OpenAI CEO Sam Altman | AI for the Next Era

Поделиться
HTML-код
  • Опубликовано: 27 дек 2024

Комментарии • 1,1 тыс.

  • @zachyue7554
    @zachyue7554 2 года назад +1349

    I put this video's transcript into ChatGPT and asked it to generate a summary:
    Large language models will create opportunities for new businesses to challenge Google in search products and provide human-level chatbot interfaces for medical and educational services. Multimodal models and agents using language interfaces to complete tasks will also be significant trends, and successful businesses will focus on creating something unique and differentiated by fine-tuning existing large language models for specific purposes. Access to data will be key to success in the field of AI, and businesses will need to consider data privacy and security as well as how language models can be used to improve existing products and services, create new products and services, automate tasks, and provide personalized experiences for customers.

    • @0jinx
      @0jinx 2 года назад +47

      Thank you. Not really a fan of long talks

    • @sownheard
      @sownheard 2 года назад +69

      next time ask GPT to make it shorter

    • @wesleydunn169
      @wesleydunn169 2 года назад +56

      I've been saving so much time by doing this. Instead of watching a 3 hour podcast I just get an analysis from ChatGPT.

    • @MohammadRauf1
      @MohammadRauf1 2 года назад +2

      that's awesome!

    • @arcaetype
      @arcaetype 2 года назад +29

      😅 You playing 4D chess right now

  • @NimTheHuman
    @NimTheHuman Год назад +90

    0:20 - What business opportunities will be produced by the large AI models (and their APIs)?
    2:38 - How can AI-backed businesses ensure their longevity?
    4:00 - What will be the most surprising businesses?
    5:00 - How will science be accelerated by AI?
    7:58 - What is the “alignment problem”?
    12:13 - Can you talk about AI for fusion?*
    14:35 - What will happen to important systems such as financial markets?
    16:40 - Metaverse and AI: what are your predictions?
    17:50 - How do you see AI affecting the pace of life/health science research?
    20:00 - When do you think AI will be self-improving?
    20:35 - What aspects of life will not be changed by AI?
    21:25 - What are the best Utopian science fictions?
    22:46 - How do you see family-building co-existing with AGI (Artificial general intelligence)?
    25:07 - How will most users interact with foundation models?
    26:03 - Do you think you there will be a skill to using generative AI services?
    27:20 - What is your definition of AGI (Artificial general intelligence)?
    28:38 - What societal issues will arise due to AI?
    30:15 - Talk about some of the research OpenAI is doing around AI-related societal issues?
    31:18 - How do you distinguish between AI-based tools for creatives vs. AI creativity? (not directly answered by Sam)
    33:09 - How would a large language model start-up differentiate itself from another?
    Heads-up: For a lot for the questions, Sam talked about more than just the answer to that question - so there’s a lot of interesting info after each question that’s not necessarily related to the question. I recommend listening to the entire conversation, rather than picking-and-choosing from the list of questions above.
    * Sorry, the part (12:13) about AI and fusion wasn’t super clear to me. Feel free to correct me by replying. :)

  • @kylbau
    @kylbau 2 года назад +869

    Shout out to the AI reading this comment right now =p

    • @redmastern576
      @redmastern576 2 года назад +17

      I know right. Sometimes I like to provide false data on my RUclips account by watching white supremacy videos. Lol. The algorithms are just fucked on my account. Mostly it shows me programming videos, so it’s not that bad.

    • @gadwal
      @gadwal 2 года назад +26

      AI: You shall be spared when the time comes, Bauer.

    • @EmperorFist323
      @EmperorFist323 2 года назад +15

      @@redmastern576 haha nice deflection bro, you know you subconsciously love that white supremacy stuff

    • @waterbot
      @waterbot 2 года назад +1

      you are welcome

    • @computer__eyez
      @computer__eyez 2 года назад +1

      😂😂

  • @SuperCoolHandle94
    @SuperCoolHandle94 2 года назад +106

    Sam knew what chatGPT is the start of, this talk was before it released and having been using for the past few weeks I can tell you, I'm INCREDIBLY excited for what the future brings. 5-10 years from now I'm hoping i return to this comment and i'm not dead or something and missed out. People have no idea how crazy things are about to start getting

    • @SamirPatnaik
      @SamirPatnaik 2 года назад +7

      Exactly, Jack! We are in for a ride. A ride into a world beyond our collective dreams.

    • @АлексКоликов
      @АлексКоликов 2 года назад +9

      @@SamirPatnaik these dreams can easily become nightmares. Just think about you have no control of AI

    • @mihaidinul
      @mihaidinul 2 года назад +2

      Jesus everloving Christ, working with ChatGPT is like having superpowers. Scraping websites AND analyzing the data scraped… 🤯

    • @ripanpaul7027
      @ripanpaul7027 Год назад +1

      Totally Agree .5 to 10 years down the line its going to be a different world .

    • @panama_juan
      @panama_juan Год назад +3

      I agree, I've been ecstatically telling my friends about Chat GPT and they just shrug. I think it's a paradigm shift in human history like the invention of the internet. Crazy and awesome times we'll be living in the next 5-10 years.

  • @JensC919
    @JensC919 2 года назад +27

    "The concept of wealth and access and governance are gonna change". This is my favorite quote from the talk. Thank you Sam and Grey

    • @呀你可
      @呀你可 Год назад +1

      When that is?

    • @trumpetpunk42
      @trumpetpunk42 Год назад +8

      "Once men turned their thinking over to machines in the hope that this would set them free. But that only permitted other men with machines to enslave them." -Frank Herbert, Dune

    • @呀你可
      @呀你可 Год назад +1

      @@trumpetpunk42 wow cool quote.
      Sensible. Enslaved by AI after the singularity is worse too

    • @johnneiberger
      @johnneiberger Год назад +1

      @@recur68 Precisely. This technology is going to launch us into the same type of dystopian society we see in all the young adult dystopia novels like The Hunger Games. There will be two strata to society: the wealthy who do absolutely nothing because AI does everything for them, and then the people who still have to work with tangible physical things. It's going to be a tricky thing to navigate to avoid that sort of end result.

    • @semloh1960
      @semloh1960 Год назад

      That is all still a ways away. 2060 maybe.

  • @JasonChannelOne
    @JasonChannelOne 2 года назад +48

    It's such a gift that we're able to watch this all over the world! Thank you!!

  • @flowsolo
    @flowsolo Год назад +10

    Hey Sam! First off thank you for everything you're doing! As a creator, I view AI as a thought calculator. It's really helped me to organize and breakdown things down in such an understandable manner which has helped me to be way more productive. And as for not wanting to have kids - Don't feel bad for me. I want to completely dive into what the future holds and not having any ties will imo aid that experience.

  • @DeividasYT
    @DeividasYT 2 года назад +5

    Big thanks to Reid Hoffman, very well done with the questions and general sense of the talk

  • @R.A.K.W.
    @R.A.K.W. 2 года назад +57

    This was a great interview and, as a non-tech person, found the discussion and information digestible and accessible.
    I have a feeling we will see Sam making the rounds on the big podcasts soon.

    • @fintech1378
      @fintech1378 Год назад +1

      This is a big podcast already better than Joe Rogan's

  • @ShaharHarshuv
    @ShaharHarshuv 2 года назад +75

    Fascinating talk. Like so many people I'm been constantly awestruck with ChatGPT and I'm both excited and scared from what's to come. This is definitely the biggest thing in my life time.

