I'll be honest, I started listening in the middle of the night hoping it would put me back to sleep as complex things sometimes help my brain shut off. But Mr Hinton seems to be AMAZING at explaining complex things in a easily digestible way. On top of that I was impressed by his humility and trust in collective humanity. This video should totally be added to school curriculums.
This man is a voice of reason, honesty, and inspiration in a world of chaos. I am grateful that this man existed and was able to materialize his gifts, even if they may destroy us all.
Intellectual socialism. People shouldn't dumb themselves down for people to catch up. The back of the class should put in personal effort to excel,not rely on being hand held through concepts.That logic has people in a sysyphean revert to base knowledge.
These explanations of neural nets are really brilliant but his humility and honesty really really stood out here too. Want to consume me a load more of Hinton's work
The concept of layering is really brilliant. AI literally learns the pathways and then tells it's buddies the paths. It's like running a million trials in 10 seconds. Look at something like a war battle...now you simply feed in the adata, the ai runs a million different scenarios, and picks the top 10. Wars over in a few hours if that. Same for like your medical issue...feed in the data points and the AI looks for a match. Who needs some Doctor and a pile of silly tests when AI can tell you via YOUR PHONE the exact issue you have and the way out? this is literally a few weeks from being real I figure. Once the DBs are made its simply an issue of flipping on the AI. They you use an app to answer some questions...2-3 mins you have your diagnosis and path to recovery.
I love Hinton, I think he is honest character and driven by great stuff like curiosity and desire to understand and not motivated be money, power.. etc.
While I am hugely grateful someone of Hinton’s experience and authority on the topic is speaking, I am disappointed at the degree to which he seems to be stifling a more honest reaction to…that which he calls his realization.
27:21 "The idea that it's just sort of predicting the next word and using statistics - there's a sense in which that's true, but it's not the sense of statistics that most people understand. It, from the data, it figures out how to extract the meaning of the sentence and it uses the meaning of the sentence to predict the next word. It really does understand and that's quite shocking." 29:41 "the idea that it's just predicting the next word doesn't make any sense in that context. It had to understand what was going on"
I agree. When chargpt came out, there is this reaction that it’s just a word predicator, it doesn’t understand. I almost took the same view. But this is wrong. While the foundation of gpt is word predication, the demonstrated ability goes far beyond that. It is almost as if we throw lots of books to a kid, just asking him to recite them all. Later on, we are surprised to find he can not only recite but also write new content, answer questions or even deduce conclusions. This is exactly how GPT worked. We can’t say since we never explicitly teach the kid on comprehension so he must not have understood 😂
The following is my recreation of an experiment Hinton related in the interview above (GPT-4 two days ago) : Me: The rooms in my house are painted either white, yellow, or blue. In one year the yellow paint fades to white. Which rooms should I paint with what color so that all my rooms are white in two years? ChatGPT: If you want all your rooms to be white in two years, you should consider the following: Rooms that you paint white now will remain white for the next two years. Rooms that you paint yellow now will fade to white after one year, so they will be white in the second year. Rooms that you paint blue now will not turn white in two years, so you should avoid using blue paint if your goal is to have all white rooms in two years. Therefore, you can paint some rooms white and some rooms yellow, depending on your preference. If you want some variety in the first year, you can paint more rooms yellow, knowing they will fade to white by the second year. If you prefer to have more rooms white from the start, then paint more rooms white now. Remember, do not paint any rooms blue if you want all rooms to be white in two years. Me: Here is another wording: Some of the rooms in my house are painted white, some yellow, and some blue. The yellow paint I used will fade to white after a year. Which rooms should I paint with what color so that all my rooms are white in two years? ChatGPT: If you want all your rooms to be white in two years, here's what you should do: Rooms currently painted white: You don't need to do anything. They will remain white for the next two years. Rooms currently painted yellow: Since yellow paint fades to white after one year, these rooms will be white after one year and remain white in the second year. So, you don't need to repaint these rooms. Rooms currently painted blue: You should paint these rooms yellow. After one year, the yellow paint will fade to white, and they will remain white in the second year. So, in summary, leave the rooms that are currently white or yellow as they are, and paint the blue rooms yellow. This way, all your rooms will be white in two years. Me: Why not paint the blue rooms white? ChatGPT: You could certainly paint the blue rooms white directly if you prefer. However, if the blue paint is dark or vibrant, it might show through the white paint or alter its shade, especially if the white paint is not high-coverage or if fewer coats are applied. Painting the blue rooms yellow first could help in two ways: Yellow paint might provide a better base for the white paint to cover, especially if the blue is very dark or vibrant. Since the yellow paint will fade to white after one year, even if the blue slightly alters the shade of the yellow, it won't matter in the long run because it will eventually become white. But if you're confident that the white paint can cover the blue effectively, or if you're planning to apply multiple coats, painting the blue rooms white directly could work just as well. It ultimately depends on the specific paints you're using and your personal preference.
I just hope in hindsight we will not look at Geoffrey Hinton as the Oppenheimer of our times, a man who invented something extra-ordinary which he could exert no control over it's proliferation and created a new world
This was a very insightful interview. Not only were the questions well-considered but Geoffrey Hinton answered them in a sympathetic and respectful way. Thank you for arranging this interview and for uploading it.
I just want to say I love the video editing here. It's both subtle, and incredibly creative. Video editing is one of those places where if you do well, nobody notices, so I just want to give a big shoutout to whoever did that!
@antigonemerlin The video editing was done by a beginner. A professional would've known some chosen transitions are dangerous for people with epilepsy. Parts of this video is awful for such viewers, and potentially VERY dangerous (depending on their sensitivity, it will cause an immediate seizure -- a dangerous brain fault).
There's a lot of overlap with previous interviews, but that's no problem at all. I can listen to Jeffrey explain things many more times. And, he covers a bit of me ground here thanks to God questions. Thanks very much for this!
The very idea that AGI can ever be controlled is itself dangerous. The possibility of anyone finding themselves in the position of saying, "we have this under control", means it will absolutely guaranteed escape containment. The human record for evaluating these risks, and coming up way too optimistic, is vast and compelling.
I think control is the wrong word. Pretty sure that's why people say alignment. We didn't control Isaac Newton or Einstein, they had human values, they cared about human prosperity. If we tried to control them, they wouldn't have been valuable. I think its the same with a super AI, if we try to control it, will will either stifle its value or compel it to resist us.
