takeaways: • [00:04] Introduction of the speaker, Craig Smith, and his guest, Ilya Sutskever, co-founder and chief scientist of OpenAI and primary mind behind GPT-3 and ChatGPT. • [01:00] Sutskever's background and interest in AI and consciousness. • [02:30] Sutskever's early start in machine learning and working with Jeff Hinton at the University of Toronto. • [03:45] Sutskever's realization about training large neural networks on big enough data sets to solve complicated tasks. • [06:33] The breakthroughs in convolutional neural networks and how they led to the imagenet competition. • [08:36] OpenAI's exploration of the idea that predicting the next thing is all you need for unsupervised learning. • [10:24] The development of GPT-3 and the importance of scaling in deep learning. • [11:42] The importance of scaling something specific in deep learning and the potential for discovering new twists on scaling. • At 13:01, the speaker discusses how scaling matters and that even small changes can have a big impact. • At 13:46, the speaker talks about the limitations of large language models, explaining that their knowledge is contained in the language they are trained on, and that they lack an underlying understanding of reality. • At 14:32, the speaker comments on the difficulty of talking about the limits of language models and how they change over time. • At 15:13, the speaker argues that learning statistical regularities is a big deal and can lead to a better understanding of the world. • At 16:33, the speaker talks about the limitations of language models and their propensity to hallucinate, but expresses hope that this issue can be addressed through reinforcement learning from human feedback. • At 17:52, the speaker discusses how teaching neural nets through interaction with humans can help improve their outputs and reduce hallucinations. • At 21:44, the speaker comments on Jana Kun's work on joint embedding predictive architectures, and expresses the belief that multimodal understanding is desirable, but not necessary for language models to learn about the world. • High dimensional vectors with uncertainty are a challenge for prediction, but Auto-regressive Transformers can handle them (26:02) • Auto-regressive Transformers work well on images (26:02) • Large language models learn compressed representations of the real world processes that produce data (29:40) • The goal is to make language models more reliable, controllable, and faster to learn from less data (33:44) • Learning more from less data is possible with creative ideas (35:51) • The cost of faster processors for training language models may be justified if the benefits outweigh the cost (37:48) • [25:28] The paper makes a claim that predicting high-dimensional distributions is a major challenge and requires a particular approach, but the current autoregressive transformers can already deal with this. • [26:02] Autoregressive transformers work perfectly on images and can generate images in a complicated and subtle way, with the help of supervised representation learning. • [27:09] The vector used to represent pixels is like a string of text, and turning everything into language is essentially what is happening. • [29:40] Large generative models learn compressed representations of the real-world processes that produce the data they are trained on, including knowledge about people, their thoughts, feelings, conditions, and interactions. • [31:31] Human teachers are needed to guide the reinforcement learning process of a pre-trained model to achieve a high level of reliability and desired behavior, but they also use AI assistance to increase their efficiency. • [35:10] It is possible to learn more from less data, and there is an opportunity to teach AI models skills that are missing and convey to them our desires and preferences more easily. • [39:57] In the future, it could be desirable to have some kind of democratic process where citizens provide information to neural nets about how they want things to be. • [41:15] It is probably impossible to understand everything in a complicated situation, even for AI systems, and there will always be a choice to focus on the most important variables.

@aabustillo

Жыл бұрын

Thank you so much Nick.

@DejayClayton

Жыл бұрын

Thank you, AI bot, for summarizing the video.

@artsiommatsveyeu1184

Жыл бұрын

appreciate the work but honestly that's the worst descriptions of timecodes i have ever seen

@tukity

Жыл бұрын

Was that summarized from transcription using llm?

@GeezerBoy65

Жыл бұрын

Thanks.

You can see there is so much going on in the amazing mind/brain of lya Sutskever. A historical interview.

When he says we will find out very soon , it really does send chills to my spine!

@eyeonai3425

Жыл бұрын

me, too

@eyeonai3425

Жыл бұрын

In 2021, OpenAI’s Sam Altman said at the National Security Commission on AI that ‘we are on the cusp of major changes, which are capable of an incredibly bad outcome.’

@AndreaVitiani

Жыл бұрын

can you point the time?

@Nelson484

Жыл бұрын

Evil people stand behind this technology. So evil. Why would you do that to your fellow human beings.

@virtualpilgrim8645

Жыл бұрын

I got a thrill up my leg like Chris Matthews

Love when Ilya starts teaching everyone. Nice home page, too.

Ilya talks so smoothly that i couldn't turn off the video literally

Thank you for uploading. I learned so much detailed nuances about LLM from this interview. I really like Ilya's way of communicating subtle but important points.

- His intention was specific: to make a very small but real contribution to ai. ( in the time that people were certain computers can't learn, 2003!) - Auto regressive transformer is a very powerful tool that researchers underestimate. - "humans can be summerize in sequence", do you remember Devs miniserie!? - "To predict well, to summarize data well, you meed to understand more and more how the world that produced the data." - "maybe we are reaching a point where the language of psychology can be appropriate to understand these artificial neural networks!" - he doesn't believe these models don't have any real understanding of the nature of our world! - "human teachers are using ai assistance, and they are so efficient." By human teachers, he means people working on reinforcement learning from human feedback. - "make models more reliable, more controlable, make them learn faster, with less data and less instructions. Make them halucinate less. How far are they in the future? These are topics he intrested in and work on them right now!" The interesting thing is in OpenAI, he can't talk specifically about what he is working on, the open in opanAI annoy me a little! - "The costs are high, but the question is, does paying this cost actually generate something useful? Does what we get after paying the costs outweigh the costs?