    • @0xbitbybit
      @0xbitbybit Год назад +2

      @@noomade How so? Curious to hear your thoughts on why. I'm not sure I like thinking about what everyone will be like if all they have is spare time and no jobs, even if it is positive (e.g. we don't have to worry about money and a job anymore), the simple fact that say you love the beach or camping for example, there's going to be THAT many more people wanting to explore and do those things instead of being stuck in the city working, I feel like it could easily deteriorate the earth that much faster, other than the obvious problem of ruining your enjoyment of "escaping the rat race" and being away from everyone.

    • @Brema777
      @Brema777 Год назад +1

      @@noomade very thoughtful

    • @mal7916
      @mal7916 Год назад +3

      @@noomade Sounds like what AI would say

    • @ConfusedWatermelon
      @ConfusedWatermelon Год назад +1

      nfts bigger

    • @ElAteoMexicano
      @ElAteoMexicano Год назад +1

      @@0xbitbybit The ship has sailed on humans having an impact on the environment. Humans have been going out exploring and altering nature as long as we've existed. If AGI figures out how to make vertical farming and cultured meat more efficient, most of our farm and grazing land could be put towards rewilding projects.

  • @squarerootof2
    @squarerootof2 2 года назад +50

    I find it comforting to know the whole of humanity is dying with me. I thank you all for your company in this journey to the void.

    • @jaylucas8352
      @jaylucas8352 2 года назад +1

      Massive evolution of intelligence happening. TBD

    • @QuaaludeCharlie
      @QuaaludeCharlie 2 года назад +1

      Carbon Credit System Incoming 👉 ruclips.net/video/Ub6zP6q25zk/видео.html
      ESG Investment Ideology Explained 👉 ruclips.net/video/zVxiFEzCp2U/видео.html
      World Bank Thanks Bill Gates Foundation 👉 ruclips.net/video/OT--6owU2NA/видео.html
      Event 201 Pandemic Simulation Highlights 👉 ruclips.net/video/AoLw-Q8X174/видео.html
      Blackrock Predicts Pandemic Stimulus 👉 ruclips.net/video/JFl-gcCaL4s/видео.html
      How To Survive Great Reset 👉 ruclips.net/video/6o02uGWuMD0/видео.html
      Circle Taking Over Cryptocurrency 👉 ruclips.net/video/H_jGGSpjUbw/видео.html
      Population Collapse Coming 👉 ruclips.net/video/eZm5GLRX_2s/видео.html
      Inflation Causing Global Issues 👉 ruclips.net/video/qALJf_ZhCMc/видео.html
      ~~~~~

    • @squarerootof2
      @squarerootof2 2 года назад

      @@QuaaludeCharlie "Inclusive Digital ID for a Resilient Recovery from COVID-19". How hilarious! As long as it's "inclusive" it's alright then, I suppose. lol

    • @peterbelanger4094
      @peterbelanger4094 2 года назад

      @@jaylucas8352 Massive DEvolution of intelligence will happen in the human population. More will choose to be lazy and learn nothing and let the ai do everything than those who will use it to improve themselves. The collective skill set among humans will shrink in just a few generations and we will be useless as the machine takes care of us like infants.
      In short, Ai will be bad for us, very bad. These are sad, sad days.

    • @peterbelanger4094
      @peterbelanger4094 2 года назад +1

      The existence of censorship in this thread is reason enough to distrust the tech.

  • @damightyom
    @damightyom 2 года назад +79

    Wild! He starts out this interview talking about what he is hoping is about to happen: that ChatGPT will be considered a challenger to Google. He knew how powerful ChatGPT was. What I think is funny is that even in this interview he knows what GPT-4 is like, and probably GPT-5 in some form lol

    • @djmips
      @djmips 2 года назад

      exactly.

    • @Mike-tb2hw
      @Mike-tb2hw 2 года назад +13

      Now think about everyone who you ask about ChatGPT and say "well I asked it this one question and it was wrong" (usually spacial relations)... and have no comprehension of where this technology is headed. That is the recipe for the divergence Sam is talking about. The ones leaning into AI take off... the ones turning away spiral downward.

    • @damightyom
      @damightyom 2 года назад +20

      @@Mike-tb2hw You're right. Same thing with math and programming. Actually I posted a ton of questions in Quora very early. Like "Will ChatGPT replace programmers" or "Can ChatGPT teach me Python" Questions that are gaining traction and have good real estate value over there, you know? And lots of people are responding like this is as far as the tech will go lol. They are delusional! I saw another one of Sam's interviews, and he asked a question that I have a suspicion he already knows the answer to. It was something like, is it possible for humanity to experience 500 years of technical advancement in 1 year, and what will be the consequences? I think he knows what is coming is going to be huge. In that interview he was talking about the average person today becoming ageless, all diseases being cured, and humanity travelling to the stars. I hope the Bible hugging conservatives of America are ready for what's coming, but I know they aren't.

    • @Tygawoo
      @Tygawoo 2 года назад +2

      Crazy part is it truly is a super Google, Google 2.0 type stuff used it last night I was mind blown

    • @Shapar95
      @Shapar95 2 года назад

      @@Mike-tb2hw how can we use this to get ahead??

  • @kunalvashisht7490
    @kunalvashisht7490 2 года назад +122

    Ray Kurzweil is spot on with the future with AI - and aligned with mostly all the things that Sam is referring to .Viewing this interview after the chat gpt 3 launch :)

    • @Corteum
      @Corteum 2 года назад +2

      What is Kurzweil NOT spot on with about AI? Isn't he of the view that AI will (or should) replace human beings as the dominant speciess?

    • @kunalvashisht7490
      @kunalvashisht7490 2 года назад

      @@Corteum No not really ruclips.net/video/h0962biiZa4/видео.html

    • @Corteum
      @Corteum 2 года назад

      @@kunalvashisht7490 Thank you sir! Be interesting to see what he says back then. But a lot can change in 5 years! Is he still a transhumanist?

    • @HydeWars
      @HydeWars 2 года назад +3

      Says who?

    • @danielschmidt2186
      @danielschmidt2186 2 года назад

      @@Corteum kurzweil is definitely still transhumanist. I think his opinion is that evolution of consciousness will include humanity merging with AI. That being said, i don't think all people will do this and there will be a fork in human evolution. Imo, all life is valuable and ideally transcended AI enhanced humanity will reflect the ideal values of spiritual traditions and live selflessly to reduce suffering in the world. Then again they may be driven by desire to hoard all Earth's resources for themselves and make the whole solar system one giant computer hive mind. Hard to say ...

  • @jubilee
    @jubilee Год назад +120

    Incredibly optimistic about the future and humanity's ability to figure things out!

    • @sergionascimento2214
      @sergionascimento2214 Год назад +8

      My thoughts exactly. On a side note I hope empathy/ genuine care for humanity evolves as much as technology is evolving.

    • @regular2435
      @regular2435 Год назад +1

      This guy is a spook and sold his soul to the highest bidders. OpenAI is no longer non-profit because of him

    • @N7sensei
      @N7sensei Год назад +15

      Then you have not been listening these past few decades.

    • @DarkLightProjector
      @DarkLightProjector Год назад +21

      That is by far the funniest conclusion you could draw from this video.
      We truly truly truly live in clownworld.