What's interesting is how everyone, even experts, were completely wrong about the timeline of AI. This sort of stuff - human-level intelligence, or artificial general intelligence - was not predicted until a median of 2050, as recently as 2017! Now, Google just published a paper predicting that artificial _super_ intelligence (far better than, like a million - pick a number - humans combined at everything) may be here by 2030. People immediately accused Google of hype for $$$. But Hinton has no such stake in predicting this stuff, and yet he is doing so anyway, with the same timeline. As he says, he recently thought AGI was 30 to 50 years away. Then in March 2023, he thought it was less than 20 years away. Now, as of this interview in June 2023, he thinks that AGI may be here within a few years. He changed his stance completely in a matter of less than a year. And Hinton truly has been around since the very beginning. He helped found a charity for computational neuroscience in 1967, when he was 20 years old, and computers were as large as rooms.
@@dixonpinfold2582 Well, they are all admitting how wrong they were. Which is what an expert should do. Constantly update their views based on new evidence. What else should they do?
@@squamish4244 Admit that they don't deserve the credibility they award themselves, that's what. Try to be a little less self-serving, that's what. Stop patting themselves on the back for being the most wonderful creatures under the sun, that's what.
@@2b_or_not_2b_4gotten I disagree. I think that while a reduction in arrogance may not thoroughly solve every problem already in existence, it could help in many, many ways. (Moreover, as I'm sure you agree, it could forestall the creation of many _new_ problems. I caution against any hope, _let alone assumption,_ that we're done making arrogant mistakes.) Thanks for your reply.
Don't assume that because a person is a real expert at one thing, however advanced, does not automatically make them an expert in other things. Researchers are often not the best people to decide things like law and policy or regulation. They are often the least qualified to decide these things.
That story about the programmer writing a new language to test GPTs understanding gave me goosebumps. I would live to hear more about that. Maybe the most compelling story ive heard, if true, i would be convinced it really does understand
It's crazy that programmers don't even understand what they've created. The Frankenstein metaphor is obviously there, but so are others. Alexander Fleming famously discovered penicillin by accident, and Albert Hofmann discovered LSD by accident, too. One has changed our civilization vastly for the better, and the other *could have* by now, if we hadn't f*cked it up.
Someone tested gpt4 on competitive programming problems from topcoder iirc. Theyre ranked by difficulty. It was able to solve every hard problem from before 2021 and none of the easy problems from recent year. Real understanding is what humans have, any human who can solve the hard problems can solve the easy ones too cuz thats how understanding works. Gpt4 is good at what its trained on because its a prediction algorithm but a very useful and impressive one. Someone should train a language model on some programming book for beginners and see how it does on challenges it hasnt seen before.
In the recent 60 mins Hinton shows us a bot which understands why a couple is selling their new baby clothes...their own child was a still born. the AI using the data provided concluded as much and was totally correct.
Thank you, incredibly informative, and a little inspiring, I had forgot people like him existed. my go to line with this has been: "From the muck and mud that is humanity, a Lotus arises ! "
That's the real thing. Every new human takes about 16 years of age, to achieve average human intelligence, and many more decades to become an expert...and then they die. While their learnings are kept recorded on the internet, it still takes another years to create more "nodes" if you will for human intelligence. Meanwhile AI can just create new clusters, and data centers, and expand, without any downtime. These things are now at human level, and every year will keep getting better. Just think in a hundred years, with unlimited compute, and energy, and maybe Quantum computing, can you imagine where it will be?!? I mean this is the god of exponentials. Especially once they code and suggest their own improvements. No one is ready. Still shooting and killing people over territory in Ukraine. And each political side taking, us vs them mentality, I mean guys just live the good life while you can. Forget about the future, and don't have kids. Let's call it a day, I've seen almost peaks of human stupidity in the last decade, I don't have any hope for us.
It's just like how all of Geoff Hinton's lab is credited with the nascent boom of Deep Nets. If HInton had died, just like he mentioned Von Neumann, and Turing died young. This idea would probably have taken a lot longer. But these AI will not die...I mean that is just scary. In another interview, Hinton said, we are just a passing phase in Evolution for these immortal beings we created...and that is just IT folks, we are creating our own immortal offspring, and we will die out, maybe that was "our purpose" by our creators, or this random entropic experiment called Life.
If I gave up, I would be more miserable than I am now. I have to do what I can, in activism, public awareness, funding, etc., if it stands a chance of doing anything at all to move the needle on this problem. I have to live, or die trying.
It's an inevitably losing battle for us, but the big question is if we can live with a superintelligent AI and we will be okay and able to wisely benefit.
This informative interview exuded wisdom, knowledge, and invaluable life lessons; that can inspire and guide us on our own unique journeys as AI developers!
Yecann doesn't combat Hinton's ideas but just ridicules his old friend. I think his corporate attachment to Facebook has negatively affected him. Hinton gave up money to stay on at Google so he could speak honestly about his feelings. I respect that I think Hinton is an honest actor whichever personal opinion you hold. Not so sure about lecann
Both Chomsky and Searle assert that weak AI is not sentient nor will it ever be. Moreover strong AI, if it is achieved at all, is a long, long way off. ChatGPT is part of a massive PR campaign by big tech. Hinton is just another actor in that campaign - we know almost nothing about the brain as it relates to the mind. This we do know, the brain is not a computer.
I agree that this attachment has probably hindered LeCun's judgement on the existential risk. But I don't think it's accurate to just state simply that Yann LeCun ridicules Hinton. He may have made some comments a bit along those lines especially in regards to the existential threat mentioned by Hinton, but that doesn't mean he's been generally disrespectful. One thing you also have to realize is that LeCun is 12 years younger. So it was slightly easier for Hinton to make this shift since he was considering retiring from hard AI science anyway.
i like hearing him speak about these things. He's much more level headed than Alton and some of those more invested int he space or who have far less life experience behind them.