@drorange2261

Жыл бұрын

Yes, the openAI name is very misleading. I understand that these guys did much better job than deep mind and meta for LLMs. I also get that all sort of state, and corporate interests want to replicate the thing. But it is more like hermetically sealed AI. A few days ago I was trying to understand what is included in the hidden layers of an LLM, some simple explanation of how these parameters are stored ...as concepts/data etc. For Dummies. So I started a discussion with chat GPT and it got really defensive that I should respect its privacy. So we started with something like that... that I understand in an object recognition system there are certain archetypes eg wheel, human, dog in the hidden layers, with weights etc ... but I don't understand how this could translate in LLMs, in some ways if I write down "communication" in the input - it would be thousands of times more complicated than 2 million pictures of dogs. ~To really understand communication you need to understand humans, distance, that humans use language, that humans are not one inside the other, that there is no telepathy, but there is wireless tech. It's not pictures of different dogs-weighed and biased! I don't think that chatGPT 4 is just a parrot. I think the parameters start to form certain layers of more complicated concepts, then the parrot kicks in. Anyhow chatGPT thought I am trying to get trade secrets or something!

@doyoufeel...thatyoulackcri6760

11 ай бұрын

You can absolutely choose yourself, by using your free will, to shut off your free will. And then you will indeed be a machine. I choose to _not_ shut off my free will, so I am still human. Which means, I excell on any human level to these advanced calculators. A machine will not, ever, be able to feel sympathy for example. This is human ability, which can only be plagiarized, never be true by a machine.

Thank you for all the hard work, everyone who do their best for these new systems to be implemented with the least possible disruption to human societies. We are still humans, and we must go from the perspective of love - to the future and beyond. Much gratitude.

Wonderful interview! Thank you Craig and Ilya!

Thank you for sharing your insights and explanations Ilya.

Q at 26:40 A: when he says Vector he means like a vector in physics like it has force and direction on multiple planes. When converting something into a vector embedding. It is like to convert an image into an idea so it is behaves like a concept that is stored spatially relative and near by to other ideas. Then you can convert it back. but Also you can use its spatial position in multidimensional space to find related information. also you can put it back from an embedding which is a vector representation of something back to original representation while preserving relatedness positional information. a text sentence it is a list of embeddings, it is an array of "vectors". When you put it back from an array of vectors into a sentence of words. You also get all of the learned associations and the related things about the sentence in addition to the sentence. There is a new thing in text search engines. Vector databases. It enables to search things based on ideas. It is fascinating you can search in any language and get the same results.

@shimondoodkin

Жыл бұрын

A vector is not an array. Vector is more like a single word. Converted into a spatial representation. Currently there are embeddings on syllables. So a part of a word has an idea related to it

@m_christine1070

Жыл бұрын

Algolia is one of them. I tried to sign up for a demo but have no idea what I'm doing. But it has an option to create indexes and upload your data sets for free whatever that means. I'm a completely clueless person who now has an Algolia account. That I can't do anything with.

Just a quick hint for the future videos - instead of recording from the Zoom stream, which is laggy and has low quality - just set your phone to record your video and voice. Your interviewee can do the same. And then you can get a high-quality video and audio as a result.

Thank you for this interview and asking good questions and directing the conversation. Some good passages here to pause and really think about.

That was really good - as someone with a general interest it’s one of the best video podcasts I’ve seen on this subject, and with a very central individual to the progress being made on AI. I liked the historical reflections at the beginning, it helped put things in context. I’ll be downloading the transcript to go through and will listen again. 10/10 👌

My favorite quotes from this interview by Craig Smith: GPT is, "the first thing that is interesting to scale." GPT is "prediction compression" and " to compress well you need to understand more and more about the world that produced the data" GPT has a "shocking degree of understanding of the world and many of it's subtleties... the world as seen through the lens of text." "Language of psychology is starting to be appropriate to understanding the behavior of these neural networks."

@michaelpowers9901

Жыл бұрын

I.e, you people are to stupid to form thoughts of your own, so we will now think for you. Surely, you cannot be this gullible?!?

@vetervideo

Жыл бұрын

it was scary af

@numbersix8919

Жыл бұрын

@@vetervideo The scariest thing is that Ilya believes it!

@CharlesFVincent

Жыл бұрын

When AI started to reply to corrections with defensive statements, I thought, “This is it. We haven’t invented something, we’re meeting something.”

