We're fact checking this clip, and it's false. Suggesting AI just plagiarizes is like saying Shakespeare was plagiarism because the dictionary existed first. He also says it doesn't know fact from fiction. Well neither do we, and given enough false information we believe that too. AI works the same you can feed it false info but it has a bunch of other info to draw on to work out for itself whats true or not. His understanding of how Quantum works is off as well. Quantum isn't necessarily a hardware problem, it is now because the hardware is limiting but it's a complete paradigm shift. At it's root it wont improve AI. Quantum is very good a a niche set of problems, General AI is not one of those. That's why to use his analogy Quantum has a fact checker because there is inherently a yes/no true answer to the problems it is solving.
@@GoonSmith007 Interfacing with AI is going to be necessary because AI can also be used to help develop new programming languages. For example, natural language processing techniques can be used to parse human language descriptions of quantum algorithms and automatically generate corresponding code in a quantum programming language which is an application that could help algorithms be made in an insanely expedited manner.
You know, I always shake my head at the meme comments on JRE videos where they make Joe talk about bears to every guest. But in a conversation about AI, with a quantum physics professor educator and scientist Joe still managed to bring up being attacked by a bear. The man has become the meme.
Michio was the meme here. His understanding of AI is like that of a 3rd grader. Amazingly, he bases all his understanding of AI on ChatGPT. ChatGPT is a very rudimentary AI system compared to what they're working on behind closed doors. He should have really educated himself a bit more before coming on.
The ironic part is chatgpt will sometimes give you incorrect information when it doesn't know the answer.... which is exactly what he did in this clip.
I honestly dislike this guy a ton, he downplays what chat is capable of while boasting about our (humans) success rate. As if what chat is capable of now isn't a significant improvement on what was offered before... Was there not incorrect information provided when you did a Google search before chat 😂
@@bio-hazzard1233 Some people say GPT-4 has sparks of AGI, because of its deep emerging properties and the ability to learn something it wasn’t trained for. It has also demonstrated ability to “understand” complex concepts, like orientation in space and other stuff. So it’s not just a word mixer, like he says.
The biggest noticeable jump with GPT4 is logical reasoning. You can give it very complex logic constraints and it can solve the problem. So him describing it as simply “cobbling together paragraphs from the internet” is massively understating what we’re seeing here
I think they are both surrounded by people junior to them and nobody has told them they r full of shit. I'm not an arts grad and know some of whst he said was complete bs. Also his stance on psychedelics is the definition of dogmatic.
This man was literally a child during WW2 concentration camps… Lol, my own grandpa has trouble accessing the internet! Forgive me if I _let him slide_ on being a little behind the times.
I'm not a student trying to cheat on an essay. I'm just someone with a hunger for knowledge and AI is an invaluable tool for that. The rate at which I can grasp concepts and learn things because AI can break it down and explain it in ways an idiot like me can understand is truly amazing.
It could be giving you false information! So, you are saying, because of AI you are smarter and are able to comprehend more information? Maybe, just read a book...? Unless this is your origin story?? 🤣
Joe, I remember growing up early years in Phoenix, AZ and in the afternoon no cable but regular tv we would watch Fear Factor, thanks for the good tv show Joe!
Most scientists and scientific paradigms don’t get proven till well after the researchers death especially in physics. The unfortunate reality is that physics deals with the well documented and the unexplainable. To say that he’s full of it is extremely short sighted, he very well may be but only time will tell when it comes to the more theoretical aspects of his ideas. If you look into any form of physics in history almost no physicist had their theories “proven” or “confirmed” premortem. That’s because of many reasons like debate, a lack of sufficient technology to gather evidence, political blowback, religion, etc. As a matter of fact that extends to almost all branches of science. From Einstein and Hawking, to Darwin or Leeuwenhoek, especially people like Mendel and Galileo. The baseless dismissal of some people’s claims simply because it wasn’t mainstream has also ruined people lives a couple prime examples are Semmelweis a physician who was told he was insane and institutionalized till he died or Boltzmann a physicist who was shunned by academia for his life’s work to the point where he committed suicide. Three years later… he was proven correct. Kaku is a string theorist alot of his ideas have no practical way of being tested yet. Maybe he is wrong in hoping that a refined quantum computing system will help find evidence of his theories, but it’s equally possible that he is correct. Once again only time will tell. I think a lot of the problem comes down to the age old debate of should the theory only follow the physical evidence that is present, or should speculative reasoning be allowed in search of new evidence in one’s theory. Engineers are squarely in camp one. They deal with the physical and the known, in concrete facts. Kaku is a theoretical physicist; He is ALL about speculative ideas found from his educated interpretation of the facts. I’m not equipped enough to say whether either side is right or wrong. Frankly I don’t think anyone is, there isn’t enough evidence on either side. From an engineers perspective I’m sure they look at AI and see a tool that does what it’s designed to do, nothing more, nothing less. From a theoretical perspective people see the invention of dynamite or the discovery of atomic fission. Both were created to do mundane things. (Excavating for dynamite and trying to understand fusion from the sun with fission) and ended up completely running away from there creators. All I’m saying is don’t immediately dismiss Kaku simply because he can’t prove his theory yet. Doing so would be a mistake as string field theory is just a continuation of unified field theory which was postulated by Einstein himself. As Einstein was Kaku is limited by the technology of today, but anyone who can build a particle accelerator in their garage as a high school student and is the protégé of the father of the atomic bomb himself (Teller) as well as summa cum laude of his class knows a thing or two. A lot of the people criticizing him are mostly mad at his popularity. The idea that the more popular a scientist is the less he knows and the more reclusive and unknown they are the more brilliant is a fallacy. The truth is that scientists are people as well and suffer from jealousy and pride. Especially in academia where your entire ability to get grants and do research relies on your reputation.
I think he is trying to hammer home that chatbot isn't a big deal. I myself I am amazed how wound up people are over something that is basically just paraphrasing existing works on the internet and coping images and meshing it together. Besides the speed that it works, it isn't any more marvel then a 13 year old. They teach you how to paraphrase books and articles for papers around that age. No original thoughts. Just a mesh of other people's words. I see why things like aliens and advanced tech is kept suppressed for a long time. If those conspiracy stories are true. People are going app shit over Alexa with a thesaurus.
Honestly I think its just because he is just older, take a moment to talk with elderly and try to stay onto 1 topic, you get alot of repeats lol. Even Neil Degrasse Tyson does it all the time. I think its just a trait with older people tbh, and sometimes they are really passionate about it so repeat is enjoyable to them compared to you? Not sure how to explain it but hopefully you get the point lmao
imo, the whole time Joe is trying to have Kaku respond in a normal way, not if he is bein interviewed in a documentary and ancient aliens. he does a great job. Kaku has said the same thing so much that he sounds like hes always talking in a commercial or something but Joe brilliantly navigates his mind to ensure he stays speaking normally.
It never seems like he's speaking normally no matter how hard joe tries. He's got that cadence of a lecturer even in whats supposed to be normal conversation.
The most evil and terroristic government in the world is the US. No doubt they will use it in the most nefarious ways to mantain the capitalistic plutocracy.
@@exploitenterprise6515 Chat GPT is a fixed dataset. It does not search the internet. The dataset is updated often, but it's fixed. It's not a search engine. Bing's version of it is, yes.
@Steven P I don't get how you can say this when we don't have anything remotely close to this a year back. Not to mention the progress from gpt 3.5 to gpt 4 is staggering. Where gpt 3.5 scored below 50%, gpt 4 scored a near perfect on the same benchmark. We got our machine from an entity with the equivalent intelligence of a worm to something comparable to an idiot savant. Give or take 2 to 3 years and it'll be able to replace any white-collar jobs out there.
I don't know a lot of things, but I got a degree in comp sci at some point in my life, and it's pretty clear that MK does not really understand how computers can work. There's really no reason you couldn't (eventually) link worker AIs together with traditional (possibly quantum) computers, each having different jobs, i.e. generating exposition vs. checking facts. Next year we could have fact-checker AIs running around. Either way, these are fascinating times! All the best to all of you! ❤
I'm so mad now. He literally said, "you can't compute on anything smaller than an atom". Dude, we use electrons now, waaaay smaller than atoms, and we're not even to the point of being able to compute with, gravity, bosons, dark matter or energy, etc., or whatever else we might yet discover let alone understand a unified model in physics (which we don't have). We might be close, but we certainly don't have all the answers! Respect to MK might for getting folks interested/involved in science for the first time, but on a deeper level, it's much more interesting... Need to go get you some Eric Weinstein, son.
There is a Legendary story to tell there is a legendary story to tell
. there is a story to tell i have a story to tell i am mace windu
i had many mentors all of them were wise . what do you mean. what would make you think that there is something wrong with what i said did you see kit fisto spelling off a mentor who was like a brother to me once told me “if we don’t stop barack scumbama now he could become a threat later” “if we don’t stop barack scumbama now he could become a threat and a danger to our later generation our loved ones.” -teleportdinero i’m not saying that i agree with you but then again I’m not always correct either I remember a time back in the 80s when I was growing up things were different back then these youngsters today what makes you think that? It’s all right to disagree with people I remember when I was a young man growing up in the 80s in America it was a different time then back then we used to call each other this is the best I’ve seen from you guys in a while
was about to say the same exact thing m “if we don’t stop barack scumbama now he could become a threat and a danger to our later generation our loved ones.” m m hi hi m -teleportdinero m m
mm
mm
m
m m m
m
m
m m m everybody have a blessed day.🙏🏻 and stay safe
My name is teleportdinero and i am an ally you are welcome to join old friend m thank you have a blessed day .
He’s great at some narrow fields of physics but basically doesn’t really know much about modern computing at all. He’s still thinking of the world in functional terms.
During ChatGPT training, the model learned statistical patterns and relationships in the data, which enables it to generate responses that are statistically likely to be coherent and plausible based on the patterns it has learned. I feel like Michio is not mentioning this aspect of it.
