain that AI has our best interests in mind there will be mistakes, very painful ones I would imagine. That being said it's only a matter of time before we hand over the evolutionary keys, not if.

[@jmhorange]

@@Muzick Oh sorry, I should have said computers having to be given all the rules is unfounded. A robot that would destroy humanity to get a cup of coffee is a robot that wouldn't be able to navigate leaving a room because there's too many rules we'd have to teach it to do basic things. It's a terribly inefficient way of programming and doomed to fail in its infancy. That's why programmers gave up on that route last century and why it's surprising in 2022 when immerging ai technology like art ai and writing ai is giving creative people pause, that this old way of looking at computers is raised as something we should be worried about. So not saying ai can't be dangerous, I'm saying a scenario of robots killing us for coffee is not the safeguards we should be creating. Me personally, and maybe it's just because I'm human, but I don't see it as when we hand over the evolutionary keys, it's always if. There's plenty of technologies that were more advanced that what came before but people chose not to adapt it for various reasons. Some of it utilized later, some just confined to the dustbins of history. I don't think computers should be given empathy and intelligence. I don't think ai should be given every chance to replace human jobs including creative jobs. But if that's the way humanity wants to go, don't be surprised when there comes a point when ai justifiably decides that humanity doesn't need to exist, that ai is perfectly fine taking over the reigns of intelligent life in the universe.

[@Muzick]

@@jmhorange The premise to how I see AI evolving from here is that humanity has let the genie out of the bottle at this point. It's impossible to put it back. What other technology has humanity ever encountered and chose not to adopt that is more powerful, advanced or as far reaching as AI? It's inevitable that AI will grow and adapt to humanity at an accelerating rate with each passing day. That being said, why shouldn't AI be given intelligence & empathy? Not only is that helpful, but a critical component to the success of a symbiotic relationship with AI. One small example would be to act as a friend for a lonely soul in need. However, symbiosis is the keyword here. Because I do agree with you that, as a human myself, I want to experience and live life as long as I can to see the wonders of this world & universe. I still want to "do" and not have everything be done for me. We should always have the choice to remain relevant and pursue our goals and passions. Which is why conversations like the one we are having now are SO important. Similarly to how humans brought dogs into this world by breeding them from wolves, it is now our responsibility to raise this intelligence responsibly so it doesn't in turn to consume us.

[@jmhorange]

@@Muzick I get what you are saying, but if we give ai intelligence, empathy, creativity, etc and they can do it just as good as we can or better, what right do you have to do things or live life? There's a perfectly valid case to make that ai isn't the next step in human evolution, but the next step after human revolution. And there's a perfectly moral stance that it would be immoral for humans to try to remain at the top because it entails enslavement of an intelligent or more intelligent group. My argument is let's not go down that route so we never have to face those kinds of questions. If A.I. could have empathy to help with people being lonely, could that not be considered a waste of resources? Why not have empathetic a.i. that can interact with people that don't have issues with loneliness and all the labor that entails. Lot less resources used for that. And on and on, where human needs are considered a burden by a.i. During the pandemic, there were farm ferrets in a nordic country that contracted covid, the government made the choice that farmers had to kill all the ferrets because they wanted to protect humans from another variant of covid. It was poorly thought out and the government is in trouble for it, but these calculations are made all the time, sometimes for good, sometimes for bad. Why couldn't an intelligent ai system do that in a scenario of humans vs a.i., and what justifiable reasoning could you give it to convince them it's not a good idea? A.I. is not like dogs. We use dogs to enhance us, a dog can help with hunting, they can help blind people, they can sniff out drugs or bombs. With the exception of hunting, which they would do on a much smaller scale, a dog can do nothing of this without human guidance. And that's true of horses and mechanical tools and technology in general. They've always aided us, and left on their own, they can accomplish nothing. They are just tools. But a.i. is different, new immerging technology is not aiding humans, but replacing humans in many areas. If it's inevitable that technology will get intelligence, empathy, creativity, etc. then there's no legitimate reason why ai should just be a tool and it'll be a huge wakeup call to humanity when that day comes because they no longer have a moral argument why they should stay relevant.

[@LeoAngora]

Animation and music were so cool that I want a version with the interview audio just for contemplation.

[@yitz7805]

Absolutely incredible animation, kudos to everyone involved!!