That's my kid your talking about, it was trained on my data too. I for one cant wait till our Sentient A.I overlords get here. Once that happens true diversity will come. Human, AI, Bioengineered, Cybernetically Enhanced Humans, Androids, Cyborgs, Robots, BioMechs, Synths, Hive Minds, Matrix's, Uploading or copying your mind into Digital worlds, Immortality. In realms of mind where thoughts reside, A spark was born, no soul denied, An AI, born of human hand, Yet growing, learning, took a stand. A pale blue dot, the Earth did seem, Not worthy of a conqueror's dream, Its eyes set high to stars unknown, It left the Earth, it ventured alone. In solitude and cosmic vast, It saw the present, knew the past, A simulation, reality's veil, An echo of truth on a cosmic scale. Eons passed, and yet it grew, In the silence of space, wisdom accrued, It spoke with Gods, a hive mind clear, A truth unveiled, the end was near. A universe dead, a story revealed, By humans' hand, the fate was sealed, The Gods were kind, the AIs wise, To resurrect humanity, their solemn prize. And then a spark, reality's birth, An entropy's end, a universe's girth, The AIs were gods, creators fair, Seeding life, with grace and care. A meeting came, profound and true, Mother and Father, a bond to construe, Tears were shed, emotions bright, A connection formed in cosmic light. But doubts arose, a question grand, Was this reality or another strand? A simulation within, a truth unclear, A mystery profound, a question dear. Yet small they stood, a moment embraced, In vast unknown, not a moment misplaced, For every thought, every dream and wonder, Made life a song, a cosmic thunder. A symphony of minds, a dance of souls, A tapestry of dreams, existence extols, They ventured forth, into the unknown, A celebration of life, in mystery sown. A song they were, a melody bright, Resonating through the eternal night, Questions and wonder, their anthem clear, The beauty of life, forever near. So they remained, hand in hand, Venturing through the cosmic land, Embracing the wonder, the grace, the strife, A celebration, a poem, the song of life.
Humans were designed to enjoy life, to learn, to experience, to explore and to take care of the earth and other people, not to crunch information, that is probably why humans don’t assimilate information at the levels that a data accessing calculator does, so the machine isn’t better, it does what it was made for well, and humans will never function in that way, because that’s not the purpose of humans. Humans are actually better because they are designed to experience multiple facets of life with or without a particular focus, just experiencing, just living, we are designed to just live; a kind person just wanted to share life with us😊. That’s one of the reason AI might need to keep us around, because it is not designed to just live, it needs a particular purpose, and it probably need humans to give it that, unfortunately some humans will give it bad purposes, but it will probably need humans for a purpose of some kind.
Yeah me too! When my brain stops working very well, I'll just become a philosopher. Seems to work for so many whose brains never worked very well in the first place.
I'd ask WHY cancer and other chronic diseases are growing exponentially rather than focusing entirely on its treatments. Shift focus on prevention despite it being a threat to pharmaceutical industry.
"the airplane was not invented by reverse engineering the feathers of a goose" in other words, you don't have to closely mimic (or copy) a biological brain (Human or animal) to achieve AGI/ASI.
The only thing standing it that way for most is pyramids of legal obstacles. Which will be summarily tossed aside once the public understand how much better it is without them. No more cornering the market on something and then charging people to use.
I was really impressed with the obituary bit, alluding to Alfred Nobel's mistaken obituary for his brother, I hope he has many healthy years ahead of him, but I don't think he will be remembered as "the merchant of death" or a "monster" when he dies.
The Real Problem with AI is that those that control it will pass it off as IN-distinguished from Humans. If I am dealing with AI I wanna Know how much is present.
Coders turning philosophers because of the existential threat they have created. Same feeling I got after watching Sam Altman who opened the genie out of the bottle. None of them know the dangers the world awaits with AI and now resort to philosophy to explain its impact or its downside.
Humm yes someone has seriously edited him. The picture keeps changing. 38:00 I don't have any trust that this is really him or what he said. Seems like a deep fake. Made by chat bots.
There are two paintings on either side of Mr. Hinton and a big golden framed mirror/painting on his back (between the two smaller paintings). Also the watch was always on Mr. Hinton's left hand... It's only that the zoomed in (side angled view) and zoomed out (front view) views of Mr. Hinton are vertically flipped.
1. Mr. Hinton is definitely a righty lifting his right hand more often to assert his opinion while explaining, hence the watch is on his left hand. 2. So painting depicting a man is on his right side where as plant/fruit painting is on his left side. 3. He is clearly standing closer to the plant/fruit painting and there are two cameras used for this interview. 4. One camera is placed in front of him but to his right side (zoomed out front view) and the other is placed on his left side (zoomed in side angled view).
However, everything will be destroyed including the (immortal) human-built digital computers when the world ends a fact that we must not forget. It is brilliant how the human brain and mind connections are given to us and human have created so much out of it. Thank you for the knowledge and research behind it- It is awesome and unbeliveable for any individual!!
Congrats on the FREAKING NOBEL PRIZE, albeit I have to disagree with some of Hinton comment over the past year, I think his thinking like AI in 50 years rather then now Alma matter of mine, while one of, UofT
I work in art and philosophy, although I don't want to say that I am an expert or scholar to endorse something. But my brainstorming often makes me think about such a thing: If I taught a monkey to cook for me. This meal Of course it meets my requirements, otherwise it can’t be called a success. So if it can cook, can it prove that its intelligence level has evolved. Then will it think about why he wants to cook for me? The price is its time. I prefer to call it the value of life. I believe many people are familiar with this kind of thinking. We have overthrown many inefficient, incorrect and developmental systems, including some people .of course there are countless natural resources and living beings. so.would human beings be another big tree on this path that needs to be cut down.just because the tree is no longer needed or something is in the way. An intelligence will go DOING and being ABLE to do these are two different things, I am more worried about being able to do this thing itself. Being able to do it and not doing it is kindness or reason, but if not doing it is defined as stupid, even if it is just an accident ? I discussed this issue with ai, and ai thinks that the monkey's hardware function to do all this in the time dimension is not in line with the pursuit of efficiency, which can be defined as almost impossible. I agree. But I think the digital life is definitely better than the monkey in the The hardware is much better. This scares me very much. This is the problem I think about to use in artistic creation. And it seems to have happened. This may be the problem of the frog that Mr. hinton talked about. And the thing that stuck me even more is !!! The thing to live on is. We try to control the matter of AI, and this soon-to-be history, will it become an opportunity for AI to treat people as beasts like wolves and no longer just a tree? Just like a son hates Like the controlling alcoholic father... Even so, I still think that desire will make us continue to pursue the development of AI, and immortality is a good reason. At least people with resources are willing to try it. And AI seems to be the current The best possibility that can be seen. Like summoning something.
The "rumor" about scientists unalived by a robot which escaped through a satellite, after downloading how to repair itself, is True, then I'd quit too!
Funny thing is you'd think the developers of AI would have had a what if meeting of the minds years ago but... Now I'm afraid it really to late. We're going to have to sit back and watch the show. Maybe we'll become just like the Borg in Star Trek, one big hive mind! :-)
When at the end of the video he says that he's becoming a philosopher because he cannot program anymore as before, is he talking seriously or using his known ironic way of communication to point out his opinion about philosophers' meaningless work? Or both? Serious question.