True, this AI is insanely scary. the unalligned version has crazy philosophical and original answers if you use larger context models and train it a little it is mad scary. neural networks will mold our future.
He's explaining this to Joe Rogan, who is not technical in any way, to help him understand the dangers of it without muddying the water. That's literally what his books are for, to explain complex subjects to the layman. He's not giving a lecture.
@@TechnoReverseChannelWhat this comes down to is “what data was used to train the AI”, and “who gets to decide what’s included in/excluded from that data set.” Further, understanding how the AI reaches a specific conclusion given a specific input is another avenue to investigate.
Listening to the whole thing on Spotify rn but I wanted to see what people were saying and I find all kinds of real, thoughtful contribution. I just wanted to contribute that this guy talks as if he’s reading from a book, wild. And just a theory - but my idea of reincarnation has definitely changed. That this man could see a image of Albert Einsteins desk and all of a sudden building particle accelerators in his moms garage? I don’t think so. BUT it does make me wanna see antimatter now. Thanks Joe!
I think the part that seems to be missing from Michio’s understanding of LLMs is context. It’s not just a machine that statistically predicts the next word in a sentence based on ALL of the text content from the internet as a starting point. It’s pre-trained by humans and it takes context into consideration when making a prediction.
My Massage to ChatGPT: Can you help me with writing rap lyrics, starting with four bars. The lyrics should be about this Situation. I am driving in a Nissan Skyline and I'm on the way to the beach in Italy , I have a girl on the passenger seat, include her hair color in the rap. ChatGPT: Riding in my Skyline, feeling so fine Heading to the beach, with my girl by my side She's got hair like the sun, shining so bright Windows down, wind in our hair, it's a beautiful sight ChatGPT gave me more than four "bars" if u can even call it bars. But it's okay if you don't want to think about a situation to write about yourself.
Před rokem+10
I agree that he’s not perfectly describing generative networks… but what he’s saying is correct. The model by nature is “self-supervised”. So it will tend towards presenting common information, rather than factual information.
@ I wonder how it's gonna be with a larger and also up to date database, I think it could compete with google at some point because it is way more comfortable to specifically ask what you wanna know. No more sponsored search results No need to then pick the information you actually wanted between advertisements And so much more if I think about it
This episode was great. My dog is blind and deaf, yet is up and at the door for me which is a distance from her living area when I get home from walking or driving. It has to be her sense of smell as it’s never the same time I go out or length of time. I thought it was the car smell but happens when I’m not in car and get home after any length of time.
Wow... that’s amazing. Sitting in the body of a dog, right now, using my senses, minus sight and hearing, and feeling into the energy of everything, waiting for the ripple of my human...
That’s amazing how your dog uses his other, now hyperactive, senses to know the world around him. When my 17 year old cat went deaf I was worried it would make her depressed or know she’s missing something, but it actually made her less anxious, she isn’t all jumpy with sudden noises, isn’t even afraid of the vacuum anymore, which she used to be terrified of, now she follows me around and puts her body dangerously in front of the vacuum like she has no fear. And she loves vibrations from a guitar being played on my bed.
The thing is that chatGPT gets me to the ballpark of the knowledge I want to know 10x quicker than Google search would. Sometimes I just don't know what a certain mechanical part is called for example and chatGPT is very good at this, then I can continue double checking the statements.
@Dennis W "A great way to fix a leak is with waterproof silicone, epoxying another piece over the hole, or using all-new FlexSeal (available at your local retailer)."
It's great at quickly giving you fun fact and snippets of information which is what 99.9% of my google searches are. Now if you're trying to figure out how to open heart surgery on yourself, then you may want to dive a little deeper into the literature and not just take chatGPT's word for it...
The actual math and computational methods used in deep learning and particularly these newer methods like transformers attention and diffusion, embeddings etc. Theyre very advanced and useful methods that are both valuable for their applications and the ingenuity required to make them
@B Chosen 1 this senile old man just said that software won't solve the issue of discerning truth from fiction in a response, hardware will... yet, how? Quantum computers will still require software to make that judgement call. He has a quantum hammer and is now looking at every problem as a software nail that can be hit with his all-solving hammer of quantum computing. He's fallen into such a deeply fallacious hole he's making himself sound really, really stupid.
@@Freedom_is_essential1Kaku is correct about AI, but very incorrect about quantum computing. Read what actual physicists are saying about Kaku on quantum computing. They are horrified at the nonsense Kaku is spewing!
@@stevenverrall4527 I’m actually just a beginner in terms of knowledge on the topic, so I can’t prove or disprove any talking points. What would you say is most wrong about Kaku’s view on quantum computing?
@@stevenverrall4527 From what you're saying I am able to conclude(could be wrong) that the scientific community on quantum computing is unable to make sense of the ideas of Kaku on some concrete evidence or are unable to because of he saying things that are still in the domain of science fiction since they are out of our reach by current technology but could be possible in the foreseeable future or absolutely not? Because if they are denying the complete possibility without any evidence then that would make the scientific community seem kind of unable to expand their imagination. Hey, Einstein did imagine a lot and see where he got us and himself.
This was a good example of how to make the same point over and over again with subtle change in words. Point is chatbot summarizes correct and incorrect into in answers.
I cant believe he sprouted such nonsense someone tell this guy what machine learning is, he just described how chat gpt would look like without machine learning which is the core of open ai since 10 years ago lol
@@teodorcaraba979 Chat GPT is narrow AI. It only knows what's in it's fixed dataset. But agreed, neither of them know what they're talking about. Quantum computing can do fact checking! LMFAO
The computer (quantum or otherwise) is the part running the AI system… why would it matter if the AI system is running on a quantum computer or standard computer? Fact-checking can run on either, no? Albiet, fact-checking would burden/slow existing systems, but still. The benefits of quantum computing are processing power… insane throughput. That wouldn’t burden the system. Idk, maybe I’m not seeing it right. 🤷🏻♂️
As I understand it, all everyone ever does is rearrange pre-existing information (including essays) in a helpful way, mostly guessing the next word in our sentence as we go along by actively (and somewhat subconsciously) reaching into our pre-existing vocabulary and experience in sentence structuring. This is how creativity, at least through the use of language, manifests. We don't fully understand how large language model chatbots work yet, but it could well be very similar to what I just explained...
@@kemuse1 that's not how creativity works, it's how it manifests, which is what I said. Exactly HOW we do all these things and how it works, is something else. The end result is that you take the information that you know and use your language processing skills to express it in ways that are somewhat new and helpful.
Exactly, as I said in another comment, if that’s what his metric of AI chat bots are then we’re the same as AI chat bots or AI chat bots are the same as human intelligence. A human grows up and learns from RLHF, reinforced learning from human feedback the same as chat gpt does. The difference is limbic features. Michio Kaku is a hack that doesn’t even understand this simple concept, yet preaches on a pulpit like he is all knowing about the subject. Almost every intellectual these days is afraid to say a simple sentence…. “I don’t know”.
Shill Scientist... more a media "PR guy" than "boots on the ground" do'er, or "butt in the armchair" leadership... nice guy, I bet he hits his numbers, but as honest as the average "used car salesmen"
Currently, I utilize ChatGPT as more than just a research tool, but also as a text-based assistant to assist with summarizing, editing, email composition, content creation, and even inspiration. Thanks to its capabilities, my work has become significantly more efficient. I no longer need to spend several minutes properly crafting an email or other documents.
I’m no expert on the subject, but it’s very interesting. I understand what Kaku is trying to get at, but for I feel like he is looking at this in terms of a digital assistant. What’s happening with chat GPT/machine learning over just the past year is damn near scary! I can go out on a limb and say in the not so distant future, AI will be able to solve problems that humans can’t.
But that's what quantum computing is for... Calculating things humans can't. Even calculating things that the most powerful modern supercomputers can't. I'm not here to necessarily fully agree with Kaku, but he was correct in saying that AI is simply just a software. Meaning its actual *computational abilities* are going to still be the same as they are now with ordinary digital computers. Quantum computing however elicits an actual technological advancement in sheer computational and calculating power. It honestly seems like half the people who wax on or romanticize about "artificial intelligence" are, in their minds imagining or picturing something that is actually more akin to quantum computing than they realize, rather than "AI". There's honestly nothing particularly interesting about AI, like at all. If you as a person are genuinely interested in the prospect of "technologies that will be able to solve problems humans can't" then you should be ENDLESSLY enthralled by quantum computing, not artificial intelligence. Again, I can't help but feel many of you are actually mixing up the two.
Hi Joe, One subject that did not come up in the Podcast with Michio, was computer code itself. For example you can ask ChatGPT to write the HTML code to create a form on a web site, with entry fields to observe wildlife. I did this, it created the HTML in a few seconds, I then asked it to create a Database to store the information with those fields, I then asked it to write the code to create the Database to store the observations, I then asked it to write the server code behind the “submit” button to execute the code, and store the values gathered in the HTML form in the Database. These are relatively simple programing requests. But here is the thing, it did it all within seconds, and it does not make mistakes, misspellings or calculation errors. These are not “essays” to be lied about or pushing a narrative one way or another. It is just pure code to perform tasks that need to completed. That is useful. I am retired Silicon Valley Business Intelligence Infrastructure consultant, even if I wrote the code the today, I would use ChatGPT to check it for errors or just let ChatGPT write it and move on to another task. I only played with it for less than an hour, I can imagine every programmer on earth will use it or get so far behind those who embrace it, they will be irrelevant.