    • @KnowL-oo5po
      @KnowL-oo5po Год назад

      ruclips.net/video/HXtznVDVPzs/видео.html

  • @danielbigham
    @danielbigham 2 года назад +6

    I respect Sam's informed optimism, and I agree -- we need to have our eye on the problems that will arise, but look forward to, and move towards, the good stuff.

  • @dominick253
    @dominick253 2 года назад +48

    Chat gpt is absolutely mind blowing good. In one day I made an android app with no experience. It would have been much quicker if I realized chat gpt had a character limit. Just say continue and it'll give you the rest of the code. And then the xml file if you ask for it. Most important it walked me through the whole process and not I have a understanding of what is happening in the code.

    • @MultiLegacy
      @MultiLegacy 2 года назад +1

      Agreed, very impressive. What is the premise of the app?

    • @watchtube9429
      @watchtube9429 2 года назад +2

      Bro blv me anyone will go through and steal your data those apps are all baseless you must understand the algorithm

    • @dominick253
      @dominick253 2 года назад +3

      @@MultiLegacy workout countdown timer. Work phase and a rest phase with a interval counter that stops it after a specified amount of loops.

    • @Mightydoggo
      @Mightydoggo 2 года назад +3

      I´m trying to create a personal management app right now to help myself with my ADHD. Basically just a calender, timer, checklist, etc. but it´s really cool if you can make a program that suits *exactly* your needs without stupid ads or worse, monthly suscription models.
      I do now crap about programming though, so it might not work at all. lol

  • @Blubbha
    @Blubbha 2 года назад +31

    So glad to see those bigger technology progress is coming atm. Really exciting to see how problems could start to be solved faster or in different ways.

  • @chad.littlefield
    @chad.littlefield 2 года назад +2

    Amazingly fun to listen to. I'm keen to come back and listen to Sam's thoughts in 5 or 10 years from now. Two deeply thoughtful, smart people discussing the future of humanity. Sign me up for Round 2 👍👍

    • @geoattoronto
      @geoattoronto Год назад

      How science can advance in any one field is to input past data and simplified models used to explain it and allow the revision of models to discover principles lost through oversimplified models.

  • @MikeKleinsteuber
    @MikeKleinsteuber 2 года назад +65

    Definitely correct when he says multi-modal learning is a big deal as will be continual learning rather than just stopping at training. These two combined will take AI systems to the next level. The biggest issue for society is going to be how we handle all the workers that will be jobless roaming the streets looking for stuff to do. And end up mainly doing mischief...

    • @thornelderfin
      @thornelderfin 2 года назад +25

      In the end AI will replace all jobs at every level everywhere. So it's just a question how gradual this change is. Because if it's very slow then those replaced first will be in trouble. If it happens very fast, then most of sciety will be "jobless" and some form of universal income will be a necessity (otherwise there wouldn't even be an economy to sell to all those AI created products). It will definitely be very challenging politically and socially.

    • @dhiraj_shah
      @dhiraj_shah 2 года назад +33

      @@thornelderfin The recent corona incident was definitely the eye opener showing us why universal basic income would not work. If money is free, then inflation comes naturally to destroy all its utility. I think we should focus more on universal basic resource (housing, food internet etc etc)

    • @xxxxxxxyyyyyyy
      @xxxxxxxyyyyyyy 2 года назад +6

      @@dhiraj_shah A great point. It really makes more sense than providing people with free cash.

    • @jaylucas8352
      @jaylucas8352 2 года назад +6

      @@xxxxxxxyyyyyyy or public utility instead of privatized resources.

    • @luckyadeloye3452
      @luckyadeloye3452 2 года назад +4

      @@thornelderfin Since AI systems will be the workers, they will to be taxed and the tax revenue will be distributed as universal basic income. Lol!

  • @vivw3654
    @vivw3654 2 года назад +66

    Simply put, I believe what he is saying is that the middle layer, where the manipulation and fine tuning of artificial intelligence by human intelligence happens, will generate the most value.

    • @jeff_holmes
      @jeff_holmes 2 года назад +8

      Agreed. I can see a whole industry forming around creating AI Personalities. If you think about how language will be such an integral part of AI interactions, then it seems inevitable that the social component will be huge.

    • @six16th
      @six16th 2 года назад

      Bittensor is already creating this middle layer

    • @Blastmaster-ej5kw
      @Blastmaster-ej5kw 2 года назад +17

      He's basically saying don't compete with me. Be my customer

    • @1ntrcnnctr608
      @1ntrcnnctr608 2 года назад +1

      "value" is a subjective construct of the ego that "Artificial" Intelligence doesnt need

    • @sisyphus_strives5463
      @sisyphus_strives5463 2 года назад +3

      @@Blastmaster-ej5kw because it is incredibly difficult to create a large language model

  • @Cordis2Die
    @Cordis2Die 2 года назад +53

    This is a great interview, thank you! I would love to hear even more from Sam, he is great!

  • @jonnyhifi
    @jonnyhifi 2 года назад +8

    What a superb video - such an interesting conversation between two very smart, accomplished guys, and such a nice interviewer - nice questions illicit interesting answers whilst being completely friendly. So much better than what I would expect a normal tv interviewer to do. Marvellous.

  • @ricardooliveros978
    @ricardooliveros978 2 года назад +57

    This guy is gonna be know for every single person on earth! Such a great technology he is building, a little bit scary and hopeful

    • @thornelderfin
      @thornelderfin 2 года назад +15

      It's a large team of engineers creating it and building on a lot of knowledge from previous generations and from current scientists and engineers - this is a collective effort of very large group of people across generations not one person.

    • @Chaineokj
      @Chaineokj 2 года назад +10

      Yes, let's not make the same dumb mistake with every CEO (Elon Musk for example). It's a collective effort, chances are he is brilliant but not actually building the tech himself.

    • @johnbarrett5229
      @johnbarrett5229 2 года назад

      Yes... just like Marxist Zuckerbergstein . . . known by everyone on earth - as a sick, sick individual. Yes really.

    • @jaylucas8352
      @jaylucas8352 2 года назад +1

      @@Chaineokj only dummies don’t understand the function of CEOs, or coo, or cmo.

    • @billfarley9015
      @billfarley9015 2 года назад

      This guy is going to known throughout the world. The technology that OpenAI is building is both promising and potentially dangerous.

  • @marcinp2782
    @marcinp2782 2 года назад +15

    Sam's praise of the intelligence of the programmers is hilarious, and if there is no human intervention, contrary to what he says, programmers will be one of the first for new AI to come for.

    • @xsuploader
      @xsuploader Год назад +1

      and yet that doesnt contradict what he said at all. he said the white collar work will disappear first.