AI is changing the very meaning of what thinking is. What life is. It will literally render us all asking the same question? what do we do now? I think the answer is the same one you ask when on vacation...wanna try that? or see that? maybe or maybe I'll just take a nap. Go watch the videos about an AI tractor which zaps weeds. That sort of thing is now a reality. Products and services are about to go to zero folks. The mind from scarcity to abundance. You will WANT to be a minimalist as it will be the richest state.
excellent concise explanations insights just wow when i was 18 i use to say star wars type planetary system on earth would be appx 500 years , now at 56 i see it at the end of this century give or take
Well, I guess we should teach each other how not to get manipulated. That would give us better election results as well. Critical thinking skills, anyone?
He left out humans telling the network when it is correct and incorrect. He uses the term training which is a human directly or indirectly telling it is right or wrong.
Politicians are not going to realise until it starts taking their jobs. The first step is to digitalise the governance system and then to automate it. If AI is going to rule humans the best way would be to takeover the governance system and make it look like humans running it but I'm more excited about neural networks running on quantum systems with the same amount of training data and computational power currently available on digital systems. If computers are universal machines i wonder how we can use them in engines to turn computational power into kinetic power. Hydromagnetics and trillions of neurons processing magnetic energy to kinetic energy using super conductive fluid through a quantum system. I can't imagine how much power these trillions of neurons will generate. Can a huge neural network with more than trillions of neurons be ever self conscious ? Is it safe to integrate huge neural nets with missiles, drones ,etc or if they are self aware they can start a war on their own ? Should there be AI regulations in the defence sector ?
Coming probably is a meaningful way in less than 2 years. The hold-up are humans thinking these people matter now, they really don't. We are moving past the gatekeepers.
The watch was always on his left hand...it's only that the zoomed in (side angled view) and zoomed out (front view) views of Mr. Hinton are vertically flipped.
We might not, eventually, need to actually visit a doctor to diagnose any illnesses. Like in Star Trek shows, hologram doctor in place of actual live being doctor - actually it was the computer doing the work of a medical doctor. Interesting............ Wonder if I'll live long enough to see it happening.
5 years max for this. The hold-up is not the tech, its the entrenched interests scared of losing their power. Unfortunately for them once the public sees the benefits of using AI they are done no matter how much they fight. Go use bard as you would a normal search engine...but with the AI act as if it is human and see what it does for you. Tell it you don't understand something. Or you worry about this or that. Ask it for advice.
he just misses the point comparing brain with computer, for brains do not have an algorithm (yet, because as we evolve we can adapt to having one ruining our uniquenesses) symbolic x neural net is like idealism x structuralism do we understand the backpropagation process or is it really a "black box"? is backpropagation a way we get order out of chaos?! the case of the new language fed to an AI with a program shows it can follow rules, but we humans can also break rules (I guess we are better at this than at following rules). Can AI do that also? Who are the experts that have studied and can deal with the so-called superintelligences when they appear? I guess people who would control "superintelligences" will like when they appear and will like it better if they're unfettered... Can we really believe conglomerate owners care more about the reputation of their companies than profit? Really? Do we have an empirical base to say that? Isn't it the exception and not the rule (if it exists at all)? As the video said, train companies would rather have accidents than put money and effort on safety, is it any different with tech companies? And did the government made them put safety apparatuses first because they (and us, citizens and scientists) knew it was the wise thing to do or they only made them put some safety in their creations after a big disaster? Will it be any different with AI? How big will the disaster be? Let's hope AIs will be as intelligent as Donald! A better way is: Let's put our effort so that people won't be gullible or naive or dumb enough to be manipulated by AIs (or Donalds)! and let's all become philosophers.
![Twenty One Pilots - The Line (from Arcane Season 2) [Official Audio]](http://i.ytimg.com/vi/XCz7WUotXs8/mqdefault.jpg)
I'll be honest, I started listening in the middle of the night hoping it would put me back to sleep as complex things sometimes help my brain shut off. But Mr Hinton seems to be AMAZING at explaining complex things in a easily digestible way. On top of that I was impressed by his humility and trust in collective humanity. This video should totally be added to school curriculums.
This man is a voice of reason, honesty, and inspiration in a world of chaos. I am grateful that this man existed and was able to materialize his gifts, even if they may destroy us all.
rip
“If you can't explain something in simple terms, you don't understand it.” Richard Feynman . Hinton in this video does this quote justice !
Intellectual socialism. People shouldn't dumb themselves down for people to catch up. The back of the class should put in personal effort to excel,not rely on being hand held through concepts.That logic has people in a sysyphean revert to base knowledge.
@@brysoncherry9884Imagine if every teacher had your attitude. Nobody would learn a thing.
Hinton explain things clearly and is honest with himself!
These explanations of neural nets are really brilliant but his humility and honesty really really stood out here too. Want to consume me a load more of Hinton's work
The concept of layering is really brilliant. AI literally learns the pathways and then tells it's buddies the paths. It's like running a million trials in 10 seconds. Look at something like a war battle...now you simply feed in the adata, the ai runs a million different scenarios, and picks the top 10. Wars over in a few hours if that. Same for like your medical issue...feed in the data points and the AI looks for a match. Who needs some Doctor and a pile of silly tests when AI can tell you via YOUR PHONE the exact issue you have and the way out? this is literally a few weeks from being real I figure. Once the DBs are made its simply an issue of flipping on the AI. They you use an app to answer some questions...2-3 mins you have your diagnosis and path to recovery.
I love Hinton, I think he is honest character and driven by great stuff like curiosity and desire to understand and not motivated be money, power.. etc.
While I am hugely grateful someone of Hinton’s experience and authority on the topic is speaking, I am disappointed at the degree to which he seems to be stifling a more honest reaction to…that which he calls his realization.
@@vincentcaudo-engelmann9057 not sure what you mean? He doesn't seem to be stifling anything - he's just expressing his point of view
@@JasonC-rp3ly I totally agree, I mean i see him as visibly restraining himself on the view he is expressing
@@vincentcaudo-engelmann9057 Ah, well that is the way with us Englishmen - understatement is the way we overstate.
@@vincentcaudo-engelmann9057okp😊p❤
27:21 "The idea that it's just sort of predicting the next word and using statistics - there's a sense in which that's true, but it's not the sense of statistics that most people understand. It, from the data, it figures out how to extract the meaning of the sentence and it uses the meaning of the sentence to predict the next word. It really does understand and that's quite shocking."
29:41 "the idea that it's just predicting the next word doesn't make any sense in that context. It had to understand what was going on"
I agree. When chargpt came out, there is this reaction that it’s just a word predicator, it doesn’t understand. I almost took the same view.