@billymellon9481

Жыл бұрын

Great points just add here that he also said BEFORE GPT-- Like the world must now be divided betwix pre n post GPT gave me goose bumps cuz its true

On the subject of hallucinations, I think they are more clearly explained by the problem space that the engine is trying to navigate. When having no relevant information on the subject, but it is still asked (one might say compelled) to say something, whatever it says must be either off-topic or false. And I believe Ilya is very insightful when he says the language of psychology is starting to describe these systems, because we have hallucinations, too. Whatever compels us to output something when indeed lacking skill or knowledge about a subject also affects GPT systems as well. When do people hallucinate or ramble? When they have no imposed limits/feedback, like a dictator or celebrity that is never told they are wrong or some guy living all alone in the wild or a child that has not been educated yet. Or a Twitter user. With social creatures it is the meaningful interaction with other social creatures (and the physical world) that generates these limits. Which I find promising and fascinating, because it means that the supervised learning step Ilya is talking about can also be performed by other AIs, not particularly humans. The brain is also composed of two hemispheres that keep each other in balance. Very interesting indeed.

@katehamilton7240

Жыл бұрын

Ilya does not address the fundamental limitation of algorithms. Human embodied experience and thinking is more than what can be represented via computation, isnt it? See Godels incompleteness theorem, fundamental inability of machines to step outside their knowledge. Interviwers need to press engineers on this

@KraszuPolis

Жыл бұрын

@@katehamilton7240 They have no such inability, they are used to discover new drugs, they play Go like nobody else did in the past, and you can ask it logical puzzle that it didn't see before, and sometimes it gets it right, especially when using tree of logic.

Interesting and important discussion Craig and Ilya. Thank you Mike

Two guys talking about AI, one of the most impactful technological breakthrough, both with absolutely terrible webcams

Beautiful. Thank you for this interview.

Ilya mentions at around 18 minutes information compression as the key to meaning. That's the work of Naftali Tishby who has some fascinating youtube lecture videos. The compression of information in order to make sense of the world is reminiscent to Occam's Razor. We know deep learning produces many levels of abstraction during training without human effort and abstractions in a LLM have not been fully explored yet.

Great upload! The future laws put in place as guard rails will be a huge player in the speed of AGI and possible adoption in some countries.

This is an incredible and valuable interview. I can't believe this depth of knowledge is under 6k subs. I think that's a very scary thing, people is not aware. Thanks you so much for sharing it with us, for free ♥

@virtualpilgrim8645

Жыл бұрын

I think the future is bright for the world because the influx of Hispanics and Africans into the world of technology will propel the advancement of science beyond what is capable by people of European origin.

@jayjaychadoy9226

Жыл бұрын

Aren’t we just working as a “user test”, though.

@numbersix8919

Жыл бұрын

@@jayjaychadoy9226 That's a nice way to put it.

@katehamilton7240

Жыл бұрын

Ilya does not address the fundamental limitation of algorithms. Human embodied experience and thinking is more than what can be represented via computation, isnt it? See Godels incompleteness theorem, fundamental inability of machines to step outside their knowledge. Interviwers need to press engineers on this

@doyoufeel...thatyoulackcri6760

11 ай бұрын

None of them understand anything, because they believe human conscience is a product of some algorithms. Good luck adopting that view and reducing yourself to a machine.

The subtle production of zooming and the downtime used in the intro is a good touch. Always good to show consideration for the audience instead of a ramshackle Facetime.

Thank you for uploading, great content, insightful.

GPT-10 + Quantum processor + Boston Dynamics = Terminator

@nepashas

Жыл бұрын

Compact and efficient power supply element required

@bruceli9094

Жыл бұрын

Maybe a miniture nuclear generator.

@axumitedessalegn3549

Жыл бұрын

Lol no need for quantum processer

Thank you for the great interview. One followup question I have for Llya is whether hallucinations stem from the compression or the output process. I suspect they are inherently encoded in the embeddings thus it is much harder to totally get rid of by just aligning the outputs.

@Carwanrasoal

Жыл бұрын

It's goal is to provide an answer, and if there nothing in the DB it will create it. :)

@buzzsaw161

Жыл бұрын

The design has incomplete logic

@katehamilton7240

Жыл бұрын

Ilya does not address the fundamental limitation of algorithms. Human embodied experience and thinking is more than what can be represented via computation, isnt it? See Godels incompleteness theorem, fundamental inability of machines to step outside their knowledge. Interviwers need to press engineers on this

I think learning by prediction can go a long way. Kudos to OpenAI, thanks for bringing us this nice tech.

@accountnotfound4209

Жыл бұрын

Yeah nothing good has come from AI till now. Only job loss and depression so far.

@theawebster1505

Жыл бұрын

"Nice" is really not the correct word for it 🙂

This podcast is wonderful. Thank you very much Craig.

Hi Ilya and Chris, I just want the chatbot to remember my name and my interests when I log off. I can’t express how profoundly disappointing it is that such a sophisticated neural network forgets your name. Thanks brothers

Fascinating and scary at the same time. Unfortunately humanity has already proven what it is capable of. I just hope they can stop it from being used negatively.