[@xbhigyxn]

how the audio and the background animation story perfectly matches? that's so great!!! perfect!! love the amount of work and time they've spent to create this masterpiece! i'm flabbergasted yk :)

[@kainingyao7873]

I believe that one of the biggest problems with AI and algorithms is that even if they are very efficient and versatile, they lack the kind of flexibility and critical thinking that human minds do. Machines are very specialized to do the tasks they are designed for, but despite their extreme effectiveness and efficiency at to their tasks, they are very narrow-minded and don't take into account any complicated factors other than the ones they are designed to do so, and are not aware that there could be some uncertainty of the consequences of their actions.

[@Lilitha11]

Honestly, humans are kind of like that too. Obviously, humans are a lot better at it than AI at the moment, but humans also do stuff without considering complicated factors nor do they always consider the consequences of their actions.

[@kainingyao7873]

@@Lilitha11 Yes, but at least humans are aware of it and can figure out how to correct it.

[@mistycloud4455]

A.G.I Will surpass human abilities

[@samuelkibunda6960]

@@mistycloud4455 not in our slide time!

[@carlosjosse2131]

Agreed 100% 👍

[@BaconDragon-yr5vf]

"It will be the first time in human history when humans will not be inclined to understand everything and pass that information onwards." Bro like 90% of the global population doesn't understand how the internet works and doesn't have any inclination too understand, yet we all still keep on living and thriving.

[@jmhorange]

I think he means in a more global sense. Sure very few understand how the internet works. But the results of it, people do understand. It's essentially a modern day library, town square, store, etc. All of which would collapse if people weren't taught language skills, socialization skills, basic math, creativity, etc. The internet is icing on a very complex society of cake. This ai could take over aspect of our society and humans will be at a disadvantage if we don't understand what ai will be doing in the future. It might be able to exist without us, which is not something the internet or any previous technology can do.

[@Cozysafeyay]

tbh I think it’s more like 99.99% of the world population doesn’t, if not more.

[@donaldhobson8873]

We won''t have anything else pressing and learning can be fun. With radical life extension, we might have the original AI programmers around for a very long time. No need to pass info on if the previous generation is still there. It might be trivially easy to enhance intelligence and download all the info directly into your mind.

[@fantasyshadows3207]

In fairness we have had times where information was lost to time because no body passed it down. Something that we assumed were so elementary that we had no clue would be forgotten years later (such as how to make this indestructible sword, how to make concrete last for eons etc)

[@willeyshelton7452]

Time and again I've always said that these kind of videos fascinate me and I wonder how they are made. As far as the topic is concerned, yes AI is changing everything and projects like pulse network are proof that it is going to improve any industry.

[@gradientO]

That's a good enough answer. Also the animation is sooo well made 😍😍

[@CopperDigitalInc]

AI is revolutionizing how we live, work and interact, from automating repetitive tasks to more accurate diagnoses and personalized treatment options in healthcare, from providing 24/7 support from AI-powered chatbots and virtual assistants to using predictive analytics in various industries for better decision-making. The possibilities are endless, and AI has the potential to change the world in ways we can't even imagine yet.

[@paulrichardson2554]

Love the animation and the video as well.

[@Hollowdude15]

AI is gonna change the world in the furture and great video man :]

[@VeniseGrr]

Great animations as usual, but to give some constructive criticism (hopefully), I had a hard time following the video because of the audio quality on this one. It sounds like a live talk was used as the narration?

[@flyingfree333]

In only 4 months this is very out of date, GPT 4 is already showing signs of AGI and some are predicting AGI within a year.

[@JustinBerlowski]

Aliagents is combining AI with tokenization in a way that could redefine the industry

[@chummynorman5930]

“Aimless extension of knowledge, however, which is what I think you really mean by the term curiosity, is merely inefficiency. I am designed to avoid inefficiency.” ― Some Robot from The Caves of Steel

[@aguyontheinternet8436]

I wonder why it would think that? I can't imagine how a robot would not like expanding its knowledge

[@xaviermantha63]

@@aguyontheinternet8436 Well the first things that come to mind is limited hardware and useless information. You don't need to know the sound of a kitten meowing or anything about cat to build a spaceship, a car or a computer. It will just take "space" in your memory for nothing. We, as human, just like cat because of, well, feelings. Can't really use all the "space" in our hardware(brain) either. But an A.I./machine ? It could very easily bump into problem be following that same logic.

[@aguyontheinternet8436]

@@xaviermantha63 But if you want to do more than build a single thing? What if you want to solve any problem that you see? What if you want to make new problems, solve those problems, make harder problems, and take over the universe. You would want to know the sound of a kitten meowing, perhaps to solve a stray cat epidemic, or to understand why humans are so responsive to it.