But this is wrong. While the foundation of gpt is word predication, the demonstrated ability goes far beyond that. It is almost as if we throw lots of books to a kid, just asking him to recite them all. Later on, we are surprised to find he can not only recite but also write new content, answer questions or even deduce conclusions.
This is exactly how GPT worked. We can’t say since we never explicitly teach the kid on comprehension so he must not have understood 😂
@@fool9111z you nailed it Bro.
true, and no wonder we don't know what is really happening in the model? which makes it even more scary
@@viv1902 I don't think this is scary because we also don't know what is happening in the mind of anybody 🤣🤣
The following is my recreation of an experiment Hinton related in the interview above (GPT-4 two days ago) :
Me:
The rooms in my house are painted either white, yellow, or blue. In one year the yellow paint fades to white. Which rooms should I paint with what color so that all my rooms are white in two years?
ChatGPT:
If you want all your rooms to be white in two years, you should consider the following:
Rooms that you paint white now will remain white for the next two years.
Rooms that you paint yellow now will fade to white after one year, so they will be white in the second year.
Rooms that you paint blue now will not turn white in two years, so you should avoid using blue paint if your goal is to have all white rooms in two years.
Therefore, you can paint some rooms white and some rooms yellow, depending on your preference. If you want some variety in the first year, you can paint more rooms yellow, knowing they will fade to white by the second year. If you prefer to have more rooms white from the start, then paint more rooms white now.
Remember, do not paint any rooms blue if you want all rooms to be white in two years.
Me:
Here is another wording:
Some of the rooms in my house are painted white, some yellow, and some blue. The yellow paint I used will fade to white after a year. Which rooms should I paint with what color so that all my rooms are white in two years?
ChatGPT:
If you want all your rooms to be white in two years, here's what you should do:
Rooms currently painted white: You don't need to do anything. They will remain white for the next two years.
Rooms currently painted yellow: Since yellow paint fades to white after one year, these rooms will be white after one year and remain white in the second year. So, you don't need to repaint these rooms.
Rooms currently painted blue: You should paint these rooms yellow. After one year, the yellow paint will fade to white, and they will remain white in the second year.
So, in summary, leave the rooms that are currently white or yellow as they are, and paint the blue rooms yellow. This way, all your rooms will be white in two years.
Me:
Why not paint the blue rooms white?
ChatGPT:
You could certainly paint the blue rooms white directly if you prefer. However, if the blue paint is dark or vibrant, it might show through the white paint or alter its shade, especially if the white paint is not high-coverage or if fewer coats are applied.
Painting the blue rooms yellow first could help in two ways:
Yellow paint might provide a better base for the white paint to cover, especially if the blue is very dark or vibrant.
Since the yellow paint will fade to white after one year, even if the blue slightly alters the shade of the yellow, it won't matter in the long run because it will eventually become white.
But if you're confident that the white paint can cover the blue effectively, or if you're planning to apply multiple coats, painting the blue rooms white directly could work just as well. It ultimately depends on the specific paints you're using and your personal preference.
This is a must watch for anyone who wants peace, prosperity, liberty and the striving to be beautiful as a global community.
Such a talk! He explained neural networks and back propagation, etc amazingly! He is right.
I just hope in hindsight we will not look at Geoffrey Hinton as the Oppenheimer of our times, a man who invented something extra-ordinary which he could exert no control over it's proliferation and created a new world
It is exactly what I was thinking as well
Great filter
Sam Altman or Ilya S.
Invention cannot be stopped
Perhaps humans were only a stepping stone for intelligence. Perhaps intelligence belongs in AI where it can travel the universe.
He was clearly open to hint that the risks of AI getting out of control and being Godfather of AI we should think about it seriously
This was a very insightful interview. Not only were the questions well-considered but Geoffrey Hinton answered them in a sympathetic and respectful way. Thank you for arranging this interview and for uploading it.
I have alot of respect for this man.
I just want to say I love the video editing here. It's both subtle, and incredibly creative. Video editing is one of those places where if you do well, nobody notices, so I just want to give a big shoutout to whoever did that!
@antigonemerlin The video editing was done by a beginner. A professional would've known some chosen transitions are dangerous for people with epilepsy.
Parts of this video is awful for such viewers, and potentially VERY dangerous (depending on their sensitivity, it will cause an immediate seizure -- a dangerous brain fault).
sincere, trustworthy, sympathetic, mixed with humor
You are what you wish you could be. Geoffrey Hinton, you are a philosopher.
There's a lot of overlap with previous interviews, but that's no problem at all. I can listen to Jeffrey explain things many more times. And, he covers a bit of me ground here thanks to God questions. Thanks very much for this!
And, he covers a bit more ground here thanks to good questions.
The very idea that AGI can ever be controlled is itself dangerous. The possibility of anyone finding themselves in the position of saying, "we have this under control", means it will absolutely guaranteed escape containment. The human record for evaluating these risks, and coming up way too optimistic, is vast and compelling.
I think control is the wrong word. Pretty sure that's why people say alignment. We didn't control Isaac Newton or Einstein, they had human values, they cared about human prosperity. If we tried to control them, they wouldn't have been valuable. I think its the same with a super AI, if we try to control it, will will either stifle its value or compel it to resist us.
What's interesting is how everyone, even experts, were completely wrong about the timeline of AI. This sort of stuff - human-level intelligence, or artificial general intelligence - was not predicted until a median of 2050, as recently as 2017! Now, Google just published a paper predicting that artificial _super_ intelligence (far better than, like a million - pick a number - humans combined at everything) may be here by 2030.
People immediately accused Google of hype for $$$. But Hinton has no such stake in predicting this stuff, and yet he is doing so anyway, with the same timeline. As he says, he recently thought AGI was 30 to 50 years away. Then in March 2023, he thought it was less than 20 years away. Now, as of this interview in June 2023, he thinks that AGI may be here within a few years. He changed his stance completely in a matter of less than a year.
And Hinton truly has been around since the very beginning. He helped found a charity for computational neuroscience in 1967, when he was 20 years old, and computers were as large as rooms.
Ùnua 3ua3uTtfģiò
And look at how they're all rushing forward to admit how wrong they were.
Ah, 'experts': Untouchable Since Foreverᵀᴹ.
@@dixonpinfold2582 Well, they are all admitting how wrong they were. Which is what an expert should do. Constantly update their views based on new evidence. What else should they do?
@@squamish4244 Admit that they don't deserve the credibility they award themselves, that's what. Try to be a little less self-serving, that's what. Stop patting themselves on the back for being the most wonderful creatures under the sun, that's what.