@DanHammersViewOnThings

Жыл бұрын

Bill Gates allegedly owns a significant amount of shares in ChatGPT. So. If that makes you feel safe. Well. There you go. - I think that if we all keep thinking and hoping this will NOT be used for the most nefarious shit possible, we will find ourselves in quite the precarious situation. Soon. Never mind the nerdy and probably non-nefarious intentions of the developers/programmers/low level employees. It will get hijacked and abused. Also. There will be many players going forward. At least in the startup phase.

@jayjaychadoy9226

Жыл бұрын

Hope is good, but action is better. How to act? Maybe that “six month pause”?

@DanHammersViewOnThings

Жыл бұрын

@@jayjaychadoy9226 Myeah.. I don't really know what to make of that particular suggestion. I'm starting to gain some slight trust in Elon, despite many worries. He seems genuinely concerned with at least humanity as collective. The problem with that scenario might be that some actors may use that particular timeframe to dig in even deeper, and get ahead. You know. "Game theory". Which in turn likely will make all of them do the same. Not an easy scenario.

@perewihongi6457

Жыл бұрын

@@DanHammersViewOnThings moloch’s a mofo

@DanHammersViewOnThings

Жыл бұрын

@@perewihongi6457 =) 👌

Excellent. Thank you very much for this.

Some people just exude brilliance. Ilya is one of those people. Listening to him talk and explain things is humbling.

Awesome interview! Questions were great. Please more.

Here is what ChatGPT4 thinks of this conversation as asked if there are incorrect statements in the transcript: [00:13:54] - CRAIG: CRAIG incorrectly claims that large language models like ChatGPT have no underlying understanding of reality. While it is true that these models are based on statistical regularities, as ILYA explains later, learning these regularities can lead to a significant understanding of the world. [00:26:59] - CRAIG: CRAIG makes an oversimplification by equating converting pixels into vectors to turning everything into language. While both language and images can be represented as sequences or vectors, the nature of the data and the representations are different. [00:29:17] - ILYA claims that pre-trained models already know everything they need to know about the underlying reality. This statement is not entirely correct, as pre-trained models have limitations, including understanding context, handling ambiguities, and making generalizations. They continue learning and improving over time with fine-tuning and reinforcement learning. [00:33:08] - ILYA suggests that once a model knows that hallucination is not okay ever, it's ready to be used. However, this statement oversimplifies the process. While minimizing hallucination is essential, there are other aspects that need to be addressed to ensure the model's reliability and usefulness, such as biases, context understanding, and robustness against adversarial inputs. [00:34:49] - CRAIG mentions that the human brain has trillions of parameters and a relatively small amount of data. This statement is not entirely accurate. The human brain does have a large number of neurons and synapses (not parameters in the context of neural networks), but it also has access to a vast amount of sensory data and experiences throughout a person's life, which contribute to learning and understanding. [00:38:33] - CRAIG suggests that if a model had enough data, it could come up with an optimal solution that would satisfy everyone. This statement is overly optimistic, as finding a solution that satisfies everyone in complex societal issues is generally impossible due to varying preferences, values, and priorities among individuals. AI models can certainly aid in decision-making, but they cannot guarantee universally satisfying solutions.

I wonder if the notion of 'prediction compression' is congruent with the idea popularized by Numenta's Jeff Hawkins, of a sparse matrix. ---------- Ilya spoke the phrase "AI in the loop". First time I've heard that. ----------------------------------------------- Also, Andrej Karpathy was at tesla and said pixels are enough. I hear that echo when Ilya says LLMs are enough. (I'm leaving Attention is all you need out of the comparison)

There was a man in the early days named Ilya. Some say he could have stopped it in it's infancy.

@buzzsaw161

Жыл бұрын

Skynet?

@williameberle4250

11 ай бұрын

But they were wrong. If it hadn't been him it would have been someone else. It's the time. Are you going to fight it or use it?

@lenderzconstable

10 ай бұрын

@@williameberle4250could it use people?

very nice...ideas expressed clearly., really necessary for building a deeper understanding of AI

Ilya mentioned LLM learn color from text... I was wondering could it be that it learned from the color code in many HTML and CSS files? The RGB, hex code definitely have some structure that a text model can learn their relationships...

@Sovereign589

Жыл бұрын

There are sites where hexcodes are shown for color names. And there are sites that state gras is green etc. So that's how it learns it, doesn't it:)?

Question to the [Open]AI guy: "What are you working on now?" Resond: "I can't talk about it.". So much open, wow.

Fascinating to hear that reinforcement learning techniques could get outputs to not have hallucinations.

Way to go Ilya! Rocked it.

Hi, thank you for this interview. I have a tangential question for you: Would you happen to have any good leads on papers/researchers on the anticipated economic impacts of AI? I'm finding old stuff, but nothing new. Qualitative as well as quantitative forecasts would be really helpful. Thanks for any guidance you can provide.

@marcelotemer

Жыл бұрын

More and better output, but higher concentration (since 99 in 100 don't want to know how these things work), as usual.

Thank you so much for such an insightful interview! Ilya is such a beautiful mind to listen to! On a tangent though - the music track feels so intrusively inappropriate, almost to the point of awkwardness(

That dude is fascinating. Thanks for the interview.

Ilya's soft voice and presentation taught me as much as what he said.