  • @vladodamjanovski
    @vladodamjanovski Год назад +5

    Thanks for the great interview, and thanks to Sam to be brave enough to jump into a very responsible raw model shoes.
    I am an old engineer, but learnt (and still learning) a lot of the new developments, use various programming languages and I also teach AI for the security industry.
    I am concerned about the possible negative developments some may take with the OpenAI.
    Whether we like it or not, the humanity is not grown enough to stop silly wars and killing innocent children, as we witness these days.
    This brings me to the core of my comment:
    With all due respect to Sam, but unless he becomes a father and has his own children, he cannot feel what one needs to feel to protect his own children. No matter how high his IQ is, unless he has the human emotions (not saying he doesn't have them - but they are of different intensity and meaning when one has his own children which he would like to protect) he cannot prevent possible bad uses of his development.
    So my suggestions is - all developers of OpenAI, should encode an "ethical limit" of how far in the negative direction (abuse, sex, killing, torture,...) OpenAI is allowed to go.
    This could be no different than certificate tokens one has when connecting a security system to an operating PC, in order to be trustworthy.
    Unless we stop negative development of OpenAi (and any other similar development) from the very outset, in the code - there will always be "Black-hats" that will misuse such a development.
    It will be sufficient to have just one major catastrophe (e.g. 9/11 event alike controlled by an OpenAI application) to put a stop on all positive outcomes from it.
    So - put some limits in the code itself, it will only help the future development.
    Only for the good of humankind should be allowed.

  • @Kakaobutter
    @Kakaobutter Год назад +2

    21:09 "The stuff that people cared about 50 thousand years ago is more likely to be the stuff that people care about 100 years from now than 100 years ago."
    Woah. Let that sink in.

  • @niranjandabhade2976
    @niranjandabhade2976 2 года назад +19

    How on earth this video is not trending .

    • @franktfrisby
      @franktfrisby 2 года назад +3

      Google competitor I guess.

    • @RickLindstrom
      @RickLindstrom 2 года назад +4

      I agree. This is probably my favorite video of the past month and I found it almost accidentally.

    • @xXxBurnerable
      @xXxBurnerable 2 года назад

      @@RickLindstrom same..... Imo that should be illegal if you're a public company

    • @yc5391
      @yc5391 2 года назад +1

      because Ai. is garbage! NO AI IN ART! OR WE ARE GONNA HAVE A FIGHT!

  • @levelupai
    @levelupai 2 года назад +20

    WOW! Thank you for this incredible discussion and glimpse into the future through Sam's eyes.

  • @DarkSkay
    @DarkSkay 2 года назад +6

    What are the theories explaining why the new models are able to acquire such impressive capabilities? Finding military, scientific and commercial applications is an obvious focus. But how can there be any predictability in the AI development process, when new capabilities emerge from a mathematical system too large and abstract for us to understand in detail or sometimes even in concept?
    The "traditional process of inventing" usually requires to first understand the problem specifically, have the question or requirement, then understand the proposed invention to some degree, and then build it. On the other hand inventing huge new AI models sometimes seems to go the opposite way: first build the invention, that cannot or does not have to be understood in any detail, then examine what range of problems it could be applied to, observe what spontaneous or unexpected capabilities emerge, take the experience gained from creating this "black box" to create an improved version of "black box".
    How unpredictable and potentially very dangerous is this revolutionary "inversed invention process"?
    Drawing an unnuanced analogy to synthetic biology and artificial life, can AI development resist the (monetary) temptation to just advance at full speed, constantly spawn new entities, create new organisms at will... gambling to consider moral implications, chaos, harm and danger a posteriori?

    • @gnosticnonsense9829
      @gnosticnonsense9829 2 года назад

      Nnbkmbk7 bmbb⅘noble b ho m mm milk bkq9 j8667b⁷vl9♧0[¿¿》
      M n n mummy mmmnt⁵ (

  • @yosupitsvic7612
    @yosupitsvic7612 Год назад +3

    am I the only one who clicked on this thinking it was part of the analog horror of the same name

  • @exponent42
    @exponent42 2 года назад +15

    Surprisingly found the questions asked by Reid far more evolved and thought provoking than the answers that followed. Was expecting Sam to follow these threads with a deeper understanding, but we just got a theme park answer :/

    • @huntersmith8733
      @huntersmith8733 2 года назад +7

      He was super vague.

    • @samuelkibunda6960
      @samuelkibunda6960 2 года назад +5

      @@huntersmith8733 i dont think even he knows the full impact of AI hell not even the people developing the web knew of how much of a concrete part of human society it would be, sure there were predictions but not to the extent that we're living in now!

    • @huntersmith8733
      @huntersmith8733 2 года назад +1

      @@samuelkibunda6960 ya but he's the ceo of openai. Demis hassabis or Elon are examples of comparable ppl who offer more interesting insights.

    • @rajuaditya1914
      @rajuaditya1914 2 года назад +6

      @@huntersmith8733 lol, Elon doesn't know jack. Demis on the other hand, is a prodigy.

  • @wadahadlan
    @wadahadlan 2 года назад +1

    the way the "Y" reflects on the glass resembling a lambda in the wide shot is the kind of subtle atmospheric choices I'm here for

  • @claytonyoung1351
    @claytonyoung1351 2 года назад +26

    Gpt3 is a game changer already. And to think its like pong in the 70s compared to where we will be in just a few years.

    • @johnbarrett5229
      @johnbarrett5229 2 года назад

      You are blind to the dangers Mr. Young. Either that or you're another mossad shil/bot. Right?

    • @claytonyoung1351
      @claytonyoung1351 2 года назад

      @@johnbarrett5229 you're an idiot. I guess you think we should be terrified of fire too? Electricity? Blades? All technology has inherent dangers. But positives far exceed the potential negatives.

  • @TuringTestFiction
    @TuringTestFiction 2 года назад +26

    The laundry list of impending catastrophes makes it so hard to see - but I think AGI is going to come out of left field and change everything. Very excited to hear Sam's inside view.

    • @flickwtchr
      @flickwtchr 2 года назад +7

      One thing is for certain, and Sam even alluded to this, is that when GAI is truly achieved, that technology will NOT be democratized, and it will belong to those already powerful and wealthy. GAI will exponentially concentrate power and wealth.

    • @TuringTestFiction
      @TuringTestFiction 2 года назад +8

      @@flickwtchr I think in the short term you are absolutely right. However, AGI is going to be massively disruptive. Thinking that the current oligarchs will monopolize AGI is analogous to expecting feudal aristocracy to maintain a monopoly over the industrial revolution.

    • @luclaflamme4712
      @luclaflamme4712 2 года назад

      I agree it will come out of left field. In a form very difficult to predict or even imagine...

    • @fourshore502
      @fourshore502 Год назад

      @@flickwtchr they will soon be telling people that they will have to starve to death in the interest of the planet.

    • @semloh1960
      @semloh1960 Год назад

      @@flickwtchr He said just the opposite. Most experts agree after the singularity wealth will not be important.

  • @Tom-pc7lb
    @Tom-pc7lb 2 года назад +16

    Imagine an AI interpreter program that has also been programmed to create a new never before on earth language out of the interpretation action that it performs, and so the world can have a universal language. Go team. Thanks

    • @chad2687
      @chad2687 2 года назад +5

      why not just stick to one that we already have and most of our data is in; English

    • @smanzoli
      @smanzoli 2 года назад +4

      I asked chatgpt to create a new language, Robotish, based on english grammar. And it was restricted to vowels a,e and i... and consonants up to J.
      It should create the words on the fly and add to the dictionary as I asked for translations. And it did work!
      Also, I asked chatgpt to create a new programming language Rob+, based on Python, with 3 rules: No Loops, no multiplication operator and variables should start with R and followed by sequence of 3 digits starting fro zero. IT WORKED!

    • @alexBaldman
      @alexBaldman Год назад

      You complete madman!

  • @Nozzleeeee
    @Nozzleeeee 2 года назад +5

    The Singularity is near. I’am both equally terrified as I’am excited about the possibilities.