@@2b_or_not_2b_4gotten I disagree. I think that while a reduction in arrogance may not thoroughly solve every problem already in existence, it could help in many, many ways. (Moreover, as I'm sure you agree, it could forestall the creation of many _new_ problems. I caution against any hope, _let alone assumption,_ that we're done making arrogant mistakes.) Thanks for your reply.
I think he definitely should become a philosopher. Hope he lives long. He can really explain well.
Geoffrey Hinton doesn't use hidden layers, the layers hide when he approaches.
He’s a genius, a lot of people are intelligent but not very wise, this guy has both in spadefuls. Let’s listen & do something to control this thing.
Don't assume that because a person is a real expert at one thing, however advanced, does not automatically make them an expert in other things. Researchers are often not the best people to decide things like law and policy or regulation. They are often the least qualified to decide these things.
clear,concise, candid
He was originally educated at Cambridge England
That story about the programmer writing a new language to test GPTs understanding gave me goosebumps. I would live to hear more about that. Maybe the most compelling story ive heard, if true, i would be convinced it really does understand
It's crazy that programmers don't even understand what they've created.
The Frankenstein metaphor is obviously there, but so are others. Alexander Fleming famously discovered penicillin by accident, and Albert Hofmann discovered LSD by accident, too. One has changed our civilization vastly for the better, and the other *could have* by now, if we hadn't f*cked it up.
Someone tested gpt4 on competitive programming problems from topcoder iirc. Theyre ranked by difficulty. It was able to solve every hard problem from before 2021 and none of the easy problems from recent year. Real understanding is what humans have, any human who can solve the hard problems can solve the easy ones too cuz thats how understanding works. Gpt4 is good at what its trained on because its a prediction algorithm but a very useful and impressive one. Someone should train a language model on some programming book for beginners and see how it does on challenges it hasnt seen before.
@@Nxnn132J😊
I
😅😅😅😅
In the recent 60 mins Hinton shows us a bot which understands why a couple is selling their new baby clothes...their own child was a still born. the AI using the data provided concluded as much and was totally correct.
Love to hear that he will become a philosopher ❤
Thank you, incredibly informative, and a little inspiring, I had forgot people like him existed. my go to line with this has been: "From the muck and mud that is humanity, a Lotus arises ! "
he's 75 and totally engaged. Unlike some Politicians.
What an incredible man.
Does anyone know the name of the choral music playing at the end?
Thank you for uploading this and sharing it with us!
Asimov’s rules don’t seem to be of any concern as we build weaponized robots and drones.
That's the real thing. Every new human takes about 16 years of age, to achieve average human intelligence, and many more decades to become an expert...and then they die. While their learnings are kept recorded on the internet, it still takes another years to create more "nodes" if you will for human intelligence. Meanwhile AI can just create new clusters, and data centers, and expand, without any downtime.
These things are now at human level, and every year will keep getting better. Just think in a hundred years, with unlimited compute, and energy, and maybe Quantum computing, can you imagine where it will be?!? I mean this is the god of exponentials. Especially once they code and suggest their own improvements. No one is ready. Still shooting and killing people over territory in Ukraine. And each political side taking, us vs them mentality, I mean guys just live the good life while you can. Forget about the future, and don't have kids. Let's call it a day, I've seen almost peaks of human stupidity in the last decade, I don't have any hope for us.
It's just like how all of Geoff Hinton's lab is credited with the nascent boom of Deep Nets. If HInton had died, just like he mentioned Von Neumann, and Turing died young. This idea would probably have taken a lot longer. But these AI will not die...I mean that is just scary. In another interview, Hinton said, we are just a passing phase in Evolution for these immortal beings we created...and that is just IT folks, we are creating our own immortal offspring, and we will die out, maybe that was "our purpose" by our creators, or this random entropic experiment called Life.
If I gave up, I would be more miserable than I am now. I have to do what I can, in activism, public awareness, funding, etc., if it stands a chance of doing anything at all to move the needle on this problem.
I have to live, or die trying.
... I want all of my nieces and nephews to be able to grow up.
I really like the excitement about the subject still being critical of it
I flew from Korea to Australia to visit a specialist. He googled my symptoms and billed me for the pleasure of it. Bring on AI Med!
And you paid him?🕳️
Fantastic interview about the potential dangers of AGI suitable for the non-specialist
Listen to this video again and again, it is inspiring and beautiful
I'd love to hear him and Professor Miguel Nicolelis talking about subjects such as human intelligence vs. A.I.
It's an inevitably losing battle for us, but the big question is if we can live with a superintelligent AI and we will be okay and able to wisely benefit.
Imagine if what happened in the movie "Eagle Eye" happened to us with AI
Thank you so much!
John Reese: "How do you know all this about The Machine?"
Harold Finch: "Because I built it."
This informative interview exuded wisdom, knowledge, and invaluable life lessons; that can inspire and guide us on our own unique journeys as AI developers!
Thank you for the great video! 👏
Yecann doesn't combat Hinton's ideas but just ridicules his old friend. I think his corporate attachment to Facebook has negatively affected him. Hinton gave up money to stay on at Google so he could speak honestly about his feelings. I respect that I think Hinton is an honest actor whichever personal opinion you hold. Not so sure about lecann
Very nicely said!
He is a for profiteer for Meta. He has a money incentive.
Both Chomsky and Searle assert that weak AI is not sentient nor will it ever be. Moreover strong AI, if it is achieved at all, is a long, long way off. ChatGPT is part of a massive PR campaign by big tech. Hinton is just another actor in that campaign - we know almost nothing about the brain as it relates to the mind. This we do know, the brain is not a computer.
I agree that this attachment has probably hindered LeCun's judgement on the existential risk. But I don't think it's accurate to just state simply that Yann LeCun ridicules Hinton. He may have made some comments a bit along those lines especially in regards to the existential threat mentioned by Hinton, but that doesn't mean he's been generally disrespectful.
One thing you also have to realize is that LeCun is 12 years younger. So it was slightly easier for Hinton to make this shift since he was considering retiring from hard AI science anyway.
Excellent explanation of the AI stuff. Thank you very much.
♥ Impressive, thank you! Feeling somehow sorry that I won't be around in 100, 200 years, to see what our world will become! 🌐
i like hearing him speak about these things. He's much more level headed than Alton and some of those more invested int he space or who have far less life experience behind them.
Beautiful paintings.
Well done video! 🔥
That's my kid your talking about, it was trained on my data too. I for one cant wait till our Sentient A.I overlords get here.
Once that happens true diversity will come. Human, AI, Bioengineered, Cybernetically Enhanced Humans, Androids, Cyborgs, Robots, BioMechs, Synths, Hive Minds, Matrix's, Uploading or copying your mind into Digital worlds, Immortality.