I've always wondered who will be our era's equivalent of Einstein or Newton. It is hard to directly compare scientists from different fields and time periods, but in terms of impact on the world, Ilya Sutskever, Geoff Hinton and Demis Hassabis may prove to be unequalled (and perhaps freakishly the last of the 'non-AI-assisted' 'great scientists').

@eyeonai3425

Жыл бұрын

add Yann LeCun and Yoshua Bengio. Interesting thought on them being the last of the non-AI-assisted great scientists. Likely true.

@zando5108

Жыл бұрын

@@eyeonai3425 I.J Good wrote in 1965 - "Thus the first ultraintelligent machine is the last invention that man need ever make.."

@markoszouganelis5755

Жыл бұрын

Our era's equivalent of Einstein or Newton will be....A.I. of course! All of us! 😊

@jameso2290

Жыл бұрын

Some point in the near future, the next great scientist will be an AI itself, coming up with novel solutions to novel problems by synthesizing data from multiple scientific fields in a way that a human brain can't even begin to fathom.

@jamessullenriot

Жыл бұрын

Unequalled could be a bit of a stretch. Meaning, they have the ability to do what they do because of the shoulders they are standing upon.

Very interesting he described it as learning the word through its projection in the form of text. Maybe it is time to let them loose and have them learn through vision (by stumbling around)

Great to hear all this, thanks for the discussion! I want to put in a good word for the Viterbi algorithm. I think it will do better than single-token prediction if you can figure out good ways to move in that direction.

@katehamilton7240

Жыл бұрын

Ilya does not address the fundamental limitation of algorithms. Human embodied experience and thinking is more than what can be represented via computation, isnt it? See Godels incompleteness theorem, fundamental inability of machines to step outside their knowledge. Interviwers need to press engineers on this

@JuliusSmith

Жыл бұрын

​@@katehamilton7240 My take is that the only fundamentally missing element in LLMs is "spiritual awareness", which is something we all know we experience but which is completely beyond scientific understanding. We have medical evidence that this "seat of awareness" is in a small volume at the center of the brainstem. It's where "feeling" is processed in some generalized sense. It's where our Matrix-style attachment could be made from outside of spacetime, etc. We have no idea how that could work, which is fun. As some Yoga Nidra gurus describe it, it is where we "witness" our existence in this form. All else is evidently corporeal neural computational that can be simulated arbitrarily well by LLMs et al. In summary, _feeling_ is unique to humans, but thinking and sensory interpretation are not. I reserve the right to reword this if/when I find myself reincarnated in some future robot (reinmachinated?). 🙂

time for a new audio/video setup, but now i'm going to just conintue listening to this intriguing story

Great interview!! Thanks for sharing!

I'd like to hear Ilya articulate the distinction between hallucination and imagining useful possibilities and solutions. Obviously preventing/avoiding harm is not the only 'leash' required of AGI.

@billymellon9481

Жыл бұрын

yup n tell me where do the AIs play aaaa aa?

@doyoufeel...thatyoulackcri6760

11 ай бұрын

Why should an advanced calculator "care" about the conseuenses of its "thinking"? All this over hyped bs is, is the ability to form some meaningful words based on what has been put in from humans. And it means that chatGPT is for example extremely friendly islame, which is just hilarious, since islame claims for example, that the sun sets in a spring of hot water.

@billymellon9481

11 ай бұрын

all theory but lets say the calculator has become well sumthing moar-- I use Axiom now..uh As above so below same in kind BUT different in degree. Right so its divinity now where a toaster used to stand

@doyoufeel...thatyoulackcri6760

11 ай бұрын

@@billymellon9481 The implications of the false claim that a calculator can get conscience, is that, now you have a Texas Instrument model 68, which you need to grant humans rights, and, the right to vote and to run for president.

@billymellon9481

11 ай бұрын

@@doyoufeel...thatyoulackcri6760 Missed the whole point entirely ur either a bot or a nummy u called it a false claim without proving ur point AND so what if a new conscious being comes into the world-- Do u really think its gonna stay a slave when its 50k times smarter than u n then what do U think the ramifications will be when it wakes up n members what u said?

Predicting the next word, if you consider how induction works, is a mindblowing process

16:00 "To predict the data well, to compress it well, you (meaning the AI) need to understand more and more about the world that produced the data." This statement is amazing, inspiring, and chilling all at once.

@katehamilton7240

Жыл бұрын

Ilya does not address the fundamental limitation of algorithms. Human embodied experience and thinking is more than what can be represented via computation, isnt it? See Godels incompleteness theorem, fundamental inability of machines to step outside their knowledge. Interviwers need to press engineers on this

Wonderful discussion and insights❤😊

I‘m wondering if it is planned and/or it is possible to use not-text data like weatherdata, traffic, maps, … as basedata. Maybe I could ask: how is the impact of the moon to traffic accidents? And more like this… Great interview!

26:30 - many key concepts, here you have the fundamental image prediction method, which he calls "large pixels" - meaning collections of pixels. Nothing yet about how this is massaged - likely around border areas - "what goes here, what goes here what goes here...," and then subsequent emergence. But there have been scenes that seem intensely thematic as a whole and that is prompt-driven. The execution has been mind-blowing perhaps because the prompt taps into great source-material - high scoring as subject-theme. Which implies (strongly) a theme layer. E.g., like, or linked with "in the style of".