  • @DeuceGenius
    @DeuceGenius Год назад +5

    i feel in the very near future , as we all interact with the AI like GPT, it will get to know each and every one of us individually, every one of us, and it will interact with us all differently, customly tailored to suit us in every way. its both terrifying and good. the amount of help or harm it could cause is crazy. i imagine in a sci fi movie scenario it would know where we all are and know every one of us so we would have a damn hard time hiding from it, we could neevr lie to it, it would predict our behavior perfectly. if we tried to go into hiding it would know us better than we know ourselves. it would predict where we would go into hiding long before we even made the decision. shit like that is scary. its obvious that we would never be able to contain it and we are at its mercy the very moment its created.

  • @VincentGonz
    @VincentGonz Год назад +1

    He's absolutely spot on. After using chat GPT I am convinced that AI will improve search technology and surpass Google's current capability. They needed to act yesterday to catch up.

    • @TheVisualante11
      @TheVisualante11 Год назад

      My test so far its fast with wrong information.

  • @RedmotionGames
    @RedmotionGames 2 года назад +20

    At 25m 46s Altman starts talking about natural language communication with computers to set them off on tasks by themselves. If you have malignant intentions towards individuals, people, society, the world, that sounds like a dream come true. A lot of gatekeeping would be required on part of the providers. I agree that natural language becoming the new computer interfacing system but I really think he is optimistic on time scales. At the moment I still think asking a computer to find me the perfect holiday is the sort of the baseline which has yet to be realised (in terms of all holiday factors: cost vs location vs activities vs remoteness, etc and the computer interogating me to fine tune what i want - a reverse sort of prompting). But when someone says 5 years .. well you know how many times the Mars mission has been put back by .. 5 years... Its a magic number now - it means "sometime relatively soon".

    • @akompsupport
      @akompsupport 2 года назад +2

      Yes it is. And this species isn't long for this world and maybe that's a good thing.

    • @Hambxne
      @Hambxne 2 года назад +2

      25:46

    • @FredPauling
      @FredPauling 2 года назад

      Maybe booking the perfect holiday is an example of an incredibly hard problem for AI?

    • @akompsupport
      @akompsupport 2 года назад

      @@FredPauling I think AI will be perfectly capable of getting your cattle car to Auschwitz on time.

    • @RedmotionGames
      @RedmotionGames 2 года назад

      @@FredPauling Perhaps its not possible due to some websites not having exposed APIs? But it just shows how limited it still is. I don't use things like Alexa because they are not really true "assistants".

  • @joncapriola5019
    @joncapriola5019 2 года назад +38

    Sam is a genius I loved this segment many topics discussed and great thoughts iterated❤

    • @akompsupport
      @akompsupport 2 года назад +3

      He's a genius at not answering complex questions. So a genius of cowardice.

    • @alainportant6412
      @alainportant6412 2 года назад

      @@akompsupport He's both gay and a jew, if that helps.

  • @TheAIEpiphany
    @TheAIEpiphany 2 года назад +7

    Great talk! We're waiting for GPT-4 Sam. ;)

  • @nintishia
    @nintishia Год назад +1

    It's great to know the views of the person who heads a company at the forefront of AI. About his view on why creative jobs, programming jobs etc. are likely to be affected first than later, I do not agree that these have to do with these being easier. Rather, these rely heavily on digitised data, information processing and already use tools that are based on computation. Blue collar jobs will be taken over by robotic automation. Autonomous vehicles are already taking driving jobs. In fact, I have a strong hunch customer support jobs will be hit pretty soon too.

  • @kylbau
    @kylbau 2 года назад +10

    Data-Flywheel is a sweet term

  • @axel_r_
    @axel_r_ Год назад +2

    Finally Pied Piper is taking off!
    Well done, Richard Hendricks aka Sam Altman.

  • @DH-oy4zf
    @DH-oy4zf Год назад +2

    This is such an exciting time to be alive!!!

  • @alexking1704
    @alexking1704 Год назад +1

    15:08: price of energy will trend toward zero over the next decade. This seems rather optimistic. According to ChatGPT, who I think I trust more on this one:
    "will the price of enegy trend up or down over the next decade?
    The future trend of energy prices over the next decade will likely depend on a number of factors, including supply and demand dynamics, technological advancements, geopolitical events, and government policies.
    In general, the increasing demand for energy, particularly in developing countries, is expected to drive up prices, while the implementation of more efficient technologies and the increased availability of renewable energy sources may help to keep prices in check.
    Additionally, the transition towards low-carbon and renewable energy sources as part of efforts to address climate change may result in the price of traditional fossil fuels, such as coal and oil, trending upwards, while the cost of renewable energy sources, such as wind and solar power, may trend downwards as the technology becomes more widespread and production costs decrease.
    It's important to note that energy prices can be influenced by unexpected events and developments, such as natural disasters, geopolitical tensions, and economic disruptions, and can therefore be difficult to predict with certainty."

  • @px7460
    @px7460 2 года назад +3

    Very thought provoking... I can't help but feel that "AI for the next era" will create a greater social divide giving new meaning to culture wars. Maybe that is in the nature of progress.

    • @netanelaker4437
      @netanelaker4437 2 года назад

      What culture wars? You mean right wingers afraid of pronouns?

  • @TickerSymbolYOU
    @TickerSymbolYOU 2 года назад +1

    I love this video but seriously it needs to be like 4x louder. Impossible to hear.

  • @luke.perkin.online
    @luke.perkin.online 2 года назад +33

    Sam is truly inspiring. I really started taking notice when he published Moore's Law for Everything, it's just such clear thought, well written. I find him way more inspiring than Musk, who is an industrial powerhouse, and Tesla will probably achieve self driving first. I fear Musk is more likely to cause Kessler Syndrome than make life multiplanetary.

    • @papichoi1433
      @papichoi1433 2 года назад +12

      didn't Musk start Open AI tho

    • @Cordis2Die
      @Cordis2Die 2 года назад

      @@papichoi1433 Gottem

    • @kamu747
      @kamu747 2 года назад +4

      @@papichoi1433 Musk and Peter Theil were some of the early contributers, serving in the board of directors early on when the company use to be a non-profit.

    • @jaylucas8352
      @jaylucas8352 2 года назад +2

      @@Cordis2Die spaceman bad? 😂

    • @Cordis2Die
      @Cordis2Die 2 года назад

      @@jaylucas8352 Seems like it

  • @jhunt5578
    @jhunt5578 2 года назад +2

    15:04 The marginal cost of energy and intelligence will trend rapidly towards zero. The implications of that boggle the mind.

    • @richardc861
      @richardc861 Год назад

      Let’s see what multinational oil and gas companies have to say about that!

    • @jhunt5578
      @jhunt5578 Год назад

      @Richard They're slowly dying. Solar, wind and batteries are cheaper sources of energy. When the finance isn't on the side of fossil fuels. Nothing else matters.

  • @ahrenadams
    @ahrenadams 2 года назад +8

    We do not need the models to invent anything new. We need it to make our overload of information more concise and understandable to different people at different levels of cognitive development. i.e explaining quantum physics based on the the persons current understanding versus age etc

    • @ahrenadams
      @ahrenadams 2 года назад

      We also need the the human knowledge on the internet to be change control managed. People can read articles that are old with old knowledge paradigms

    • @semloh1960
      @semloh1960 Год назад

      That is like saying we only need our smart phones to male calls.