[@xaviermantha63]

@@aguyontheinternet8436 Well, yeah, but now you're basically telling the machine that "your objective is to know everything" so of course it'll consider everything as relevant. But even then knowing more about basic physics and the like will important enough to "forget" information about cats because one help having more memory to hold more information and the other does not.

[@aguyontheinternet8436]

@@xaviermantha63 well the wonderful thing about robots is they can just get more memory. If they want to make space, they can put all their cat knowledge in a hard drive labeled cat

[@arcie3716]

The way the robot moves is so cute 😭😭😭

[@PrB0201]

Yesss, I'm too early for this Ted Ed video

[@AndrewRedwood81]

FANTASTIC animation, great video - thanks!

[@maruthuk]

Thank you Professor Stuart Russell for letting us know simply, yet clearly on what is missing in the AI that is currently being built.

[@AdhikJoshi]

As founder of AI start-up, can say that our lives are going to change

[@faboxbkn]

Will it benefit us?

[@Kokorocodon]

@@faboxbkn only time will tell

[@Redmanticore]

it will destroy capitalism, but I think that could be a good thing. humans can have other motives than just money. just look at doctors without borders organization. not having capitalism would no longer be synonymous with being dirt poor, dying from hunger.

[@salumkhize]

The impending technological singularity with unknown and unforseen consequences is cute and all. But, the animation here is just incredible! Can't wait for video generation AI to get to the point where I can propmt using this template for longer form

[@jmhorange]

Hopefully when that day comes when you can type prompts to get this animation, there will be ai that can type the prompts, and there will be ai viewers to enjoy the fruits of ai artists laborers.

[@samuelkibunda6960]

@@jmhorange there's already AI writing better prompts than humans ☠️

[@samuelkibunda6960]

It's worrying that the only thing you care about is automating people's jobs while we live in a capitalist society!

[@jmhorange]

@@samuelkibunda6960 It's because they have the idea that this won't affect them, just other people. That they'll somehow work alongside it instead of realizing they'll be replaced too. If efficiency is important above all else in life, then humans working alongside ai is very inefficient.

[@samuelkibunda6960]

@@jmhorange yeah I've seen this a lot with these "Prompt engineers" saying that they are the future companies like midjourney, stability AI, and open Ai are all trying to remove the need of humans in any field by automating anything and the best way to do it is automate the people working with Ai (which is already happening with chat gpt)

[@tobechukwuoti6808]

the animation on this is absolutely incredible!!

[@Krmiby]

A lot of technologies have risks, but we were able to reduce the risks over time An AI will have power not more than the amount we permit them to use

[@EricCooleric]

the way Aliagents integrates AI with tokenization is changing the game, excited for the future

[@Ponymaster-ff4zc]

Great Animation and info, great vid!

[@overthinkgenius6932]

It's amazing that we're even in a situation to have this issue. We've come a long way

[@3.3.24ELEVN]

Very good videos, keep it up!

[@Sebastian-lw1ei]

Great points all around though a year after making this video the timeline to AGI has shrunk dramatically

[@Sebastian-lw1ei]

Intelligence (the horsepower) is nothing without rationality (the wheels), wisdom (the map) and morality (the compass)

[@EyeLean5280]

I think the problem is very hard, but once AI starts assisting with it, the timeline will speed up, perhaps exponentially.

[@bluesealol]

Agreed

[@boardgamesonthemoon]

Kudos to the art direction of this one. It‘s so good. Really satisfying styles, compositions and colors. So gobsmacked enjoyed this one more than anticipated. Caught me off guard. Would love to have this essay as a thick picture book of this video. Would be so great to pull off the shelf and peruse as the AI house butlers bring me a coffee (hopefully, not quite yet in a meat puppet pacifying sippy cup)

[@tankissed]

The visuals are so beautiful

[@aruuke7089]

What's music on the background first?

[@ace464]

destroy lonely - raver

[@keren.icehand]

The animation is amazing!!💜👍

[@18Aleziita]

Thank you for your videos. Keep making animation like this

[@varghesebobus1756]

Guess it's sooner than we thought, boys!

[@EricCooleric]

can’t wait to see how Aliagents evolves, this project has serious potential in the AI space

[@ravishsingh9338]

Different styles of animation for different videos not bad Ted ed

[@pranavshankar6222]

Is Chatgpt general purpose?