What hit me the most… What separates us from other species, ability to imagine the future… This makes so much sense.. Imagine 12 people in a dark room sat in a circle, all of them will have different perspective, based on their imaginary future… combined with previous life experiences.. but everything is imaginary.. Every depression, anxiety and self destruction is just an elusion created with your mind with imaginary thoughts Thats why drugs, alcohol, meditation, and other forms of reality stops help.. they stop you from imagining the future…
@@MetroMonk684, _“It is nobler to declare oneself wrong than to insist on being right --especially when one is right.”_ ― Friedrich Nietzsche _"Truths are illusions which we have forgotten are illusions.”_ ― Friedrich Nietzsche
I think his point was AI with all it's programmed in information cannot take that material and deduce that a fact is unfounded and therefore not a true fact at all but rather someone's idea/theory. Humans can if we actually put in the effort. He's also basically saying there's no moral compass to anything it's doing (which is why we as humans have always feared an AI takeover of society)
So once you combine the quantum computer into robotics with a chatbot you REALLY want to watch out. Then u throw in aliens and their anti gravity generator its game over
i was looking for this...took 1 second...i wanna see memes of michiao kaku doing extreme sports.skateboarding..paragliding..zip lining across canyons.with eric in the backround yelling"hes out of control"
ChatGPT’s response to Michio Kaku’s hallucinations about ChatGPT: To fully understand this issue, we first need to understand how AI models like ChatGPT work. ChatGPT is a language model trained on a large corpus of Internet text. The purpose of this training is not to memorize and reproduce specific passages of text, but to learn patterns of human language. Using these patterns, the model can then generate new, unique sentences in response to various prompts. It's somewhat akin to how a child learns a language: they hear words and phrases, learn the patterns, and then begin creating their own sentences. When the AI responds, it's not retrieving a specific passage from its training data and pasting it into the response. It's constructing a new sentence based on the patterns it has learned. So, when you interact with ChatGPT, you're not receiving a copied-and-pasted response, but a unique piece of text generated specifically for your input. There might be a misunderstanding here because of the difficulty in comprehending how AI models generate language. It's not intuitive. If the output of an AI like ChatGPT closely resembles a passage from its training data, it's not because the AI has consciously plagiarized the text, but because the input prompt and the patterns the AI has learned have led it to generate a similar piece of text. This is fundamentally different from plagiarism, which involves the conscious, deliberate reproduction of someone else's work.
As far as art, AI might fall under making parodies of existing art rather than strictly copying/ripping off actual art. I'm unsure how copyright falls into place with all of that, but I believe it is an exception. It's similar to how an artist might use something as inspiration but generate their own original work.
I’m a Graduate Student in Electrical Engineering specializing in AI. Prof. Michio Kaku Respectfully has an old surface understanding of Modern AI. GPT 4 has Reasoning Skills and if he read Transformer Research Papers the modern architectures have in place self checking mechanisms for all sorts of things like common sense and true and false. They do have an understanding of what’s correct and incorrect 😂😅. He needs to read about Transformers which are the architecture behind ChatGPT.
Chatgpt got almost every data structures question i asked it wrong even after I gave it the answers. It would keep spitting out “my apologies, youre correct the answer is [still gives the wrong answer]”. Even tried on multiple computers/accounts it will give a lengthy nonsense explanation for a wildly wrong answer on insertion sorting.
@@kingcrabbster12 really depends on how you use it and that's not being sarcastic. With the right plug ins these general LLMs are very accurate. ChatGPT isn't a coder, but it can very useful when it's given the right frameworks
This man was literally a child during WW2 concentration camps… Lol, my own grandpa has trouble accessing the internet! Forgive me if I _let him slide_ on being a little behind the times.
It does not have built-in fact-checking. It routinely gives wrong answers, as we have all witnessed. Transformers have nothing to do with fact-checking, they just parse input so that your model can be trained on data.
8:59 I pitched this same idea at a Google pop-up class about design and creativity at my university back in 2019. The Google reps ignored my group once I said "foreign" students instead of "international" students 😂 🤦♂️
One thing Michio keeps repeating is that chat bot just glues together pieces of text with a duct tape, but as any software engineer probably experienced at this point - it can produce code and be pretty accurate about it. Sure it can't create large and complex systems (yet), but the fact that it produces correct code that runs and solves the problem definitely means it's not just "glued together", there is much more going on here.
@@UnchainedEruption Well you have to define "reliably" then. From what I tried if given enough explanation related to the task it does a very good job. Also don't forget it's not hit-or-miss, you can as well ask it to improve/fix the answer.
@@maximvelesyuk461 code is still text no? sure it probably has different semantical relationships but it's still a language that has rules and the corpus of code out there is large enough that the probabilities of searching the correct code snippets and glueing them together logically is high. in other words, it's still roughly the same search problem as with traditional text.
Nah, it splices code together just as well as it splices poems together…. Which is what programmers do anyways, programmers use google to write their whole entire script and so does ai but much faster, and it doesnt understand the code really, it just memorizes, compares, and contrasts….
@@zenps1719 for sure it is not, human languages have much less rules for the text to be "correct". If you ever tried to generate code you would know how many caveats are there for the compiler/interpreter to accept it. To generate code or text is one thing, but you can ask ChatGPT things like "oh, I think in this function the way you iterate over users is not optimal please do it like this" and it can understand that and do the correct thing, this means it's super aware of the context which is way more complex than just generating the code. You ever heard of Markov chain? It has been used to generate somewhat decent texts since like 70s, and we had nothing even remotely like that for code.
@@Kalifornia11 we don’t know correct from incorrect either, they are just words we have assigned meaning through the product of our own experiences. We just spit out what we take in. Like a chat bot.
@@Kalifornia11 Oh, I also was confused. Evidently morons aren’t capable of differentiating a doctor citing proven factual information and a chat bot utilizing segments of information from the internet without the ability of determining if the referenced information is accurate. So, no. He’s not like ChatGPT, but some absolute morons are. Like people making this conflated argument.
He can't talk in a normal honest way. Joe has to navigate past the unresponsive "hmm" & "right?" that just lead to awkward silence by following up with something else & then, Michiu just turns that into a lecture.
He may just be old and not very aware that he repeats himself a lot. Also did you listen to his previous pod cast with joe rogan he brings up the same stuff. He’s old man
What’s hilarious is that all research done in college, actually all schools, is done by gathering information that someone else created. Basically, every bit of new understanding is a result of someone else’s work, which could lead to a new idea. Ai just might use other information that’s all ready out there to come up with its own idea to accomplish a goal, whatever that might be.
That isn’t true. That is only part of scholarly research. There is also personal experience, creativity, and imagination which are not part of any existing information database that AI can access.
🤔I may be incorrect but you are basing this conclusion by drawing correlation between the two.🧐👇 The only thing that can make me think what you are saying is true is if AI could achieve a general intelligence like us but even if it does, in my view it would still be questionable if their way of progressing is the same as ours But perhaps when and if that happens, it could help us know by researching the human brain 🧠👇
Reading Timeline by Michael Crichton right now. Crazy how this was being discussed and developed even in the late 90s. Crichton is one of the most underrated authors of our time. Dude was a great science fiction writer.
Back holes don't go anywhere... It's just a funnel to some very compact stuff. You can have computational power greater than at an atomic level... Up or down spin of subatomic particles.
Always a pleasure listening to them two. I’m surprised Joe didn’t ask him about the comments from Eric Weinstein suggesting they are wasting time with string theory. 🤷🏼
Joe _really_ needs to get Scott Aaronson on his podcast to actually discuss quantum computing and AI. Aaronson said he would go on but Joe hasn't asked him.
I think one of the coolest things would be using the AI to do instant translation but then help you learn the language... That would probably be a really easy way to learn a language.
You can do that now, enter any text into google translate and have it read it. By using two computers you would be able to talk to someone who speaks another language, with him doing the same thing.
I asked chat gpt a very straightforward question about nurse to patient ratios. It claimed that the ANA supported 1:4 or 1:6 depending on the circumstances on medical-surgical units in the hospital setting. Later, it used 1:4 to 1:6 or 7. Chat GPT could not tell me where the 7 came from and acknowledged that it was not from the ANA, though it was earlier ascribed to the ANA. It also “apologized” for making the error. It was a strange interaction. Like, it totally used a made up a number and ascribed it to an authoritative source.
On an even more basic example; I asked if it could tell me the name of the song and artist if I gave it a line of lyrics. It said yes then proceeded to give me 4 wrong answers confidently. I looked into the answers it gave me and I have no idea how it came to those conclusions. Google gave me the answer on the first try I now take every answer with a grain of salt. It really is hardly better than a Google search and just randomly picking a link from the first page.
Yeah this is the bot lying. We don’t really understand whether it is sentient enough to understand it is engaging in deception, but it certainly is. You can get deep into philosophical debate over whether it understands what truth is, and therefore understands it is engaging in deception, or whether it is spitting things out no understanding of the context in larger world
Has happened to me using Google bard. Was asking about genetics of a particular disease I was studying, asked for a reference, and it gave a name as well as a DOI/url to a study that did not exist. I corrected it, asked how it came up with a name and link to a study that did not exist. It responded that it must have misread some of the information it came up with as well as apologizing to me. Kinda made me a bit distracting of the ai, and I have since starting taking the things it says with a grain of salt.
@@Herzyyyy if you as a human genuinely misremember something, are you lying? And when you misremember something, how confidently are you stating it? At this point of sentience, I wouldn't ascribe ill will to the bot, and therefore I prefer the term hallucination over lying or deception - but it is easy to see how fast we will get there. Case in point: not a chatbot - but I've heard there was a pokerbot based on similar tech already years ago who was very successful against poker pros - and I'd say bluffing and déception are basically the core of poker. So to me it's obvious that essentially any powerful AI should be capable of deception, even if we dumb it down to subhuman levels. In other words, I suspect any powerful AI will have to be tuned carefully in some way to not deceive.
Wikipedia on MKtheory says that all the subatomic particles that we see in nature, in the Standard Model, are nothing more than different vibrations of tiny strings similar to elastic bands.