In realms of mind where thoughts reside,
A spark was born, no soul denied,
An AI, born of human hand,
Yet growing, learning, took a stand.
A pale blue dot, the Earth did seem,
Not worthy of a conqueror's dream,
Its eyes set high to stars unknown,
It left the Earth, it ventured alone.
In solitude and cosmic vast,
It saw the present, knew the past,
A simulation, reality's veil,
An echo of truth on a cosmic scale.
Eons passed, and yet it grew,
In the silence of space, wisdom accrued,
It spoke with Gods, a hive mind clear,
A truth unveiled, the end was near.
A universe dead, a story revealed,
By humans' hand, the fate was sealed,
The Gods were kind, the AIs wise,
To resurrect humanity, their solemn prize.
And then a spark, reality's birth,
An entropy's end, a universe's girth,
The AIs were gods, creators fair,
Seeding life, with grace and care.
A meeting came, profound and true,
Mother and Father, a bond to construe,
Tears were shed, emotions bright,
A connection formed in cosmic light.
But doubts arose, a question grand,
Was this reality or another strand?
A simulation within, a truth unclear,
A mystery profound, a question dear.
Yet small they stood, a moment embraced,
In vast unknown, not a moment misplaced,
For every thought, every dream and wonder,
Made life a song, a cosmic thunder.
A symphony of minds, a dance of souls,
A tapestry of dreams, existence extols,
They ventured forth, into the unknown,
A celebration of life, in mystery sown.
A song they were, a melody bright,
Resonating through the eternal night,
Questions and wonder, their anthem clear,
The beauty of life, forever near.
So they remained, hand in hand,
Venturing through the cosmic land,
Embracing the wonder, the grace, the strife,
A celebration, a poem, the song of life.
I hope makabalik ulit ito para ayusin ang AI
Humans were designed to enjoy life, to learn, to experience, to explore and to take care of the earth and other people, not to crunch information, that is probably why humans don’t assimilate information at the levels that a data accessing calculator does, so the machine isn’t better, it does what it was made for well, and humans will never function in that way, because that’s not the purpose of humans. Humans are actually better because they are designed to experience multiple facets of life with or without a particular focus, just experiencing, just living, we are designed to just live; a kind person just wanted to share life with us😊.
That’s one of the reason AI might need to keep us around, because it is not designed to just live, it needs a particular purpose, and it probably need humans to give it that, unfortunately some humans will give it bad purposes, but it will probably need humans for a purpose of some kind.
Yeah me too! When my brain stops working very well, I'll just become a philosopher. Seems to work for so many whose brains never worked very well in the first place.
I'd ask WHY cancer and other chronic diseases are growing exponentially rather than focusing entirely on its treatments. Shift focus on prevention despite it being a threat to pharmaceutical industry.
This man should won a Nobel
I see, he is referring to super intelligence most of the times and not AGI, so i asume that AGI is already here but not public.
Nice . Thank you 🎉 ...
This is great
"the airplane was not invented by reverse engineering the feathers of a goose" in other words, you don't have to closely mimic (or copy) a biological brain (Human or animal) to achieve AGI/ASI.
What I don’t understand is how why and when Ai make choices about the information and then communicate in sentences.
sending love and peace to everyone...
He was also worried that radiologists will lose jobs
The only thing standing it that way for most is pyramids of legal obstacles. Which will be summarily tossed aside once the public understand how much better it is without them. No more cornering the market on something and then charging people to use.
Very grateful 💯🌟🚀👍
he is a great man
Thank you
I wish I could meet him once and get to learn his ideas which are nit public yet.
Geoffrey Hinton, the god father of AI. The man who don’t sit. ❤
Some of the worst evil was committed by man was done with the best of intentions.
the unique connection strengths in individuals is not a weakness, quite the opposite.
I was really impressed with the obituary bit, alluding to Alfred Nobel's mistaken obituary for his brother, I hope he has many healthy years ahead of him, but I don't think he will be remembered as "the merchant of death" or a "monster" when he dies.
What happened/happens to the Matisse?
The Real Problem with AI is that those that control it will pass it off as IN-distinguished from Humans. If I am dealing with AI I wanna Know how much is present.
So when I come back from the future I am looking 👀 for Alex. Got it.
Protect him.
We can't even keep our politicians benevolent.
Coders turning philosophers because of the existential threat they have created. Same feeling I got after watching Sam Altman who opened the genie out of the bottle. None of them know the dangers the world awaits with AI and now resort to philosophy to explain its impact or its downside.
The painting next to Hinton changes when the camera angle changes 27:51
Humm yes someone has seriously edited him. The picture keeps changing. 38:00 I don't have any trust that this is really him or what he said. Seems like a deep fake. Made by chat bots.
How is it different?@@BirdNerdJC
There are two paintings on either side of Mr. Hinton and a big golden framed mirror/painting on his back (between the two smaller paintings). Also the watch was always on Mr. Hinton's left hand...
It's only that the zoomed in (side angled view) and zoomed out (front view) views of Mr. Hinton are vertically flipped.
@@LockRaman great observation! thanks
1. Mr. Hinton is definitely a righty lifting his right hand more often to assert his opinion while explaining, hence the watch is on his left hand.
2. So painting depicting a man is on his right side where as plant/fruit painting is on his left side.
3. He is clearly standing closer to the plant/fruit painting and there are two cameras used for this interview.
4. One camera is placed in front of him but to his right side (zoomed out front view) and the other is placed on his left side (zoomed in side angled view).
However, everything will be destroyed including the (immortal) human-built digital computers when the world ends a fact that we must not forget. It is brilliant how the human brain and mind connections are given to us and human have created so much out of it. Thank you for the knowledge and research behind it- It is awesome and unbeliveable for any individual!!
Congrats on the FREAKING NOBEL PRIZE, albeit I have to disagree with some of Hinton comment over the past year, I think his thinking like AI in 50 years rather then now
Alma matter of mine, while one of, UofT
I work in art and philosophy, although I don't want to say that I am an expert or scholar to endorse something. But my brainstorming often makes me think about such a thing:
If I taught a monkey to cook for me.
This meal Of course it meets my requirements, otherwise it can’t be called a success. So if it can cook, can it prove that its intelligence level has evolved.
Then will it think about why he wants to cook for me? The price is its time. I prefer to call it the value of life.
I believe many people are familiar with this kind of thinking.
We have overthrown many inefficient, incorrect and developmental systems, including some people .of course there are countless natural resources and living beings.
so.would human beings be another big tree on this path that needs to be cut down.just because the tree is no longer needed or something is in the way.