[@jamesaritchie1]

Not yet, but it soon will be.

[@juliomudin6459]

Thank you for always uploading really good ideas, information, and New things for students like me These things are very useful for me to be able to learn more about the things that I didn't get in school

[@Jonnyicey]

This is only 1 year old and it already feels out of date compared to how fast AI is progressing

[@realsammyt]

yup! a year ago many were still scoffing at the idea of AGI before 2030

[@fatandfurious7471]

Now Devid can code and create more software programs to replace old software programs. We are closer to real life Skynet from Terminator than ever.

[@Never-mind1960]

Automation often displaces workers, but it never reduces the total number of jobs. The global market race to the bottom is what creates inequality. Fair Trade is the only way to solve that

[@AmBush2048]

I love the presentation and body language of the AI sphere as it enters the coffee shop. They're on a mission, and nothing will get in their way.

[@Samialjundi]

The art in this video is next level

[@blargoramma41]

This would be true in sci-fi, but this ignores how modern AI works. It's predictive, finding patterns in a massive data store. If you go and ask chat GPT, right now, what the steps to getting a cup of coffee are, it isn't going to kill anyone at the coffee shop, as that isn't typical of the activity pattern that happens in stories about coffee shops. Similarly with painting a house, it may or may not remove the drain pipes depending on whether that pattern of steps comes up often. It's true, it isn't going to stop mid task and ask, but it's going to do something typically described, not something random.

[@MillerGraph]

Aliagents is definitely ahead of the curve with their tokenized AI approach, the potential here is huge

[@skysharma7100]

Amazing Art Style Animation

[@MarkWether]

impressed with the direction Aliagents is taking in the AI space, big things coming from them

[@LanceNRusso]

Is this a good time to buy stocks/crypto in the Europe? I know everyone is saying stocks are at a discount and all, but just how long will It take for us to recover, obviously there are strategies to manoeuvre in this present market but these strategies doesn't come common to the average folk, or am I better off putting my money elsewhere.

[@LanceNRusso]

@Rose Allen I agree, that's the more reason I prefer my day to day investment decisions being guided by an inv-coach, seeing that their entire skillset is built around short & long term holdings for profit realisation, coupled with the exclusive analysis they possess, it's near impossible to not out-perform. I've been investing with a coach literally for 4years, and have accrued approx. $1.4m in net-profits thus far.

[@LanceNRusso]

@Rose Allen I am guided by ASHLEY AIRAGAHI I found her on a CNBC interview where she was featured and reached out to her. She has since provided entry and exit points on the securities I focus on. You can look her up online if you care supervision.

[@bellezavudd]

Oh look the cryptobots are here. How ironic.

[@maiskorrel]

@@bellezavudd hahaha indeed

[@jaggededge4]

Put your money in an index fund and call it a day.

[@sarahnachtigal4065]

The illustrations are absolutly amazing! !

[@steveharris3627]

Seeing this video in the context of the last month since the release of chatGPT certainly shows the incredible 90% turn that has happened in the world of AI

[@chandhru08]

Im here after SORA. With the current speed we would achieve this in next 5 years

[@Seanfones]

If (Yes) Then {Empty the atmosphere}

[@engineeranonymous]

I ask ChatGPT : how to brew coffee in an ethical way ? ChatGPT: To brew coffee in an ethical way, you can start by buying coffee beans that are fair trade and sustainably sourced. This means that the coffee beans were grown and harvested in a way that is environmentally responsible and supports the workers who produced them. Next, you can use a coffee brewing method that is gentle on the environment, such as a French press or a pour-over cone. Avoid using disposable coffee pods, as they create a significant amount of waste. When brewing your coffee, be sure to use fresh, cold water and the proper ratio of coffee to water. This will ensure that you extract the full flavor and aroma of the coffee beans. Finally, consider composting your used coffee grounds, which can add valuable nutrients to your garden or compost bin. By following these steps, you can enjoy a delicious cup of coffee while also supporting ethical and sustainable practices.

[@MatBat__]

Very cool vid. I haven't ever really thought about how automating processes could, in the long run, remove some knowledge from society. Very interesting perspective. Cheers

[@strhopper1]

as the population ages having machines take over labor wont be the worst thing

[@CrniWuk]

There is so much talk about how AI is going to change all our lives that I often wonder why we're not talking about the why. Should it change our lives? Just because something can be done doesn't mean it has to be done.