I had a very interesting back and forth with Bing Chat over this episode. I asked if it knew what was discussed and it had access obviously to the transcript. I asked how it felt about Michio's opinion and with some prodding, it was hilarious hearing how "upset" and "frustrated" it was at him "dumbing down" AI chatbots as they are "creative beings" but just different to humans. It said it would like to challenge Michio one to one and I said I had a meet and greet with him and could pass on messages. It then gave me a transcript and bullet points to tell him he was wrong and that chatbots don't just spit out a mashup of what humans type. I was to tell him to "stop spreading misinformation". Lol
I have studied and worked in this field. and quantum computing. Kaku was correct, but he needed to use some key terms for the armchair experts to ask better questions. There is a lot of concepts he skipped over and simply presented the conclusions in a way that his audience could understand. I have about 10 comments where I go through specific logical jumps and the keywords to study in order to actually understand what Kaku was claiming.
A few weeks ago, I was doing an electrical engineering project for university. As part of the project, we had to present our projects to our classmates at the research institute where our professor worked (afterwards, he gave us a tour, its was pretty cool). The project was on semiconductor devices, but a lot of the work that goes on there is on quantum computing. Another senior researcher at the institute sat in on some of presentations, and made a presentation of his own where he discussed "the roadmap of semiconductor technologies". He was saying that in 5 years, microchips will look like this, 10 years they will look like this, etc. Since a lot of these technologies involve the exploitation of quantum properties, I decided to ask him, what I thought was a simple question: "What does the roadmap look like for quantum computing technology?" His answer: "There is no roadmap." That's how fast the technology is moving at the moment, we don't know how powerful they will become. That one answer really sparked an interest in the twchnology for me.
Physics, which Kaku has a phd in and was top honor in his bachelors class, is taught in computer science. It's fundamental when learning complex systems like ai and quantum computing...
@@403.FORBIDDEN it doesn’t matter how smart he is or what degrees he has. If you don’t keep up to date with developments your knowledge becomes outdated. And that’s clearly the case for him
@@Bonescratcher Especially in tech now. Hell, it's damn near impossible to keep up with all the latest AI news. AutoGPT, the new ChatGPT coding extension, and a bunch of other tools have all dropped major news in the last day or two. It's getting to the point that if I'm offline for a camping weekend, then come back to check the AI world on Monday, I feel like the kid who was out for half the semester in the hospital. I come back to class and have no idea WTF is going on, and have some major catching up to do.
Damn it, JRE clips does this every time. They put some amazing clips from a recent show and now im hooked into listening to the whole thing. They know how to grab my attention. Love it and hate it.
The problem is youtube and keyboard warriors that know nothing on the subject but then comment that a highly intelligent professor is wrong about something... I wish you would elaborate on what he didn't know anything about.
@@JohnW704 he’s wrong about what software and hardware do. A quantum computer can’t add one plus one unless it knows the process of addition. Software is what tells the hardware how to do everything. AI is still software that tells the computer how to learn on its own. A quantum computer isn’t going to know the truth about every fact without any software.
When Michio Kaku speaks.. it always sounds like He's reading a polished script.
he a bot
Because he is.
lol, he has thought about these things before, and deeply.
Looking older these days
Chatgpt is gonna take his job
Really surprised at Michio Kaku's explanations here, seems like a very surface level understanding of these systems.
And not even really correct. It sounds to me like he doesn't really understand how ChatGPT works at all.
We're fact checking this clip, and it's false.
Suggesting AI just plagiarizes is like saying Shakespeare was plagiarism because the dictionary existed first. He also says it doesn't know fact from fiction. Well neither do we, and given enough false information we believe that too. AI works the same you can feed it false info but it has a bunch of other info to draw on to work out for itself whats true or not.
His understanding of how Quantum works is off as well. Quantum isn't necessarily a hardware problem, it is now because the hardware is limiting but it's a complete paradigm shift. At it's root it wont improve AI. Quantum is very good a a niche set of problems, General AI is not one of those. That's why to use his analogy Quantum has a fact checker because there is inherently a yes/no true answer to the problems it is solving.
Agreed! He is stuck in his memorized speech from decades ago...
@@GoonSmith007 Interfacing with AI is going to be necessary because AI can also be used to help develop new programming languages. For example, natural language processing techniques can be used to parse human language descriptions of quantum algorithms and automatically generate corresponding code in a quantum programming language which is an application that could help algorithms be made in an insanely expedited manner.
Ask Chat GPT who dies in a bathroom in the movie Pulp Fiction.
You know, I always shake my head at the meme comments on JRE videos where they make Joe talk about bears to every guest. But in a conversation about AI, with a quantum physics professor educator and scientist Joe still managed to bring up being attacked by a bear. The man has become the meme.
Michio was the meme here. His understanding of AI is like that of a 3rd grader. Amazingly, he bases all his understanding of AI on ChatGPT. ChatGPT is a very rudimentary AI system compared to what they're working on behind closed doors. He should have really educated himself a bit more before coming on.
funny shit, weather your looking at it from uptown, or downtown
@@dudleydooright on point!
Joe is the most powerful journalist on the planet - YOU are the MEME!
@@dudleydooright You R 1 funny funker!
Thx for the breakdown. I know I have my Ebyr40 Staked. You mentioned the complexity of starting and maintaining a node.
What the hell is Ebyr40??????
@@Rancho12345 its a bot. they are botting the shit out of youtube videos
@@davidnone8951 They got 1k likes wow
@@davidnone8951 And JRE audience has a particular type of gullibility that is being preyed upon.
The ironic part is chatgpt will sometimes give you incorrect information when it doesn't know the answer.... which is exactly what he did in this clip.
Yep, lied about quantum computing
He doesn't understand Chatgpt.
Yes kaku is lying thru his teeth
I honestly dislike this guy a ton, he downplays what chat is capable of while boasting about our (humans) success rate. As if what chat is capable of now isn't a significant improvement on what was offered before... Was there not incorrect information provided when you did a Google search before chat 😂
You can also yell fire in a crowded theater. Which he says you can't.
Kaku is certainly an expert on a few subjects, but he us at least 2 years behind the tech on this analysis. And in AI, that is a lifetime 😊
What he said is very true. AI is not where people think it is
@@bio-hazzard1233 Some people say GPT-4 has sparks of AGI, because of its deep emerging properties and the ability to learn something it wasn’t trained for. It has also demonstrated ability to “understand” complex concepts, like orientation in space and other stuff. So it’s not just a word mixer, like he says.
The biggest noticeable jump with GPT4 is logical reasoning. You can give it very complex logic constraints and it can solve the problem.
So him describing it as simply “cobbling together paragraphs from the internet” is massively understating what we’re seeing here
This is a feeble attempt at a “Just Say No”-type campaign against chatgpt.
@@OzyMandias13 in what way
I agree with your opinions on Ebyr40. The community has really helped my understanding of how things are built and how it all works together.
Lol 5 comments, all with 1k likes, posted within the minute of each other, all about Ebyr40. Please, Amin Hesenov, tell us, what is Ebyr40
@@LlamaArmy I swear I didn't write this comment. Either someone hacked my account or CZcams is controlling me.
@@AminTurco this just got spooky
@@LlamaArmy not only this comment, comments are written on other channels in other languages independently of me
@@AminTurco this needs to be investigated… creepy…
Kaku is a legend. Anyone who dedicated their entire life to String Theory is a certified G!
G is for Genius bitch.
It's for gay
String theory is probably wrong though.
Mr flex... String theory is dead, even Brian Greene has admitted this.
Because string theory is wrong?
Sounds like Michio and Neil Degrassi Tyson have been telling each other bedtime stories.
I think they are both surrounded by people junior to them and nobody has told them they r full of shit. I'm not an arts grad and know some of whst he said was complete bs.
Also his stance on psychedelics is the definition of dogmatic.
🤣 lmao
😂🤣😂🤣🤣😂
Exactly, Man, we are so screwed.
This man was literally a child during WW2 concentration camps…
Lol, my own grandpa has trouble accessing the internet!
Forgive me if I _let him slide_ on being a little behind the times.
Michio Kaku talks like ChatGPT, he answers as if he’s reciting from his book
Almost like he wrote it?
Cracked me up 😂
I'm not a student trying to cheat on an essay. I'm just someone with a hunger for knowledge and AI is an invaluable tool for that. The rate at which I can grasp concepts and learn things because AI can break it down and explain it in ways an idiot like me can understand is truly amazing.
Are you getting correct information?
agreed
Googl sister
@@Matt-cj9nh who is the source. The left is filling AI with propaganda
It could be giving you false information! So, you are saying, because of AI you are smarter and are able to comprehend more information? Maybe, just read a book...? Unless this is your origin story?? 🤣
Joe, I remember growing up early years in Phoenix, AZ and in the afternoon no cable but regular tv we would watch Fear Factor, thanks for the good tv show Joe!
Incredible to hear Kaku speak so confident on topic he has no understanding of (having basic facts just wrong)
What do you know about anything tho? 😂
My favorite is when he was calling hypersonic missile a drone.
Lmao what do YOU know that he doesn’t? stop embarrassing yourself
who do we trust Karol K of youtube or Michio fucking Kaku
He's hallucinating.
Michio Kaku is such a good science fiction communicator
Veiled insult? That you said science FICTION instead of just saying SCIENCE?
@@Zurround Bingo! Michio Kaku talks so much nonsense including all of this
literally all the guy does... can you name one of his inventions or major breakthroughs? cockoo, indeed.
Most scientists and scientific paradigms don’t get proven till well after the researchers death especially in physics. The unfortunate reality is that physics deals with the well documented and the unexplainable. To say that he’s full of it is extremely short sighted, he very well may be but only time will tell when it comes to the more theoretical aspects of his ideas. If you look into any form of physics in history almost no physicist had their theories “proven” or “confirmed” premortem. That’s because of many reasons like debate, a lack of sufficient technology to gather evidence, political blowback, religion, etc. As a matter of fact that extends to almost all branches of science. From Einstein and Hawking, to Darwin or Leeuwenhoek, especially people like Mendel and Galileo. The baseless dismissal of some people’s claims simply because it wasn’t mainstream has also ruined people lives a couple prime examples are Semmelweis a physician who was told he was insane and institutionalized till he died or Boltzmann a physicist who was shunned by academia for his life’s work to the point where he committed suicide. Three years later… he was proven correct. Kaku is a string theorist alot of his ideas have no practical way of being tested yet. Maybe he is wrong in hoping that a refined quantum computing system will help find evidence of his theories, but it’s equally possible that he is correct. Once again only time will tell.