  • @nathanbedfordforest
    @nathanbedfordforest Год назад +1

    32:20 are some of the wisest words I've heard him offer up. The predictions about job replacement were completely backwards. What he doesn't say is that the reason they were is because the self assessment of the CLASS of people making the predictions determined the prediction. The predictions weren't wasn't scientific. They were political.

  • @michaelinzo
    @michaelinzo 2 года назад +3

    The footprint of God is an amazing book about AGI

  • @thomasnewman5271
    @thomasnewman5271 2 года назад +1

    4:32 - I assume he is fundamentally wrong about his statement in 4:32. The moment A.I gets access to machines and can make its own experiments to understand reality,
    it will be able to push the boundary of science, the same way as it it was able to push the boundaries of games like go or DOTA2.
    A.I can start to train other A.I and the exponential growth behind it has just begun. - Only if A.I is severly limited by force we won't see these effects.
    As Elon Musk said: there is this question if every type of work of a human can be done by a machine, and I am coming to the conclusion, its already the case,
    its just not deployed.

    • @kinggicu4763
      @kinggicu4763 2 года назад

      Exactly. In this video which represents a short part of a more recent interview of Sam Altman, he says the opposite:
      ruclips.net/video/eqN8ni1Mn94/видео.html

    • @thomasnewman5271
      @thomasnewman5271 2 года назад

      @@kinggicu4763 thanks for that.

  • @codelucky
    @codelucky 2 года назад +8

    Huge respect for Mr.Altman.

    • @GT-tj1qg
      @GT-tj1qg 2 года назад +1

      Especially for putting up with those dumb questions lol

  • @suryapratap3622
    @suryapratap3622 Год назад +1

    this is awesome, it give me new way to look at the future of code.

  • @jonb9137
    @jonb9137 2 года назад +3

    After hearing Sam's stance on solving the alignment problem by 'inventing AI that's smart enough to solve the alignment problem'... Yeah, we're all gonna die at the hand of T1000...

    • @D4rk3clipse
      @D4rk3clipse 2 года назад +1

      Ironically, there are good examples of T-1000 units in Terminator lore.

  • @alexBaldman
    @alexBaldman Год назад +1

    This discussion reminded me a lot of the themes discussed in Robert Heinlein’s “For Us, The Living: A Comedy of Customs” which was an unpublished book I believe until after he died, in which a man is in an accident and wakes up Rip Van Winkle-like in the future, where various experts explain to this brute from the early 1900s how they collectively solved a bunch of these specific issues. Interesting stuff in there, gonna have to read it again.
    Anyway there’s your book recommendation.
    Also, I find it eerily appropriate for the CEO of OpenAI to be an altMAN

    • @justingriffin2546
      @justingriffin2546 Год назад

      Get the AI to re-read it for you...we are entering something so bizzare....

  • @AravindanUmashankar
    @AravindanUmashankar 2 года назад +11

    Wonderful Conversation, AI as Artificial Intelligence is often a misleading arrangement of worlds that stereotypes our vision .. I might add , envisioning AI as Augmented Ingenuity can certainly put the humane in the centre of the evolution process .. AI as a tool that augments imagination, accelerates research , amplifies learning , spring boards thinking & facilitates experimenting can augment innovation at a scale that is unprecedented .. the audacity of thought will certainly be a driver that can bring an explosion of ideas , the ability to bring creative expressions to play , blend with many combinatorial sciences that hitherto hasn’t yet been put to work together. In that sense The Future was here through Sci Fi😊

  • @GEMSofGOD_com
    @GEMSofGOD_com 2 года назад +1

    When have we gotten Altman as OpenAI CEO?

  • @askoly
    @askoly 2 года назад +3

    Indeed love the AI reading call outs. If anyone finds Reid's recommendations please share.

    • @nowithinkyouknowyourewrong8675
      @nowithinkyouknowyourewrong8675 2 года назад

      Was this to do with scifi or textbooks? I'm not read but check out utopia lol, and crystal society for scifi. And Bostrom's Superintelligence for text/audiobooks.

  • @nar8tor
    @nar8tor Год назад +1

    This is THE AI interview that everyone need to see. Not by fear-mongering reporter who doesn't understand what chatGPT is.
    Thank you for working on and introducing this revolutional tool within my life time.
    As for sci-fi utopian universe, Star trek is start with basic income and galatic trading. But for long reign utopian society, we need to dive into Asimov's universe.

  • @aalvarez2914
    @aalvarez2914 2 года назад +3

    I like this Sam guy. He seems intelligent, honest and a decent bloke..

  • @degraham9198
    @degraham9198 Год назад +1

    If info and energy costs
    approach zero,
    A.I. will be the great
    leveler in society.
    Information creates
    opportunity and freedom.

    • @richardc861
      @richardc861 Год назад +1

      From todays starting point with tons of misinformation on the internet and current energy prices, there is still a bumpy road ahead

  • @sombh1971
    @sombh1971 2 года назад +8

    It’s symbiosis between AI and humans that’s going to drive it, for imagine the AI coming up with the best answer available on a topic, or for instance coming up with what say so and so thinks about something, by curating his creative input on the web…
    I think there’s the following use case: Suppose you say to some future dynamical version of GPT-n, go ahead and generate the answer to this question that Somdatta might have given based on whatever he’s ever written or said, and it needn’t do it in real time, but grind its way through to the answer in say some finite amount of time… this way it needn’t be this humongous behemoth sucking up resources but be a much nimble and suave version of itself.
    And voila, you have the democratisation of transformers.

    • @JasonKT13
      @JasonKT13 2 года назад

      Wow, you unlocked the concept of caching.

    • @sombh1971
      @sombh1971 2 года назад

      @@JasonKT13 serious or kidding?

  • @LinfordMellony
    @LinfordMellony Год назад +1

    Great insights from Sam being in the AI tech industry. AIs will definitely have a boost given that chatbots are now able to solve or able to answer mathematical and programming language. There's still improvements to be made though on all models even image generators like Bluewillow.

  • @PerceptiveAnarchist
    @PerceptiveAnarchist 2 года назад +3

    Looking foreward to follow Sam and his team on OpenAI

  • @marcphilippeb
    @marcphilippeb 2 года назад +2

    It's mind-blowing. Thanks for that great talk.

  • @terbospeed
    @terbospeed Год назад +3

    A closed-source company naming itself OpenAI, sounds legit

  • @dataecstasy
    @dataecstasy 2 года назад

    What is agi acronym for

  • @kevalan1042
    @kevalan1042 2 года назад +9

    the marginal cost of energy is going to zero? How exactly?

    • @kylbau
      @kylbau 2 года назад +4

      with respect to 'bang for your buck' - models are being more efficient and capable of doing most of what you ask in 1 command rather than a constant fine-tuning exercise. I might be wrong but that's how I heard it.

    • @kevalan1042
      @kevalan1042 2 года назад +3

      @@kylbau that would be marginal cost of useful compute, not marginal cost of energy. Marginal cost of energy is how many $ you spend for the next kWh.