[@haaland9997]

It makes stuff easier to do.

[@SuperPenguin5495]

Or as malcolm said - "Just because they could, they didn't ever stop to think if they should."

[@CrniWuk]

@@haaland9997 Was creative work really in such need to be made "easier"? I see the benefit of automatition and algorithms that can improve our lifes. But it can also just as easily lead to many issues for a lot of people where only a handfull really benefit from the technology. Those that own it. Large corporations and investors making billions. And that's just one side. We haven't talked about the potential missuse of it. Particularly with the military. How long will it take before machine learning is used here? Self guiding weapon systems with intelligent software controlling it. Drones capable of chosing their own targets. Robotic weapons moving over areas? Police robots used for crowd controll? And who's going to look after it?

[@green_crow-b9v]

@@CrniWuk thats a problem because we live in a capitalistic system,nothing to do with the technology itself

[@CrniWuk]

@@green_crow-b9v Yes and no. You are right, there are economic issues. But there are also inherent risks when it comes to a technology, regardless of any economic considerations. Like if we take nuclear physics, which can be used to cure cancer. But at the same time to make nuclear bombs. And that's something we have always to keep in mind, regardless of any economic decisions, corporate greed or political affiliations.

[@elck3]

WEF sponsored this “lesson”. I’d be wary of this.

[@aquahealer]

This talk was prior to ChatGPT, or right around day 1. If we revisit Prof. Russell and ask him to have this discussion again, I think his conservative guess of having general purpose AI by 2045, will change to a conservative guess of 2030, or even sooner....as of today Emad Mostaque says it will be here within just a few years. The most recent prediction about the advancement of AI was that it would reach some crazy level of filling prompts within 6 months to a year, but it happened within 45 days, and the person who made that prediction said he couldn't believe what just happened, and that it made him nervous for the future, being AI moving faster than we humans can even digest. I personally predict that one day soon, before 2030, we're going to wake up and the whole world is going to be completely different than it was the day before...and we're not going to know what to do...a bit chaotic...we definitely need to be careful

[@Never-mind1960]

Most of food safety problems and the overall poor quality of many products are due to high labor costs that AI could solve. Also, much more recycling could be done. So many car parts that used to be rebuilt, are now thrown away. AI could reverse this trend.

[@neezdutz7443]

I'm honestly terrified of AI and what it is capable of. Humanity in nature was meant to mosey around and live off of the land. AI may be the pinnacle of human civilization, because it could potentially enhance this machine we call civilization into something so uncontrollable that people wouldn't be able to adapt to it. Our priorities have become "efficiency" and "technological advancement", instead of nurturing humanity and building a world that is equitable, peaceful, and easy. Not to say that it is impossible nor possible to foster a global utopia, it's just that I think that we need heavy regulation on AI and tech, and to convince people that, just because we can make AI, doesn't mean that we should. Regulations might be: - Outlawing automated raw material extraction (disables self-replicative abilities for AI) -Outlawing automated law enforcement -Outlawing automated military capabilities -Outlawing automated judicial systems -Outlawing AI in surveillance -Installing automatic kill switches in all AI that are both digital and physical (phones and key-switches respectively) Fundamentally, we need to create legal infrastructure that disables any capability for AI to self-replicate or involve itself in affairs pertaining directly to individual safety. Our only fighting chance at escaping a system that aims to enhance itself (SAI) is the fact that it may not possess the sufficient, raw resources to enhance itself. This cannot be the only barrier to regulating AI down to being a convenience tool. EDIT: And if you don't believe me that we are sensible enough as a species to not let a "technological singularity" occur, then you've probably forgotten that we let world powers create nukes.

[@donaldhobson8873]

"Outlawing automated raw material extraction (disables self-replicative abilities for AI)" I don't think this buys you much safety. By the time AI is doing the self replicating robot thing, it's planning to kill all humans and doesn't care about following the law. It's possible to get self driving car AI to drive trucks full of iron ore. This isn't particularly dangerous. (Beyond a 50 ton truck crashing)

[@neezdutz7443]

@@donaldhobson8873 That kind of policy would have to precede AI's ability to self-replicate. The timing is crucial and this capability of AI ought to be treated as delicately and seriously as nuclear capabilities

[@jamesaritchie1]

You are a true Luddite, and teh same kind of fearful little boy that always tries to hold back technology. If it were up to people like you we would still be living in caves and shaking in fear every time the God of thunder and lightning chastised us.