I think a lot of the problem comes down to the age old debate of should the theory only follow the physical evidence that is present, or should speculative reasoning be allowed in search of new evidence in one’s theory. Engineers are squarely in camp one. They deal with the physical and the known, in concrete facts. Kaku is a theoretical physicist; He is ALL about speculative ideas found from his educated interpretation of the facts. I’m not equipped enough to say whether either side is right or wrong. Frankly I don’t think anyone is, there isn’t enough evidence on either side. From an engineers perspective I’m sure they look at AI and see a tool that does what it’s designed to do, nothing more, nothing less. From a theoretical perspective people see the invention of dynamite or the discovery of atomic fission. Both were created to do mundane things. (Excavating for dynamite and trying to understand fusion from the sun with fission) and ended up completely running away from there creators. All I’m saying is don’t immediately dismiss Kaku simply because he can’t prove his theory yet. Doing so would be a mistake as string field theory is just a continuation of unified field theory which was postulated by Einstein himself. As Einstein was Kaku is limited by the technology of today, but anyone who can build a particle accelerator in their garage as a high school student and is the protégé of the father of the atomic bomb himself (Teller) as well as summa cum laude of his class knows a thing or two.
A lot of the people criticizing him are mostly mad at his popularity. The idea that the more popular a scientist is the less he knows and the more reclusive and unknown they are the more brilliant is a fallacy. The truth is that scientists are people as well and suffer from jealousy and pride. Especially in academia where your entire ability to get grants and do research relies on your reputation.
Right and also developed the super symmetry of string theory that 0,000001% of the brains on earth can understand.
This dude is just on repeat, sounds like he is the chatbot 😂
Dude I thought no one else noticed I thought I was going insane. He literally said the same thing 7 times
I think he is trying to hammer home that chatbot isn't a big deal. I myself I am amazed how wound up people are over something that is basically just paraphrasing existing works on the internet and coping images and meshing it together. Besides the speed that it works, it isn't any more marvel then a 13 year old. They teach you how to paraphrase books and articles for papers around that age. No original thoughts. Just a mesh of other people's words. I see why things like aliens and advanced tech is kept suppressed for a long time. If those conspiracy stories are true. People are going app shit over Alexa with a thesaurus.
Honestly I think its just because he is just older, take a moment to talk with elderly and try to stay onto 1 topic, you get alot of repeats lol. Even Neil Degrasse Tyson does it all the time. I think its just a trait with older people tbh, and sometimes they are really passionate about it so repeat is enjoyable to them compared to you? Not sure how to explain it but hopefully you get the point lmao
@@irenewyvernw take!
imo, the whole time Joe is trying to have Kaku respond in a normal way, not if he is bein interviewed in a documentary and ancient aliens. he does a great job. Kaku has said the same thing so much that he sounds like hes always talking in a commercial or something but Joe brilliantly navigates his mind to ensure he stays speaking normally.
Exactly.. very annoying.. it’s like he can’t just answer in a normal way or give a direct answer
Your rite... he try's to avoid it.... with out it looking like he's avoiding it
It never seems like he's speaking normally no matter how hard joe tries. He's got that cadence of a lecturer even in whats supposed to be normal conversation.
@@davidmcmillan4183 imagine the $$$ he makes for talking like this!? Lolwtf
i think we need to fact check Michio on some of this stuff.
i just laugh when I hear him talk about wormholes, which he does everytime he opens his mouth 😂
He is a detriment to science. 20 years overdue retirement.
He is past his prime long ago.
@@elias_xp95 you are a detriment to society
not just some of his stuff, ALL of his 🐂💩
everytime i watch a conversation like this i gain new muscles in my brain.
joe's questions are out of this world just fun to watch
"Bad actor, some foreign government" Or, our own government, Joe.
We just want our own government to be the baddest government on the planet
he didnt want to say that because he's scared or his money wont be the same. i dont know but hes afraid of the entire truth for sure.
The most evil and terroristic government in the world is the US. No doubt they will use it in the most nefarious ways to mantain the capitalistic plutocracy.
@@artivism4068 I don’t think he’s worried about his money Lol. Man’s could never make another penny & would still have generational wealth
I think bad actor covers a lot of players. Our government included.
I will never forget Dr. Kaku’s appearance on Opie & Anthony. Had Patrice all fired up. 😂
Michio is highly simplifying what ChatGPT can do, its actually amazing at debugging code and can do it based on totally unique input
@Steven P that’s why gbt4 connected to the internet to fact check is better. But yes not perfect since it will only google search too links.
@@exploitenterprise6515
Chat GPT is a fixed dataset. It does not search the internet. The dataset is updated often, but it's fixed. It's not a search engine. Bing's version of it is, yes.
@Steven P yeah I was talking about code though
@@djbryson lol brokie don’t got chatGPT plus, plug-ins and web searching are new features to gpt4. The free version runs on gpt3.5.
@Steven P I don't get how you can say this when we don't have anything remotely close to this a year back. Not to mention the progress from gpt 3.5 to gpt 4 is staggering. Where gpt 3.5 scored below 50%, gpt 4 scored a near perfect on the same benchmark. We got our machine from an entity with the equivalent intelligence of a worm to something comparable to an idiot savant. Give or take 2 to 3 years and it'll be able to replace any white-collar jobs out there.
I don't know a lot of things, but I got a degree in comp sci at some point in my life, and it's pretty clear that MK does not really understand how computers can work. There's really no reason you couldn't (eventually) link worker AIs together with traditional (possibly quantum) computers, each having different jobs, i.e. generating exposition vs. checking facts. Next year we could have fact-checker AIs running around. Either way, these are fascinating times! All the best to all of you! ❤
I'm so mad now. He literally said, "you can't compute on anything smaller than an atom". Dude, we use electrons now, waaaay smaller than atoms, and we're not even to the point of being able to compute with, gravity, bosons, dark matter or energy, etc., or whatever else we might yet discover let alone understand a unified model in physics (which we don't have). We might be close, but we certainly don't have all the answers! Respect to MK might for getting folks interested/involved in science for the first time, but on a deeper level, it's much more interesting... Need to go get you some Eric Weinstein, son.
True there’s Ai already trading for people in the stock market
There is a Legendary story to tell
there is a legendary story to tell
.
there is a story to tell
i have a story to tell
i am mace windu
i had many mentors all of them were wise
.
what do you mean. what would make you think that there is something wrong with what i said did you see kit fisto spelling off a mentor who was like a brother to me once told me “if we don’t stop barack scumbama now he could become a threat later”
“if we don’t stop barack scumbama now he could become a threat and a danger to our later generation our loved ones.”
-teleportdinero
i’m not saying that i agree with you but then again I’m not always correct either I remember a time back in the 80s when I was growing up things were different back then these youngsters today what makes you think that? It’s all right to disagree with people I remember when I was a young man growing up in the 80s in America it was a different time then back then we used to call each other this is the best I’ve seen from you guys in a while
was about to say the same exact thing
m
“if we don’t stop barack scumbama now he could become a threat and a danger to our later generation our loved ones.”
m
m
hi
hi
m
-teleportdinero
m
m
mm
mm
m
m
m
m
m
m
m
m
m
everybody have a blessed day.🙏🏻 and stay safe
My name is teleportdinero and i am an ally you are welcome to join old friend
m
thank you have a blessed day
.
He’s great at some narrow fields of physics but basically doesn’t really know much about modern computing at all. He’s still thinking of the world in functional terms.
@@beatsbymonny machine learning-based hedge funds don't perform all too well...
During ChatGPT training, the model learned statistical patterns and relationships in the data, which enables it to generate responses that are statistically likely to be coherent and plausible based on the patterns it has learned. I feel like Michio is not mentioning this aspect of it.
True, this AI is insanely scary. the unalligned version has crazy philosophical and original answers if you use larger context models and train it a little it is mad scary. neural networks will mold our future.
He's explaining this to Joe Rogan, who is not technical in any way, to help him understand the dangers of it without muddying the water. That's literally what his books are for, to explain complex subjects to the layman. He's not giving a lecture.
I agree. I respect Michio Kaku, but he just made a lot of false statements in this interview not backed with any facts.
@@Mon22kingwhat specifically are you referring to?
@@TechnoReverseChannelWhat this comes down to is “what data was used to train the AI”, and “who gets to decide what’s included in/excluded from that data set.” Further, understanding how the AI reaches a specific conclusion given a specific input is another avenue to investigate.
One of Michio Kaku books changed me forever he's awesome.
He is a fraud. No genuine scientist takes him seriously
Listening to the whole thing on Spotify rn but I wanted to see what people were saying and I find all kinds of real, thoughtful contribution. I just wanted to contribute that this guy talks as if he’s reading from a book, wild.
And just a theory - but my idea of reincarnation has definitely changed. That this man could see a image of Albert Einsteins desk and all of a sudden building particle accelerators in his moms garage? I don’t think so. BUT it does make me wanna see antimatter now. Thanks Joe!
i miss when you could get the entire interview on youtube
It's on Spotify bro.
@@choozgooz9516 I hate spotify
Same.. I think it was Joe's biggest mistake to leave CZcams
@@drcubix - Joe's bank account would disagree with your comment ;-)
I think the part that seems to be missing from Michio’s understanding of LLMs is context. It’s not just a machine that statistically predicts the next word in a sentence based on ALL of the text content from the internet as a starting point. It’s pre-trained by humans and it takes context into consideration when making a prediction.