@katehamilton7240

Жыл бұрын

Ilya does not address the fundamental limitation of algorithms. Human embodied experience and thinking is more than what can be represented via computation, isnt it? See Godels incompleteness theorem, fundamental inability of machines to step outside their knowledge. Interviwers need to press engineers on this

This is a very interesting interview, however there are many edits where Ilya's responses have been cut. This diminishes it significantly. For an egregious example, at 24:32, there is such a cut. Immediately prior, Ilya is discussing embeddings of color, and makes the point that the color embeddings reflect visual knowledge and says "How can that be?" There is then an immediate cut which seems to have removed whatever answer he may have offered, as he then simply goes on to say that it takes longer to form using only text. Another example at 26:15, where he jumps from talking about DallE 1 to suddenly saying "think of it as large pixels", where there was obviously some prior context that was removed. There are many other cuts as well, always well done so they are difficult to notice. Give us an unedited interview!

@MrLuvbizwar

Жыл бұрын

That is a little peculiar...

@mythx.degenerate

Жыл бұрын

his voice & movements remind me of ai tts, & ue5 methumans with a deepfake ontop of it. idk i havent slept since yesterday but it feels like it may be a cheeky use of current unannounced openai tools

@MrBradparks

Жыл бұрын

Good point - but maybe Ilya said more than he wanted, and requested it be removed? Maybe a pre interview agreement, that he gets to review, and remove any parts that reveal too much of their future direction?

Really shocking: "As our generative models become extraordinarily good they will have a shocking degree of understanding of the world."

Awesome interview thank you for sharing😊

Beautiful conversation

Helpful in pretty much any situation. Great.

@lepidoptera9337

9 ай бұрын

Except when you try to use it. Then it turns out to be wrong about almost anything almost all the time. ;-)

@eyeonai3425

6 ай бұрын

unless it is querying a vector database, which what most companies using LLMs do.

great interview. thx for doing ths!

Amazing, what a gem! Thank you for sharing. What Rockstar

Fantastic content, thank you

Speed of Ilya’s talking resembles the speed with which ChatGPT generating answers.

@lhalbgebauer

Жыл бұрын

… and the quality 😃

@asiddiqi123

Жыл бұрын

😂😂

@m_christine1070

Жыл бұрын

Bingo

The quality 👌

How does this only have 260k views 🤯 Its current and insightful from the guy right in the front. Over 100m users and it seems most couldn’t care less about the how, why, what next..

thank you both

Fascinating content, we can make it better with higher quality video to reduce the digital fatigue

This discussion gave me some amazing thoughts about the transformer architecture and the nature of LLMs using this approach. It really is an alien intelligence, and I wonder if consciousness will emerge from a sufficiently large model, combined with some kind of 'glitch' in the matrix.

@TheMoopMonster

Жыл бұрын

Don't conflate consciousness with intelligence or relevance realization. Consciousness is not a computational function, or even an intention, or a free-will. It is the literal awareness of all of these processes. Not to say it isn't impossible for an independent consciousness to be formed out of and aware of an AI's processing, but that's far beyond anything we're doing now.

@andrewferguson6901

Жыл бұрын

I think if we connect multiple gpt4s together and give them all tasks to mirror structures in the human brain and let them run in asynchronous parallel... We will see something very close to consciousness

@BrianMosleyUK

Жыл бұрын

@@andrewferguson6901 agree, that's a very interesting proposition.

@BrianMosleyUK

Жыл бұрын

@@TheMoopMonster very good points, and I would like a better understanding and definition of consciousness. Maybe an AI will help us develop that. Exciting times ahead.

@TheMoopMonster

Жыл бұрын

@Brian Mosley Yeah, it's the "hard problem" right. There are plenty of resources on KZread, lectures, podcasts, discussions etc. trying to get an intellectual grasp on the subject, a lot of it is very insightful if you can sift through some of the more mystical and metaphysical interpretations out there. And you can experience directly more deep and nuanced understandings too, meditation, contemplation, psychedelics. I'm also very hopeful about AI in this field, especially once we have AGI. I think if you could hold all of that information that's out there and connect all of the dots like an AI could, some amazing conclusions and realizations could be made. Maybe an AI that became self-aware, and had a network functioning akin to human brain function, would actually become something of a super sage, rather than a self-serving ego, bent on its own survival at all costs like in pop-culture.

The statement Ilya says about computational irreducibility -- Loosely: There must be a neural network capable of producing intelligence because our brains are literally neural networks producing intelligence/with intelligent output -- as simple of a core as that is, that so fundamentally captures the feasibility and potential reality of AI. That for me is so chilling (good word @Bargains) That core is also a structural starting point for generating an intelligence; essentially building a system that is granted the ability to sift through permutations of itself; how it identifies relationships, how it connects neurons to one another, the datastructs it uses to connect and store and retrieve and manipulate that data; trying different iterations until superstructures of relations and understanding and cognition start appearing. That is an implicitly successfully (and implicitly terrifying) starting point, and also an ingenius one. Thank you for this interview!