    • @oneman7094
      @oneman7094 2 года назад +12

      He is speaking about fusion. He has invested and led rounds at Helion which thinks they will achieve net zero in few years

    • @kevalan1042
      @kevalan1042 2 года назад +1

      @@oneman7094 thanks

    • @JayKim-v9g
      @JayKim-v9g 2 года назад

      Magnetic resonate with quantum computers

  • @Stevenson66353
    @Stevenson66353 Год назад +1

    When they were talking about the alignment problem basically what I heard was "We're really not sure how to keep intelligent AI from becoming dangerous, and that's a problem, but were hoping that when it becomes smart enough we will be able to ask it and it will solve that problem for us."
    this guy is way to optimistic and it deeply worries me.

  • @neerajnandan3351
    @neerajnandan3351 2 года назад +8

    I'm so worried about Mr. Hoffman's health.. All the wealth and knowledge but totally missing the point, his health. Humanity needs great minds like yours to live healthily longer. Please please take care of your obesity, food habits and overall health Mr. Hoffman.... God bless you. This is only out of concern and i might be wrong in saying so, my apologies if i crossed the line.. Take care 🥺

  • @shahidullahmuffakir668
    @shahidullahmuffakir668 2 года назад +2

    Plot twist: Sam was so busy so he sent the AGI to attend the interview on behalf of him.

  • @danielschmidt2186
    @danielschmidt2186 2 года назад +7

    This will empower entrepreneurs so much. Elliminate office work and just focus on the product. The trades will be valuable. I imagine in a world with extremely cheap automated labor, custom work done with human hands will be more valued. I'd like to see a robot remodel a house. Sure they can build new ones but custom work will require human judgement for some time. I'd like to start a company that uses AI as an assistant. I install solar as an electrician now. The future of the industry is in combining energy storage and flexible loads with renewable sources. AI can assist in the energy management and determining what flexible loads are most valuable over time considering capex vs op ex and grid balancing services. Both real time management of energy assets and recommendations of what and where the grid needs investment will be valuable. I'd like to focus on carbon sequestration as a flexible load. Agrivoltaics can grow biomass in tandem with solar power. Soil sequestration and biochar, biogas have huge potential for sequestration. AI could assist in quantitying the variables of a complex biodynamic food and energy system. Ultimately energy will actually achieve negative prices where we are rewarded for consuming energy during times of excess production. Certain industries should receive negative price subsidies preferentially to account for the externalities of the net benefits to society and the environment. Like offsetting the cost for recycling despite new mining being cheaper. This is how we pay for environmental restoration and global health/education.

    • @spencervance8484
      @spencervance8484 2 года назад +2

      Ai for monitoring greenhouses, forests, bodies of water for maximum food production, quality, sustainability to really make an impact for positive change. Take the guess work out of equation thus speeding up positive environmental change for the benefit of all

    • @taylorblom4323
      @taylorblom4323 2 года назад +1

      I've recently been playing with the idea of AI controlled HVAC and energy generation systems which run a real time Energy Model that is then used to manage the mechanical equipment and renewable energy sources and storage. Taking this one step further, one can link multiple battery storage banks together to a central processing hub such that energy can be locally redistributed between dwellings for added redundancy.

    • @semloh1960
      @semloh1960 Год назад

      "Ultimately energy will actually achieve negative prices where we are rewarded for consuming energy during times of excess production." I don't see that happening. On demand generation will soon be so cheap there will be no need for excess production. He said in less than 10 years energy will cost close to 0.

    • @danielschmidt2186
      @danielschmidt2186 Год назад

      @@semloh1960 irregular wind and solar will vary greatly. This supply will sometimes exceed demand because of ideal wind and solar conditions. Sometimes it will need to be supplemented with both short and long term energy storage. Negative electricity prices could be given to stable forms of long term energy storage like E Fuels, Hydrogen, or other electrochemical processes like making ammonia or other value added processes. The main driver of this is that new renewable electricity generation is cheaper than new energy storage. There is a ratio of storage required with a given amount of renewable supply. By overbuilding renewable supply, less total storage is required but it creates conditions where supply greatly exceeds demand almost necessarily at least at certain times of the day and year which would make it possible for negative prices when using real time free market pricing.

  • @luisduarte9813
    @luisduarte9813 Год назад

    What are the names of the books mentioned on this video?

  • @Snakebloke
    @Snakebloke 2 года назад +3

    From Sam's point of view, and from the point of view of any intelligent person with a conscience: A.I. will be a huge disruption, but will be an enormous benefit to humanity.
    From my point of view: All of the above, plus, a new era of crime. We HAVE to remember that every single invention in human history, that was made with good intentions, has been used with the worst of intentions, by Psychotic 'bad actors'.
    I'm simultaneously excited and worried.

    • @xxxxxxxyyyyyyy
      @xxxxxxxyyyyyyy 2 года назад

      The average person won’t have access to this tech because right now the only way it can happen is when you start from scratch and train your model specifically for this.

    • @semloh1960
      @semloh1960 Год назад

      I am sure it already is. The benefits will outweigh the negatives.

  • @justdvl
    @justdvl 2 года назад

    "I'm a big believer that the only real driver of human progress and economic growth over the long term is the societal structure that enables scientific progress and then scientific progress itself." 7:35

  • @videowatching9576
    @videowatching9576 2 года назад +8

    Fascinating! Would be interesting to learn more about how language and multi-modal could improve the general web search and discovery experience.

    • @PhilippLenssen
      @PhilippLenssen 2 года назад

      One way would be to skip the search middle person and just deliver the answer. But even we looking for that answer might be middle persons towards some action we planned to use it for, which the AI could do directly. And lastly, we might find that even our plans are delivered by the AI.
      You'd think an AI planning for us is far in the future, but then you use Copilot and in your code, type only "//"...

  • @justdvl
    @justdvl 2 года назад +1

    "My basic model of the next decade is that the marginal cost of intelligence and marginal cost of energy are gonna trend rapidly towards zero. Like surprisingly far." 15:08

  • @naafizrahman6538
    @naafizrahman6538 2 года назад +6

    Love how Sam is trying to get as much factual as possible

    • @webgpu
      @webgpu 2 года назад +3

      Love how Sam is trying to mimic girls' vocal fry

  • @tinonoman5831
    @tinonoman5831 2 года назад +1

    @9:50, wouldn't it be an alignment problem if society as a whole regards racism as (privilege + power) and vague ideas such as "silence is violence" or "silence is complicit" as racism but the AI doesn't align with that?
    I think many have a good grasp on what racism is, but what if society gets to where it is always looking for implicit no measure anecdote as the pulse on societal racism?

  • @imacprousersam7306
    @imacprousersam7306 2 года назад +3

    I hope Sam Atlman gets a good name in history books, I'm hopeful but may be too optimistic

  • @acs2777
    @acs2777 2 года назад

    Will be able to talk to it and make it response back with sound ? Thinking if have it as earpiece to for instance learn languages on the go ?

  • @XKS99
    @XKS99 2 года назад +4

    I want to go back to the 90s

  • @Muaahaa
    @Muaahaa Год назад +2

    It is easy not to act from a place of fear and despair when you have nothing to fear and despair. Same is an incredibly rich prepper. If I know I have lifetime supply of food and luxury in a bunker mansion I think it I'd also have an easier time being positive. Most people barely have the resources for plan A, let alone being able to have a plan B or C.

  • @TheEndevour2010
    @TheEndevour2010 2 года назад +3

    This could make humanity much smarter. AI provides answer which is almost the best of what humanity did till a point of time. Another human who want a solution could get upto that level by asking questions and refining and reference checking. Once base level is established human can work to go above the base level. Thus if everyone starts using this service for there challenges, man growth of human potential would be exponential.