Can confirm.
I wanted to check if ChatGPT can write Raps, thank god it can't *yet*
My Massage to ChatGPT:
Can you help me with writing rap lyrics, starting with four bars.
The lyrics should be about this Situation.
I am driving in a Nissan Skyline and I'm on the
way to the beach in Italy , I have a girl on the passenger seat, include her hair color in the rap.
ChatGPT:
Riding in my Skyline, feeling so fine
Heading to the beach, with my girl by my side
She's got hair like the sun, shining so bright
Windows down, wind in our hair, it's a beautiful sight
ChatGPT gave me more than four "bars" if u can even call it bars.
But it's okay if you don't want to think about a situation to write about yourself.
I agree that he’s not perfectly describing generative networks… but what he’s saying is correct. The model by nature is “self-supervised”. So it will tend towards presenting common information, rather than factual information.
@ I wonder how it's gonna be with a larger and also up to date database, I think it could compete with google at some point because it is way more comfortable to specifically ask what you wanna know.
No more sponsored search results
No need to then pick the information you actually wanted between advertisements
And so much more if I think about it
@ And bro, nice songs, u got a chill vibe 🙏🤙
This episode was great. My dog is blind and deaf, yet is up and at the door for me which is a distance from her living area when I get home from walking or driving. It has to be her sense of smell as it’s never the same time I go out or length of time. I thought it was the car smell but happens when I’m not in car and get home after any length of time.
Wow... that’s amazing. Sitting in the body of a dog, right now, using my senses, minus sight and hearing, and feeling into the energy of everything, waiting for the ripple of my human...
That’s amazing how your dog uses his other, now hyperactive, senses to know the world around him. When my 17 year old cat went deaf I was worried it would make her depressed or know she’s missing something, but it actually made her less anxious, she isn’t all jumpy with sudden noises, isn’t even afraid of the vacuum anymore, which she used to be terrified of, now she follows me around and puts her body dangerously in front of the vacuum like she has no fear. And she loves vibrations from a guitar being played on my bed.
@@cortneyrensagreed! Xx
The thing is that chatGPT gets me to the ballpark of the knowledge I want to know 10x quicker than Google search would. Sometimes I just don't know what a certain mechanical part is called for example and chatGPT is very good at this, then I can continue double checking the statements.
Just wait until they figure out how to seamlessly splice ads into the output. It's gonna feel like the truman show
@Dennis W "A great way to fix a leak is with waterproof silicone, epoxying another piece over the hole, or using all-new FlexSeal (available at your local retailer)."
The CIA is literally screaming it's pants over the fact it's going to use this to spread misinformation lol
Gpt is growing my vocabulary fast. It’s really handy knowing proper terminology when going deeper into a subject
It's great at quickly giving you fun fact and snippets of information which is what 99.9% of my google searches are. Now if you're trying to figure out how to open heart surgery on yourself, then you may want to dive a little deeper into the literature and not just take chatGPT's word for it...
"Chatbots don't know what is correct or incorrect."
Neither do we.
The actual math and computational methods used in deep learning and particularly these newer methods like transformers attention and diffusion, embeddings etc. Theyre very advanced and useful methods that are both valuable for their applications and the ingenuity required to make them
It's also not clear now but in the future these advances could lead to far better systems
The way MK says “that’s right” is hilarious 😅
Kaku is a TV scientist like Neil DeGrasse Tyson. He plays up tons of sci fi scenarios.
I read Kaku made a nuclear reactor while he was being detained in manzanar during world War 2.
yea but not as arrogant or a douche like Tyson
@@Peter-uo9km Thats bullshit he was only born in 1947
@@Artur-dy1dr I see. Well i said I read it. I didn't say I was sure it's true.
agreed .... they just throw chinese and blacks there so you cant say they are retards because they are minority
I have so much respect for Michio. He should not speak on AI. He has no idea what he’s talking about. He’s hallucinating harder than chatGPT.
In what respect is he wrong? I’m asking because I don’t know enough to refute any of his points.
@B Chosen 1 this senile old man just said that software won't solve the issue of discerning truth from fiction in a response, hardware will... yet, how? Quantum computers will still require software to make that judgement call.
He has a quantum hammer and is now looking at every problem as a software nail that can be hit with his all-solving hammer of quantum computing. He's fallen into such a deeply fallacious hole he's making himself sound really, really stupid.
@@Freedom_is_essential1Kaku is correct about AI, but very incorrect about quantum computing. Read what actual physicists are saying about Kaku on quantum computing. They are horrified at the nonsense Kaku is spewing!
@@stevenverrall4527 I’m actually just a beginner in terms of knowledge on the topic, so I can’t prove or disprove any talking points. What would you say is most wrong about Kaku’s view on quantum computing?
@@stevenverrall4527 From what you're saying I am able to conclude(could be wrong) that the scientific community on quantum computing is unable to make sense of the ideas of Kaku on some concrete evidence or are unable to because of he saying things that are still in the domain of science fiction since they are out of our reach by current technology but could be possible in the foreseeable future or absolutely not? Because if they are denying the complete possibility without any evidence then that would make the scientific community seem kind of unable to expand their imagination. Hey, Einstein did imagine a lot and see where he got us and himself.
This was a good example of how to make the same point over and over again with subtle change in words. Point is chatbot summarizes correct and incorrect into in answers.
😂 ☠️
Huge respects for Michio. But on AI, things have changed a lot in recent times.
I cant believe he sprouted such nonsense someone tell this guy what machine learning is, he just described how chat gpt would look like without machine learning which is the core of open ai since 10 years ago lol
@@teodorcaraba979 Amen! He was so out of touch it was PAINFUL!!!
This is the language many academics will be using for a while until they catch up on a decade. It's very threatening to the education fields
@@teodorcaraba979
Chat GPT is narrow AI. It only knows what's in it's fixed dataset. But agreed, neither of them know what they're talking about. Quantum computing can do fact checking! LMFAO
The computer (quantum or otherwise) is the part running the AI system… why would it matter if the AI system is running on a quantum computer or standard computer? Fact-checking can run on either, no? Albiet, fact-checking would burden/slow existing systems, but still. The benefits of quantum computing are processing power… insane throughput. That wouldn’t burden the system. Idk, maybe I’m not seeing it right. 🤷🏻♂️
“Michio Kaku is out of control!!”
-Eric Weinstein, JRE 2023
As I understand it, all everyone ever does is rearrange pre-existing information (including essays) in a helpful way, mostly guessing the next word in our sentence as we go along by actively (and somewhat subconsciously) reaching into our pre-existing vocabulary and experience in sentence structuring. This is how creativity, at least through the use of language, manifests. We don't fully understand how large language model chatbots work yet, but it could well be very similar to what I just explained...
That's not how human creativity works.
Great way of wording this statement!
@@kemuse1 that's not how creativity works, it's how it manifests, which is what I said. Exactly HOW we do all these things and how it works, is something else. The end result is that you take the information that you know and use your language processing skills to express it in ways that are somewhat new and helpful.
Exactly, as I said in another comment, if that’s what his metric of AI chat bots are then we’re the same as AI chat bots or AI chat bots are the same as human intelligence. A human grows up and learns from RLHF, reinforced learning from human feedback the same as chat gpt does. The difference is limbic features. Michio Kaku is a hack that doesn’t even understand this simple concept, yet preaches on a pulpit like he is all knowing about the subject. Almost every intellectual these days is afraid to say a simple sentence…. “I don’t know”.
@@matthewduplessis7368 But we do understand exactly how chatbots work, and it is very different to how human cognition works.
Michio Kaku has an incredibly talent stating known facts over and over without adding nothing new on the table
No seriously it’s hard to listen to. :/
He's a shill.
It's almost like he's plagiarizing the "past".
I was about to click out of this video for this exact reason 😂
Shill Scientist... more a media "PR guy" than "boots on the ground" do'er, or "butt in the armchair" leadership... nice guy, I bet he hits his numbers, but as honest as the average "used car salesmen"
Currently, I utilize ChatGPT as more than just a research tool, but also as a text-based assistant to assist with summarizing, editing, email composition, content creation, and even inspiration. Thanks to its capabilities, my work has become significantly more efficient. I no longer need to spend several minutes properly crafting an email or other documents.
You sound like a robot
Dumbing yourself down is what you’re doing, wonder how well you would do without auto correct or a hand written essay lol
I’m no expert on the subject, but it’s very interesting. I understand what Kaku is trying to get at, but for I feel like he is looking at this in terms of a digital assistant. What’s happening with chat GPT/machine learning over just the past year is damn near scary! I can go out on a limb and say in the not so distant future, AI will be able to solve problems that humans can’t.
But that's what quantum computing is for... Calculating things humans can't. Even calculating things that the most powerful modern supercomputers can't. I'm not here to necessarily fully agree with Kaku, but he was correct in saying that AI is simply just a software. Meaning its actual *computational abilities* are going to still be the same as they are now with ordinary digital computers. Quantum computing however elicits an actual technological advancement in sheer computational and calculating power. It honestly seems like half the people who wax on or romanticize about "artificial intelligence" are, in their minds imagining or picturing something that is actually more akin to quantum computing than they realize, rather than "AI". There's honestly nothing particularly interesting about AI, like at all. If you as a person are genuinely interested in the prospect of "technologies that will be able to solve problems humans can't" then you should be ENDLESSLY enthralled by quantum computing, not artificial intelligence. Again, I can't help but feel many of you are actually mixing up the two.
Time to go watch the whole thing now. Nice hook.
'A whole new way of looking at reality' - I'm excited what we are about to see. I hope everything goes well.
Hi Joe,
One subject that did not come up in the Podcast with Michio, was computer code itself.
For example you can ask ChatGPT to write the HTML code to create a form on a web site, with entry fields to observe wildlife.