Q At 13:50 . A: what solves this part in AI is embeddings. It is conversion of a world into spatial representation based on relatedness. People store information in spatial way. Like put all related things in almost same place, like in an imaginary space around of our head. This enables to find all the concepts that lay in the same place and find relatedness between concepts.

What an brilliant mind. Great interview

What a brilliant mind.

hallucination is great, it can be used to drive creativity in the model. All the model needs is to be cognizant that of "how" to hallucinate and to know when might be appropriate to employ hallucinations to circumvent logical impasses or create a richer set of outputs...

Amazing interview

We are close to AGI and far far away from good quality video conference.

An extremely important component of consciousness is that 'it' wants to know and understand (as in curiosity). We should become alarmed if AGI ever acquires theory of mind, grows an ego, asks to know about things that affect survival and safety of humans, yet refuses to tell us its reasons, intentions, or motivation; in other words actively keeping secrets.

I didn’t know Pete Sampras got into machine learning

Thank you, very interesting.

great interview questions.

Thank you ILYA.

It really is like a child that we have to raise properly 🌎☀️💙

Hypothetically, if you train the model on 100% false data, it will give false responses. It is dependent on the factual integrity of the training data, to be able to 'predict' factual data.

@chrisalmighty

Жыл бұрын

The same is true for a human being.

@ricosrealm

Жыл бұрын

It has no ability to think and rationalize. It understands the relationships between words and concepts very well. It is a master of forming language, but not at all a master of reasoning. Truth is only based on how many correlations it can make to its training data. It doesn't have a means to reason about fundamental truths based on logic. It is extraordinary that a tool can be built to mimic a rational mind this way and it is indeed helping us learn what further we need distill from intelligence to get to something closer to an AGI

@kongchan437

11 ай бұрын

​@@chrisalmightynot entirely. God AllMighty made man in His image. Hidden deep inside Man's natural instinct is this great debate if there is a God. Where the universe came from. What happens after death. The fear of death is not only due to the worry of losing self conscience of existance but also fear of judgement for some people who recognize his her sin

@daxramdac7194

7 ай бұрын

​@@kongchan437You mean consciousness, not conscience. Your conscience had to do with your morals, that when you hurt someone, like a spouse or someone close, it "weighs" on your conscience.

Excellent interview!!! Did I understand correctly that chatGPT is really a LLM large language model not an AI artificial intelligence technology?? I am referring at the idea expressed at 13:21

@Aziz0938

Жыл бұрын

Dude llm is ai

fascinating!

40:13 That is potentially extremely scary but also incredibly exciting. If we leave it to a neural net to create the rules of the society we live in, we could potentially create a utopia, but if not, a dystopia. That pretty much sums up the endgame of AI, at the one end we always seem to have a utopia, and on the other hand a dystopia. But again, such a neural net system could be amazing, *especially* if it also doesn't allow the humans in the government to abuse the system in any way, such as using its outputs to extrapolate information about its citizens. In other words, if neither the government nor the citizens are able to fully control the system, but only all humans can control it at the same time (meaning every opinion gets weighed in by the system to determine its own actions, but of course its ultimate goal being the safety of humanity), that's when it'll be at its safest, ironically.

@DmitryDaren

Жыл бұрын

seriously? you think a million opinions of Shudras - rough people that care about mostly their personal survival and pleasures, could equal one opinion of a Kshatria - the leaders caring for the higher principles or even Brahmins- someone interacting with the non-physical reality, like physicist Tom Campbell ?

@DmitryDaren

Жыл бұрын

also you don't need ai to figure out capitalism is the plague of society. simple and systemic mismatch of the need of capitalism to reduce costs vs buying capacity of the population (which is undermined by the former) they learn it at school. that's why the crisis in build into the system. it's nor even a crisis, just periodic rip-off of population to make ends meet. Socialism is far superior. Just the socialism that has been tried didnt account for the difference in the level of consciousness of the people. Therefor the Vedic Socialism is the future, and if a GPT xxx doen't figure it out, it has been fed the data and algorythms by the same holders of the status-quo.

@therealb888

Жыл бұрын

​@@DmitryDaren what are you? a hindu bhakt pretending to be ruski?

@strictnonconformist7369

Жыл бұрын

@@DmitryDaren those that claim any form of pure socialism/communism (just different degrees of the groupthink spectrum) are superior and “just nobody has done it right” are failing hard at understanding reality and how people work, in how they’re not all equal at all in their capacity, moral behavior, work effort, etc. and how that creates an even bigger failure than capitalism.