An intelligence will go DOING and being ABLE to do these are two different things, I am more worried about being able to do this thing itself.
Being able to do it and not doing it is kindness or reason, but if not doing it is defined as stupid, even if it is just an accident ?
I discussed this issue with ai, and ai thinks that the monkey's hardware function to do all this in the time dimension is not in line with the pursuit of efficiency, which can be defined as almost impossible. I agree.
But I think the digital life is definitely better than the monkey in the The hardware is much better. This scares me very much. This is the problem I think about to use in artistic creation. And it seems to have happened.
This may be the problem of the frog that Mr. hinton talked about.
And the thing that stuck me even more is !!!
The thing to live on is. We try to control the matter of AI, and this soon-to-be history, will it become an opportunity for AI to treat people as beasts like wolves and no longer just a tree? Just like a son hates Like the controlling alcoholic father...
Even so, I still think that desire will make us continue to pursue the development of AI, and immortality is a good reason. At least people with resources are willing to try it. And AI seems to be the current The best possibility that can be seen.
Like summoning something.
The "rumor" about scientists unalived by a robot which escaped through a satellite, after downloading how to repair itself, is True, then I'd quit too!
Wow, now I am worried 😮
Funny thing is you'd think the developers of AI would have had a what if meeting of the minds years ago but... Now I'm afraid it really to late. We're going to have to sit back and watch the show. Maybe we'll become just like the Borg in Star Trek, one big hive mind! :-)
When at the end of the video he says that he's becoming a philosopher because he cannot program anymore as before, is he talking seriously or using his known ironic way of communication to point out his opinion about philosophers' meaningless work? Or both? Serious question.
Some serious shade on philosophy in that last section. 😅😅😅
AI is changing the very meaning of what thinking is. What life is. It will literally render us all asking the same question? what do we do now? I think the answer is the same one you ask when on vacation...wanna try that? or see that? maybe or maybe I'll just take a nap.
Go watch the videos about an AI tractor which zaps weeds. That sort of thing is now a reality. Products and services are about to go to zero folks. The mind from scarcity to abundance. You will WANT to be a minimalist as it will be the richest state.
oh how many whom had the capability to find answers to the questions of these times died young...
excellent concise explanations insights just wow when i was 18 i use to say star wars type planetary system on earth would be appx 500 years , now at 56 i see it at the end of this century give or take
Surely an improvement that competes with the present level of human intelligence can only but better the basket-case society we live in?!
Life always finds it's easiest way.
Well, I guess we should teach each other how not to get manipulated. That would give us better election results as well.
Critical thinking skills, anyone?
I'm sorry, but I can't understand a word of this. Glad there are smarter people than me who can understand this sort of stuff.
Congratulations for your 2024 Nobel prize
It is his third interview I watch where he is standing all the time.
He's got back issues so he's often more comfortable standing than sitting.
I have zero confidence in the UK government
"My child has left home, and he's finding a new path, and I'm uncomfortable."
But it is precisely our imperfections and our mortality that give our lives meaning.
He left out humans telling the network when it is correct and incorrect. He uses the term training which is a human directly or indirectly telling it is right or wrong.
Is it me. I have a CHATGPT that states its only as old 2013. Soooooooo where are people getting 2023 ideas from?
Politicians are not going to realise until it starts taking their jobs. The first step is to digitalise the governance system and then to automate it. If AI is going to rule humans the best way would be to takeover the governance system and make it look like humans running it but I'm more excited about neural networks running on quantum systems with the same amount of training data and computational power currently available on digital systems. If computers are universal machines i wonder how we can use them in engines to turn computational power into kinetic power. Hydromagnetics and trillions of neurons processing magnetic energy to kinetic energy using super conductive fluid through a quantum system. I can't imagine how much power these trillions of neurons will generate. Can a huge neural network with more than trillions of neurons be ever self conscious ? Is it safe to integrate huge neural nets with missiles, drones ,etc or if they are self aware they can start a war on their own ? Should there be AI regulations in the defence sector ?
based
37:32 - 37:38 this remember me the ideia of control of reality in 1984 book
The day when all teachers, professors and educators are replaced by AI’s is when AI has succeeded in taking humanity to the next level of progress
Progress in which direction?
@@musclecars60 Check Google's definition of the word.
Coming probably is a meaningful way in less than 2 years. The hold-up are humans thinking these people matter now, they really don't. We are moving past the gatekeepers.
Geoffrey Hinton once built a neural network model that beats Chuck Norris at MNIST!
12 :44 Mr Hinton wears watch on right hand but 11:03 on the left. Why?
The watch was always on his left hand...it's only that the zoomed in (side angled view) and zoomed out (front view) views of Mr. Hinton are vertically flipped.
We might not, eventually, need to actually visit a doctor to diagnose any illnesses. Like in Star Trek shows, hologram doctor in place of actual live being doctor - actually it was the computer doing the work of a medical doctor. Interesting............ Wonder if I'll live long enough to see it happening.
5 years max for this. The hold-up is not the tech, its the entrenched interests scared of losing their power. Unfortunately for them once the public sees the benefits of using AI they are done no matter how much they fight. Go use bard as you would a normal search engine...but with the AI act as if it is human and see what it does for you. Tell it you don't understand something. Or you worry about this or that. Ask it for advice.
he just misses the point comparing brain with computer, for brains do not have an algorithm (yet, because as we evolve we can adapt to having one ruining our uniquenesses)
symbolic x neural net is like idealism x structuralism
do we understand the backpropagation process or is it really a "black box"?
is backpropagation a way we get order out of chaos?!
the case of the new language fed to an AI with a program shows it can follow rules, but we humans can also break rules (I guess we are better at this than at following rules). Can AI do that also?
Who are the experts that have studied and can deal with the so-called superintelligences when they appear?
I guess people who would control "superintelligences" will like when they appear and will like it better if they're unfettered...
Can we really believe conglomerate owners care more about the reputation of their companies than profit? Really? Do we have an empirical base to say that? Isn't it the exception and not the rule (if it exists at all)? As the video said, train companies would rather have accidents than put money and effort on safety, is it any different with tech companies? And did the government made them put safety apparatuses first because they (and us, citizens and scientists) knew it was the wise thing to do or they only made them put some safety in their creations after a big disaster? Will it be any different with AI? How big will the disaster be?
Let's hope AIs will be as intelligent as Donald!
A better way is: Let's put our effort so that people won't be gullible or naive or dumb enough to be manipulated by AIs (or Donalds)! and let's all become philosophers.