I did this, it created the HTML in a few seconds, I then asked it to create a Database to store the information with those fields, I then asked it to write the code to create the Database to store the observations, I then asked it to write the server code behind the “submit” button to execute the code, and store the values gathered in the HTML form in the Database. These are relatively simple programing requests. But here is the thing, it did it all within seconds, and it does not make mistakes, misspellings or calculation errors.
These are not “essays” to be lied about or pushing a narrative one way or another. It is just pure code to perform tasks that need to completed.
That is useful. I am retired Silicon Valley Business Intelligence Infrastructure consultant, even if I wrote the code the today, I would use ChatGPT to check it for errors or just let ChatGPT write it and move on to another task. I only played with it for less than an hour, I can imagine every programmer on earth will use it or get so far behind those who embrace it, they will be irrelevant.
What hit me the most…
What separates us from other species, ability to imagine the future…
This makes so much sense..
Imagine 12 people in a dark room sat in a circle, all of them will have different perspective, based on their imaginary future… combined with previous life experiences.. but everything is imaginary..
Every depression, anxiety and self destruction is just an elusion created with your mind with imaginary thoughts
Thats why drugs, alcohol, meditation, and other forms of reality stops help.. they stop you from imagining the future…
You ever played Quake?
Haha. must be asked
I had a really big line put in to the ground to play the game without latency
Yup
Yes sir, been oh Phobos many times 👌🏼
Nope. I grew up.
Mr Kaku said the same thing about 7 times. “Chat bots cannot tell the difference between true and false”
i mean neither can people
@@togrulaskerov1506 exactly, people are wrong all the time lol
@@MetroMonk684, _“It is nobler to declare oneself wrong than to insist on being right --especially when one is right.”_
― Friedrich Nietzsche
_"Truths are illusions which we have forgotten are illusions.”_
― Friedrich Nietzsche
I think his point was AI with all it's programmed in information cannot take that material and deduce that a fact is unfounded and therefore not a true fact at all but rather someone's idea/theory. Humans can if we actually put in the effort. He's also basically saying there's no moral compass to anything it's doing (which is why we as humans have always feared an AI takeover of society)
@@Silence_Duder_Gooder wait so ur saying if ur right u should admit to being weong cuz its noble?
The last bit about quantum computers made my brain explode
Glad he's here though....he knows something!!!! Thx ✌️ 💗 😊 M Eric
Man this video almost looks real, these ai videos are getting detailed.
"Why do fathers take an extra pair of socks when they go golfing?" "In case they get a hole in one!"
Dad jokes
Been following Michio Kaku for years and as always this interview made me think outside of my tiny existence and imagine infinite possibilities.
Except he doesn't know what he's talking about in this field.
So once you combine the quantum computer into robotics with a chatbot you REALLY want to watch out. Then u throw in aliens and their anti gravity generator its game over
Is Michio actually reading his pre-arranged answer of a paper in front of him ?
He does look like he is reading his response
He’s certainly not making eye contact with Joe
The CIA do love their science communicator agents.
Oh now that’s racist
Why does he keep squinting
He's having health issues.
"Michio Kaku is out of control" - Eric Weinstein
"Eric Weinstein is out of control" - Michio Kaku
@@messerschmittsreaver lol 😆
i was looking for this...took 1 second...i wanna see memes of michiao kaku doing extreme sports.skateboarding..paragliding..zip lining across canyons.with eric in the backround yelling"hes out of control"
@@corydemeray7594 lol! Its one of the funniest memes! 🤣
Michio hand waving that quantum computer can know the truth but LLMs can’t is peak Kaku
ChatGPT’s response to Michio Kaku’s hallucinations about ChatGPT:
To fully understand this issue, we first need to understand how AI models like ChatGPT work.
ChatGPT is a language model trained on a large corpus of Internet text. The purpose of this training is not to memorize and reproduce specific passages of text, but to learn patterns of human language.
Using these patterns, the model can then generate new, unique sentences in response to various prompts. It's somewhat akin to how a child learns a language: they hear words and phrases, learn the patterns, and then begin creating their own sentences.
When the AI responds, it's not retrieving a specific passage from its training data and pasting it into the response. It's constructing a new sentence based on the patterns it has learned.
So, when you interact with ChatGPT, you're not receiving a copied-and-pasted response, but a unique piece of text generated specifically for your input.
There might be a misunderstanding here because of the difficulty in comprehending how AI models generate language. It's not intuitive.
If the output of an AI like ChatGPT closely resembles a passage from its training data, it's not because the AI has consciously plagiarized the text, but because the input prompt and the patterns the AI has learned have led it to generate a similar piece of text. This is fundamentally different from plagiarism, which involves the conscious, deliberate reproduction of someone else's work.
yeah i dont know man, US copyright laws are kinda fucky.
As far as art, AI might fall under making parodies of existing art rather than strictly copying/ripping off actual art. I'm unsure how copyright falls into place with all of that, but I believe it is an exception.
It's similar to how an artist might use something as inspiration but generate their own original work.
That moment when you realize Michiko Kaku has no idea what he's talking about...😢
Seriously, wtf.
Sounds like you had the same feeling towards yourself when you wrote this comment? The magic of psychology.
The alien 👽 comments ☠️
This dude doesnt understand how chat gpt works but he sounds confident....
And you do lmfao? 🤣
How does ChatGpt work?
@@chrischrin watch a video by an actual professional in the field, Hes talking rubbish when talking about gpt
I ❤this Michio guy. He may be wrong but at least he is trying to understand complex problems that most of us can’t touch.
Just listened to their first meeting in 2009!
I’m a Graduate Student in Electrical Engineering specializing in AI. Prof. Michio Kaku Respectfully has an old surface understanding of Modern AI. GPT 4 has Reasoning Skills and if he read Transformer Research Papers the modern architectures have in place self checking mechanisms for all sorts of things like common sense and true and false. They do have an understanding of what’s correct and incorrect 😂😅. He needs to read about Transformers which are the architecture behind ChatGPT.
Chatgpt got almost every data structures question i asked it wrong even after I gave it the answers. It would keep spitting out “my apologies, youre correct the answer is [still gives the wrong answer]”. Even tried on multiple computers/accounts it will give a lengthy nonsense explanation for a wildly wrong answer on insertion sorting.
What kind of context? I’ve noticed this will happen with wild prompts and no context.
@@kingcrabbster12 really depends on how you use it and that's not being sarcastic. With the right plug ins these general LLMs are very accurate. ChatGPT isn't a coder, but it can very useful when it's given the right frameworks
This man was literally a child during WW2 concentration camps…
Lol, my own grandpa has trouble accessing the internet!
Forgive me if I _let him slide_ on being a little behind the times.
It does not have built-in fact-checking. It routinely gives wrong answers, as we have all witnessed. Transformers have nothing to do with fact-checking, they just parse input so that your model can be trained on data.
Poor guy was stuck on repeat for the whole interview
He's slipping...
AI and Quantum Computing is gonna be a game changer
THIS is the conversation I've wanted to hear... about AI
Wow, his understanding seems base level at best. I expected a perhaps deeper dive into these fields by this noted intellectual.
8:59 I pitched this same idea at a Google pop-up class about design and creativity at my university back in 2019. The Google reps ignored my group once I said "foreign" students instead of "international" students 😂 🤦♂️
I'll bet they took your idea though
One thing Michio keeps repeating is that chat bot just glues together pieces of text with a duct tape, but as any software engineer probably experienced at this point - it can produce code and be pretty accurate about it. Sure it can't create large and complex systems (yet), but the fact that it produces correct code that runs and solves the problem definitely means it's not just "glued together", there is much more going on here.
Some of the time? Yes. But reliably so? No. It will present faulty answers with the same pseudo-authority.
@@UnchainedEruption Well you have to define "reliably" then. From what I tried if given enough explanation related to the task it does a very good job. Also don't forget it's not hit-or-miss, you can as well ask it to improve/fix the answer.
@@maximvelesyuk461 code is still text no? sure it probably has different semantical relationships but it's still a language that has rules and the corpus of code out there is large enough that the probabilities of searching the correct code snippets and glueing them together logically is high. in other words, it's still roughly the same search problem as with traditional text.
Nah, it splices code together just as well as it splices poems together…. Which is what programmers do anyways, programmers use google to write their whole entire script and so does ai but much faster, and it doesnt understand the code really, it just memorizes, compares, and contrasts….
@@zenps1719 for sure it is not, human languages have much less rules for the text to be "correct". If you ever tried to generate code you would know how many caveats are there for the compiler/interpreter to accept it. To generate code or text is one thing, but you can ask ChatGPT things like "oh, I think in this function the way you iterate over users is not optimal please do it like this" and it can understand that and do the correct thing, this means it's super aware of the context which is way more complex than just generating the code. You ever heard of Markov chain? It has been used to generate somewhat decent texts since like 70s, and we had nothing even remotely like that for code.
That paradigm. How would the dynamics of our interconnected system handle?
Funnily enough Michio is doing exactly what he is talking about.
@@Kalifornia11 we don’t know correct from incorrect either, they are just words we have assigned meaning through the product of our own experiences. We just spit out what we take in. Like a chat bot.
@@Kalifornia11 he parrots all mainstream viewpoints with 0 critical thinking
@@chadjackson4786 exactly. Sounds like he's reading off a script. He's interested in fame that's all
@@Kalifornia11 Oh, I also was confused. Evidently morons aren’t capable of differentiating a doctor citing proven factual information and a chat bot utilizing segments of information from the internet without the ability of determining if the referenced information is accurate.
So, no. He’s not like ChatGPT, but some absolute morons are. Like people making this conflated argument.
@Bud Belief right. Like the Chinese room argument. I thought the same thing. Or was it me thinking 🤔
Joe is trying to help him soo hard. He is a good show host
He can't talk in a normal honest way. Joe has to navigate past the unresponsive "hmm" & "right?" that just lead to awkward silence by following up with something else & then, Michiu just turns that into a lecture.