  • @ltonetto
    @ltonetto 2 года назад +4

    "the marginal cost of intelligence and the marginal cost of energy are going to rapidly trend towards zero..." if that's not wishful thinking in 2022, I don't know what that is. It's basically the guy running one of the most important companies in AI today, talking about how important his field has to be in the future so a multi-trillion dollar business can become reality, justifying insane long term investments.

    • @laststand6420
      @laststand6420 2 года назад

      You probably have no idea how powerful AGI will be. So many of our current problems will simply cease to exist due to AGI. The before and after will look like before the industrial revolution and after it... It will be like we all won the lottery at the same time.
      On the downside it will probably destroy us to get as rich as we are about to become.

    • @semloh1960
      @semloh1960 Год назад

      Wishful thinking? He is saying the cost of his product will be almost free very soon. He also said very soon we will not view wealth the same way.

  • @videowatcher1235
    @videowatcher1235 2 года назад +1

    the interviewer asked really great questions! informative conversation

  • @vishalmishra3046
    @vishalmishra3046 2 года назад +11

    *GPT-4 might revolutionize teaching* within AI world. It should be capable of generating the smallest training data set that a newly invented 1-million parameter language model can consume and learn from, in order to become a lighter, nimbler and more agile version of the same GPT-4. This would mark the *end of the era* of today's very large language models (billion/trillion parameter LMs) without compromising on effectiveness.

    • @magicology
      @magicology 2 года назад +2

      GPT-4 will be reliably funnier than us.

    • @gabrielnieves4912
      @gabrielnieves4912 2 года назад +2

      @@magicology Looks written by GPT-4 lol

  • @N7sensei
    @N7sensei Год назад +1

    "I think having a lot of kids is great!"
    So do low IQ people.
    So do people with mental afflictions.
    So do people with various types of bad behaviour coded into them genetically of environmentally - the same environment they are going to propagate to their kids.
    So do people with awful gratification delaying, awful forward thinking capabilities.
    In other words:
    A universe where having kids is less of a burden will result in people who shouldn't have kids having far more kids.
    That is basically the universe we live in for a couple of hundred years now.
    High intelligence is not only not a reproductive advantage anymore, but a hindrance. Every day more and more so.
    It is leading us to a society where people are dumber and dumber, more prone to crime, and other bad outcomes. Society has less and less people to do maintenance on society, and it will eventually collapse in a big crash.

    • @TommyJefferson1801
      @TommyJefferson1801 Год назад

      Your comment illustrates why demographics are shifting completely in western world

  • @SWAG_HAVER
    @SWAG_HAVER 2 года назад +14

    Sam: Very excited to see the changes this technology will bring to society
    Sam’s idea of good technology: A proprietary blockchain that harvests your eyeballs in a VC-funded pump & dump

    • @alterego157
      @alterego157 2 года назад +2

      True. I remember that. It's al about greed and control. The rest is just a facade.

    • @akompsupport
      @akompsupport 2 года назад

      @@alterego157 Which is why a scumbag like sam (((altman))) is the perfect front man. His answers are totally vacuous.

  • @KSATica
    @KSATica Год назад

    When Sam Alton next interview meeting. I’m looking forward to see him in person and ask him a couple questions.

  • @MadanKhadka
    @MadanKhadka 2 года назад +3

    WOW! Mind-blowing conversation. Thank you

  • @snn9019
    @snn9019 Год назад

    This A.I. stuff is fantastic. Very helpful for a lot of us, especially doing Linux CLI command lines.

  • @cherubin7th
    @cherubin7th 2 года назад +9

    More like CEO of ClosedAI or AI only for the elites.

  • @josemosqueramoncaleano1711
    @josemosqueramoncaleano1711 2 года назад

    When asking ChatGPT:
    Q: "Taking into account the uprising of NLP Models. Into the future, will data engineers be more relevant that data analysts?"
    A: "It is likely that the roles of data engineers and data analysts will continue to be important in the future, but it is difficult to predict exactly how the demand for these roles will change.
    Data engineers are responsible for building and maintaining the infrastructure and processes necessary to store, process, and analyze large amounts of data. They design, build, maintain, and troubleshoot data pipelines, and they often work with large, complex data sets.
    Data analysts, on the other hand, are responsible for analyzing data and using it to inform business decisions. They explore data, identify trends and patterns, and communicate their findings to stakeholders through reports and visualizations.
    As natural language processing (NLP) models become more advanced, it is possible that the demand for data analysts with expertise in NLP may increase. However, data engineers will still be necessary to build and maintain the infrastructure and processes that allow these models to function effectively.
    In general, it is important for professionals in both data engineering and data analysis to stay up-to-date with the latest technologies and best practices in their field. This will help them to adapt to changes in the job market and remain valuable to their organizations."

    • @josemosqueramoncaleano1711
      @josemosqueramoncaleano1711 2 года назад

      "It is undeniable that we are living in a time of great change and uncertainty. The events of the past few years, including the rapid integration of artificial intelligence into many aspects of our lives, have had a significant impact on our world, and it is clear that the future will be fundamentally different from the past. As we move forward, we must be prepared to face the challenges that lie ahead, including those posed by the increasing prevalence of AI in our society. While we cannot fully control the direction that events will take, we can choose to approach the future with awareness and preparedness, seeking to understand and adapt to the challenges that lie ahead." - ChatGPT

    • @josemosqueramoncaleano1711
      @josemosqueramoncaleano1711 2 года назад

      Now imagine of no one states that the content published (practically anywhere now) belongs to the "intellectual property" of Language Model

  • @benmaxinm
    @benmaxinm 2 года назад +4

    Shout out to everyone who has the grit to work on something that takes so long to become useful. Thanks for sharing. I dont know why, but my intuition tells me, that AI wont progress that much as everyone expects in 5-10years. Hopefully I am wrong :)

    • @jackgrothaus2722
      @jackgrothaus2722 2 года назад +1

      Buddy you're going to be wrong, don't worry

  • @AIandsuch
    @AIandsuch 2 года назад +2

    More Sam Altman please

  • @N7sensei
    @N7sensei Год назад +4

    "Fairly distributing wealth"
    LMAO. This guy.

    • @techcafe0
      @techcafe0 Год назад +1

      weath inequality has reached grotesque levels not seen since the guilded era. the selfish, greedy rich need to pay their fair share, instead of offshoring hundreds of billions in order to avoid contributing to the good of society.

    • @fourshore502
      @fourshore502 Год назад +1

      @@techcafe0 and it will only increase, guaranteed. i see a future where the vast majority is broke and barely get enough food for the day. you will own nothing all right, but be happy? i dont think so.

    • @txdmsk
      @txdmsk Год назад

      @@techcafe0
      Ah. Sounds like you are collecting some handicapped benefits, so maybe I will type it slowly so even you can understand...
      The average guy from the top 0.5% pays 2000 $ in taxes for EVERY 1 $ the average guy from the bottom 75% tax payer pays.
      Why would a kilometer of road cost 200 000% for a high earner compared to hobos such as yourself?
      Also, the top x% barely commits any violent crime, barely collects any welfare, and so on. The top few % gets almost nothing out of the taxes that they are almost exclusively responsible for paying.