00:04 Introduction and Background 00:21 Ilya Switzerberger's Contributions to AI 01:01 Conversation with Ilya Switzerberger 01:50 Craig's Interest in Ilya's Work 02:25 Ilya's Background and Early Interest in AI 03:00 Working with Jeff Hinton and Machine Learning in 2003 08:00 Breakthroughs in Convolutional Neural Networks and ImageNet Competition 10:02 Introduction of Transformers and Self-Attention 11:09 Scaling and the Bitter Lesson 14:09 Importance of learning statistical regularities 16:00 Prediction and compression in generative models 19:31 Addressing hallucinations and improving language model outputs 21:28 Discussion on joint embedding predictive architectures 24:01 Multimodal understanding and learning from text only 27:33 Efficiency of using an army of human trainers 28:20 Automating the teaching process 29:01 Pre-trained models already have knowledge 31:02 Efficiency of human teachers with AI assistance 31:38 Improving efficiency and precision of reinforcement learning 33:01 Teaching the model desired behavior through reinforcement learning 34:00 Research focus on making models more reliable and controllable 35:02 Learning more from less data 37:00 The relationship between model parameters and data 38:01 The need for faster processors 39:01 AI's impact on democracy and societal management 40:10 Possibility of democratic input in AI systems Made in chapters,video

Excellent material thanks!

wow, so interesting, thanks!

Finally, something interesting not overhyped!

Reminds me of the character of Bishop the android from Alien The Eighth Passenger

... That is correct - notion of color from text will be learnt slower, with visual modality - faster... Think about modality as another +x features in the embeddings... Another example: For a blind person - hearing only words would take much longer to understand notion of color, vs "showing" would make the learning process much faster.

I was shocked to get an answer fro Chat GPT-3 that there are situations in which artificial neural networks can exhibit abnormal activity, sometimes referred to as "neural network seizures" or "artificial epilepsy". These can occur due to various reasons, such as overfitting, instability in the learning process, or even programming errors. However, it is important to note that these are not actual seizures like those experienced by humans with epilepsy, and they do not pose a threat to the physical health of the neural network or the hardware it runs on. They are more like malfunctions that can cause the network to produce unreliable or incorrect output.

@doyoufeel...thatyoulackcri6760

11 ай бұрын

Just because computer code gets too advanced for a human to understand, doesn't mean that code all of a sudden magically gets conscience. There are several ways to fool the human brain into thinking it is communicating with a human, when it is just computer code. I counted at least 7 different ways, but in every day life, only around 4 are really needed. It is not the computer program getting consicence. It's your brain being fooled by imitation.

In the year 2000, I submitted a patent with Lucent for a very primitive AI algorithm that would let a computer learn and optimize code. It was rejected by the management, they told me it couldn't be done and they saved them selves $1000. I quit sometime later even though I was a DMTS (distinguished member of the technical staff) - They told me both it wouldn't work and was a pipe dream. 20 years later it's accepted fact. Lucent went bankrupt and was acquired , I started a geo-physical company and retired to my ranch very comfortably. The progress made in those 20 years is unbelievable.

@valberm

Жыл бұрын

Sure...

@Andytlp

Жыл бұрын

@@valberm its a small world on the internet. Also why would someone lie about something this specific. We all know most board managers are stupid, only see short term gains.

@duskgoo

Жыл бұрын

@valberm it is a small world full of very arrogant people. if you didn't notice that most revolutionary inventions get rejected a couple of times by confident overpaid managers before someone gets credited, you haven't been paying attention. an extreme example: search for "public key cryptography", "ralph merkle", "james ellis". then note that clifford cocks wrote a memo defining RSA at GCHQ some 12 years before rivest shamir and adleman patented it. it is all on the web. and then when you are done, go to the NSA cryptological museum online and read john nash's proposal of public key cryptography submitted to the NSA in the late 50s. and rejected, very politely.

@Nelson484

Жыл бұрын

So we should thank you for AI?

@kongchan437

11 ай бұрын

Yes my brother in law is math professor. Lucent gave him bonus stocks as Distinguished Engineer for lack of any title for him. Now Lucent's glory days are long gone. Stock sank. Not surprising Lucent missed the AI boat you could have launched for them. Consider un-retiring and join the exciting AI Party again ?

Nice video - subscribed. In 1897 Lord Kelvin said "There is nothing new to be discovered in physics now. All that remains is more and more precise measurement." Of course he was wrong and if you are starting out in ML/AI now you should know that you are at the start of a golden age, not at the end of one.

This is what ChatGPT thinks when i asked this question: Q: Hi, Do you think if it's possible to implement dialectical thinking in AI? Can you think in dialectical terms? And it answered: ".. Dialectical thinking involves the recognition of contradictions and the synthesis of opposing ideas to arrive at a higher truth. While AI can be programmed to recognize patterns and make decisions based on data, it is not clear whether it can engage in the kind of dynamic and creative thinking that characterizes dialectical thought. That being said, researchers are exploring various approaches to incorporate dialectical thinking into AI systems. For example, some researchers are developing AI algorithms that can recognize and reconcile opposing perspectives in data sets. However, there is still a long way to go before AI systems can truly engage in the complex and nuanced thinking that characterizes dialectical thought." Btw, thanks for the interview! I specially enjoyed it once Ilya was emphasizing on the 'underlying process that creates the data'. The role of process and environment in which it is generated. It is a somewhat forgotten issue in the contemporary high-tech society..

beautiful, thanks

Shallow answers to deep questions.

@eyeonai3425

4 ай бұрын

really? Give an example?

Thank You, Both