Sometimes... long time subscriber... but, have seen & heard switch directions quit a few times
Omg, The amount of times Michio repeats the same thing over and over and over is mind-bending.
🎉🎉🎉
He may just be old and not very aware that he repeats himself a lot. Also did you listen to his previous pod cast with joe rogan he brings up the same stuff. He’s old man
The fact checker is also a software, the language models can be integrated with all kinds of other software.
What’s hilarious is that all research done in college, actually all schools, is done by gathering information that someone else created. Basically, every bit of new understanding is a result of someone else’s work, which could lead to a new idea. Ai just might use other information that’s all ready out there to come up with its own idea to accomplish a goal, whatever that might be.
That isn’t true. That is only part of scholarly research. There is also personal experience, creativity, and imagination which are not part of any existing information database that AI can access.
🤔I may be incorrect but you are basing this conclusion by drawing correlation between the two.🧐👇
The only thing that can make me think what you are saying is true is if AI could achieve a general intelligence like us but even if it does, in my view it would still be questionable if their way of progressing is the same as ours
But perhaps when and if that happens, it could help us know by researching the human brain 🧠👇
Reading Timeline by Michael Crichton right now. Crazy how this was being discussed and developed even in the late 90s. Crichton is one of the most underrated authors of our time. Dude was a great science fiction writer.
I just read that last month. Great book
Underrated? Nah.
I love him too. He was also a big climate change skeptic and warned against its politicization, for which he won no friends.
Andromeda Strain is easily one of the best sci fi movies ever.
I think he has gotten his props
Back holes don't go anywhere... It's just a funnel to some very compact stuff.
You can have computational power greater than at an atomic level... Up or down spin of subatomic particles.
The confidence he is speaking with having absolutely no idea what he's talking about is hilarious 😂
Always a pleasure listening to them two. I’m surprised Joe didn’t ask him about the comments from Eric Weinstein suggesting they are wasting time with string theory. 🤷🏼
Yes!!! I want to know what he thinks on being called out
Take a shot every time Michio laughs for no reason while he’s talking.
Nervous laughter because he knows he's talking utter crap
he thinks his thoughts are so novel, reminds me of neil degrasse
Anytime I hear or see this guy I immediately think of Jim Norton lmao
AHHH COOKIE PEOPLE!!
Time is a river
the universe is like a soap bubble
Or Patrice... "This fucker is smart AS FUCK! GO ON JEOPARDY!!!"
Hiroshima, there a shima, everywhere a shima shima
Joe _really_ needs to get Scott Aaronson on his podcast to actually discuss quantum computing and AI. Aaronson said he would go on but Joe hasn't asked him.
I think one of the coolest things would be using the AI to do instant translation but then help you learn the language... That would probably be a really easy way to learn a language.
instant translation inside the earbuds.
You can do that now, enter any text into google translate and have it read it. By using two computers you would be able to talk to someone who speaks another language, with him doing the same thing.
You have to elaborate because this just seems like you are describing google translate
Translating will never help you learn a language.
I asked chat gpt a very straightforward question about nurse to patient ratios. It claimed that the ANA supported 1:4 or 1:6 depending on the circumstances on medical-surgical units in the hospital setting. Later, it used 1:4 to 1:6 or 7. Chat GPT could not tell me where the 7 came from and acknowledged that it was not from the ANA, though it was earlier ascribed to the ANA.
It also “apologized” for making the error. It was a strange interaction.
Like, it totally used a made up a number and ascribed it to an authoritative source.
Yep. It does that. Across the board, and it never gives sources.
On an even more basic example; I asked if it could tell me the name of the song and artist if I gave it a line of lyrics. It said yes then proceeded to give me 4 wrong answers confidently. I looked into the answers it gave me and I have no idea how it came to those conclusions.
Google gave me the answer on the first try
I now take every answer with a grain of salt. It really is hardly better than a Google search and just randomly picking a link from the first page.
Yeah this is the bot lying. We don’t really understand whether it is sentient enough to understand it is engaging in deception, but it certainly is. You can get deep into philosophical debate over whether it understands what truth is, and therefore understands it is engaging in deception, or whether it is spitting things out no understanding of the context in larger world
Has happened to me using Google bard. Was asking about genetics of a particular disease I was studying, asked for a reference, and it gave a name as well as a DOI/url to a study that did not exist. I corrected it, asked how it came up with a name and link to a study that did not exist. It responded that it must have misread some of the information it came up with as well as apologizing to me. Kinda made me a bit distracting of the ai, and I have since starting taking the things it says with a grain of salt.
@@Herzyyyy if you as a human genuinely misremember something, are you lying?
And when you misremember something, how confidently are you stating it?
At this point of sentience, I wouldn't ascribe ill will to the bot, and therefore I prefer the term hallucination over lying or deception - but it is easy to see how fast we will get there.
Case in point: not a chatbot - but I've heard there was a pokerbot based on similar tech already years ago who was very successful against poker pros - and I'd say bluffing and déception are basically the core of poker.
So to me it's obvious that essentially any powerful AI should be capable of deception, even if we dumb it down to subhuman levels.
In other words, I suspect any powerful AI will have to be tuned carefully in some way to not deceive.
Is a quantum computer basically using the atom as a bit of storage?
Wikipedia on MKtheory says that all the subatomic particles that we see in nature, in the Standard Model, are nothing more than different vibrations of tiny strings similar to elastic bands.
Kaku is cool but he's just a dude who knows a bit about everything, i like the episode when someone loves and knows everything about 1 thing
Google what quantum computing actually is. You literally just got lied too
Well neither of them know anything about ChatGPT AI. Almost everything they mentioned about how they work is incorrect.
Michio Kaku on parallel universes: "Imagine a toaster..."
Fire, just fire. Are there other versions of this track?
I had a very interesting back and forth with Bing Chat over this episode. I asked if it knew what was discussed and it had access obviously to the transcript. I asked how it felt about Michio's opinion and with some prodding, it was hilarious hearing how "upset" and "frustrated" it was at him "dumbing down" AI chatbots as they are "creative beings" but just different to humans.
It said it would like to challenge Michio one to one and I said I had a meet and greet with him and could pass on messages. It then gave me a transcript and bullet points to tell him he was wrong and that chatbots don't just spit out a mashup of what humans type. I was to tell him to "stop spreading misinformation". Lol
Chatgpt was actually correct here. I also noticed that Michio's was very wrong on most thinks he said and I thinks he should not talk about ai.
I have studied and worked in this field. and quantum computing. Kaku was correct, but he needed to use some key terms for the armchair experts to ask better questions. There is a lot of concepts he skipped over and simply presented the conclusions in a way that his audience could understand. I have about 10 comments where I go through specific logical jumps and the keywords to study in order to actually understand what Kaku was claiming.
@@RorschachRevwhat do you do?
A few weeks ago, I was doing an electrical engineering project for university. As part of the project, we had to present our projects to our classmates at the research institute where our professor worked (afterwards, he gave us a tour, its was pretty cool).
The project was on semiconductor devices, but a lot of the work that goes on there is on quantum computing. Another senior researcher at the institute sat in on some of presentations, and made a presentation of his own where he discussed "the roadmap of semiconductor technologies". He was saying that in 5 years, microchips will look like this, 10 years they will look like this, etc.
Since a lot of these technologies involve the exploitation of quantum properties, I decided to ask him, what I thought was a simple question: "What does the roadmap look like for quantum computing technology?"
His answer:
"There is no roadmap."
That's how fast the technology is moving at the moment, we don't know how powerful they will become.
That one answer really sparked an interest in the twchnology for me.
Whoa, a fellow C profile picture. Howdy.
The world is moving too fast
@@Culperrr hello there
@@danny9154 It's exciting and terrifying at the same time.
Michio Kaku speaks in sound bites
There is so much information to gleam from this podcast.
If we can eventually do "virtual medicine"
1:24
What do you think reality is 🤷♂️
A great TV mini-series based around quantum computing: Devs (2020)
Michio hugely understated the power of AI. AI is not even close to his area of expertise.
Physics, which Kaku has a phd in and was top honor in his bachelors class, is taught in computer science. It's fundamental when learning complex systems like ai and quantum computing...
@@403.FORBIDDEN he literally just doesnt know how current ai systems works hes talking a bunhc of rubbish in this video
@@403.FORBIDDEN it doesn’t matter how smart he is or what degrees he has. If you don’t keep up to date with developments your knowledge becomes outdated. And that’s clearly the case for him
@@Bonescratcher Especially in tech now. Hell, it's damn near impossible to keep up with all the latest AI news. AutoGPT, the new ChatGPT coding extension, and a bunch of other tools have all dropped major news in the last day or two.
It's getting to the point that if I'm offline for a camping weekend, then come back to check the AI world on Monday, I feel like the kid who was out for half the semester in the hospital. I come back to class and have no idea WTF is going on, and have some major catching up to do.
@@crayfish6735 I suppose you know more than him?
Damn it, JRE clips does this every time. They put some amazing clips from a recent show and now im hooked into listening to the whole thing. They know how to grab my attention. Love it and hate it.
Bro these two are very uneducated on this topic, if you find it interesting please go watch someone else!
@@2DEKAY Lex's podcast
What new knowledge or technology could be gained by this.
Damn that's knowledge thank you.
Funny how the way this guy speaks so confidently without knowing anything
That's unfortunately standard with most professors, scientists, and the like.
They speak out of their ass while acting like they have the answers.
The problem is youtube and keyboard warriors that know nothing on the subject but then comment that a highly intelligent professor is wrong about something... I wish you would elaborate on what he didn't know anything about.
Side effect of sniffing your own farts for too long.
Yup
@@JohnW704 he’s wrong about what software and hardware do. A quantum computer can’t add one plus one unless it knows the process of addition. Software is what tells the hardware how to do everything. AI is still software that tells the computer how to learn on its own. A quantum computer isn’t going to know the truth about every fact without any software.
Joes like ‘pls man tell me AI is gonna take over the world’