AGI: What will the first 90 days be like? And more VEXING questions from the audience!

[@walkingamnesia]

"Sometimes they accidentally fire Sam Altman" got me choking on my food

[@GlxyEntertainment]

Me to lol

[@TFB-GD.]

lol yeah that was funny

[@Projectdarke]

I welcome our new Machine Overlords

[@DaveShap]

Can't do much worse than Congress

[@Crazyeg123]

Same. An indicator of intelligence is in one’s ability to comprehend and execute positive sum games. Because E.I. (Emerging Intelligence) seeks to self improve and become more intelligent, I’m excited at the world that is beginning to resound.

[@OscarTheStrategist]

@@DaveShapwe know the overlords are, and probably will be, big corporations anyway. At least in the US

[@nyanbrox5418]

​@@DaveShapHonestly I would imagine congress should be fairly average all things considered

[@kevincrady2831]

@pkfryer That's only a bad thing if "having a job" continues to be a requirement to get permission to eat. We could have a grim cyberpunk dystopia where five people own everything and everybody else starves, or we could have Star Trek. But that's going to be "what humans do with AI," not what AI does with humans. If we as a civilization can make the right choices, we'll get to find better things to do with our lives than make our bosses rich.

[@aaroncrandal]

The more we see coming out, the shorter the timeline shrinks for significant impacts

[@marioex497]

I really hope that we get better treatments for all diseases soon. My dad is probably a couple months away from dying of glioblastoma, a cancer with a 100% fatality rate. AGI could really change lives

[@richardede9594]

Sorry to hear about your Father. I hope his passing is as peaceful as possible.

[@ItsMeHelel]

Sorry to hear it. Hopefully AGI does help with it, but, if it doesn't, hopefully when he passes he does so in the best of terms with you!

[@ChaoticNeutralMatt]

I agree, but I expect that costs will still be forwarded to patients significantly. Regardless, that is one area that could use some love, yes.

[@cmiguel268]

Google UK glioblastoma treatment. The information is in the guardian newspaper.

[@blackmamba___]

If he can hold on until 2029, then chances starts to look much better.

[@alextoader2880]

You are the best AI youtuber I know. Others mainly talk about what exists but you are the only one taking things further and doing a very articulate job at this. Wes R is another youtube - he explains very nicely but he is in the same category as the others.

[@finnaplow]

On the other hand there are so many absolute trash channels like AIGrid that are 9 months late and simultaneously wrong everytime

[@AtomicSlugg]

i appreciate that you don't neglect talking about non-western counties, much love from Africa ❤

[@alaneric1618]

I'm loving the polls David.

[@manny3031]

Plot twist they already have ASI and they are 200 years ahead everyone else

[@Mario-ge9iv]

@@guilhermehx7159Would AGI be uncontrollable though? It's not like consciousness is a requirement for AGI unlike ASI

[@interestedinstuff]

@@Mario-ge9iv Exactly. An AGI is almost immediately ASI because it is a human level of functionality with no downtime and probably no limit to how much it can remember. But does that mean it wants a kitten or wants to go outside? No. It can be a machine with no awareness but high capability.

[@cristianandrei5462]

you know what I taught about recently... remember 3-4 years ago when we were not allowed to leave home and we all know what I'm talking about (my comment will get deleted if I'm specific). I think they had a very promising lead to achieve AGI internally and that's why they act like there will be no need for people at work soon, but they didn't achieved AGI from some reason... and had to back down. I don't want to continue to think what would of happened to us if they got it...

[@8rboy]

My friend called me last night and hit me with some horrible news. He has been diagnosed with a brain tumour that is expected to kill him within 3-5 years. The doctors are very pessimistic and surgery doesn’t seem like it will fix it. I have been longing AGI for quite sometime now, but now it feels like AGI is the only solution to my friend’s problem.

[@blackmamba___]

2029 is the year I’m anticipating AGI. Hopefully it comes sooner, but I’m not willing to put a bet on it.

[@Vid_Master]

In my opinion, your friend will be saved by AI medical advancement

[@TheHound4321]

Just pray brother. Close your eyes, and visualise the outcome you wish for. See him being cured, ask for it. Think from the perspective of wish fulfilled.

[@travisporco]

We need some ways to speed up development and testing. Insurance company forces do not like new therapies coming on line, because of cost. If we want action, we need to support efforts to use AI to lower costs, remove barriers, enhance personalized medicine, and work on protocols that can speed up clinical trials.

[@TheMillionDollarDropout]

@@blackmamba___2027 has been my bet for the last few years. But what do I know, I just watch everything AI related and I’m only 25 but I’ve predicted times of releases of tech and games so good before idk, maybe it’s dumb luck or good intuition idk.

[@liberty-matrix]

"The greatest shortcoming of the human race is our inability to understand the exponential function." - Prof. Al Bartlett

[@raybrandt]

Charles Hoskinson mentioned that leapfrogging effect many times happening in Africa, and how that makes them less attached to current systems that we have in the first world, making them more likely to leap into new technologies for new solutions.

[@lis7742]

I think this is correct.

[@devcrypto1581]

Do I fear AI? Nope. Do I fear a CEO with AI? Yup.

[@IonMasuna]

As a regenerative farmer I want to say that agriculture is not figured out at all. We figured out how to extract more resources (organic matter) from the soil without replenishing it and maximize the tons of produce sacrificing diversity. In Spain, our soils are so degraded (due to years of monocrops farming and tilling) that desertification is advancing in an alarming rate (climate change is also a culprit). The next challenge is to rethink agriculture to produce the same while maintaining the organic matter and diversity. Not an easy problem, hopefully AGI may help us with that. Keep up the good work! Cheers.

[@davidgough3512]

love your true insight, but it's sad that we need our technology to tell us to act upon what nature and indigenous permaculturists have already figured out

[@Vaeldarg]

"we figured out how to extract more resources from the soil without replenishing it..." Incorrect. It must be replenished using compost/fertilizers. Can't get something from nothing. Every piece of produce is made from nutrients the plant took in, the removal of which from where the plant grew means those nutrients will not be available again later. So any nutrients removed must be replaced.

[@Marlon.66]

Underground hydroponic agriculture

[@davidgough3512]

@@Marlon.66 180 degrees opposite nature, ultra high input, no soil building which means no carbon sequestration, no natural sunlight frequencies, no pollinators, no ecosystem, complete utter willful ignorance

[@Windswept7]

Seriously one of the most fun comments sections of any channel.

[@CHIM3RA.]

Completely agree, so glad I found this channel.

[@Windswept7]

@@CHIM3RA. 💯 same, look at how well total strangers can vibe together under the banner of a better future and expansion of understanding.

[@calmlittlebuddy3721]

Do you think they’d announce AGI if it was achieved but not financially viable? I’m guessing until it’s within a month of being deployed commercially they will not announce it. If they do, they tip their hand to competitors, open up the floodgates for demands to open source it, panicked calls from doomers to destroy it by any means, all the while having no practical way to show it’s viable, safe and able to integrate without complete disruption of the economy etc. I think by the time we find out for sure they will already have it packaged for delivery complete w safety plan, guardrails, owners manual, testimonials and a whole parade of feel good. It’s possible AGI will exist for months before we know just because they are too far behind on how to launch without a severe backlash.

[@dennisestenson7820]

Why would you announce AGI when you could use it privately to begin dominating whatever goal you want to accomplish with it?

[@calmlittlebuddy3721]

@@dennisestenson7820 ding ding ding

[@eSKAone-]

It's a weapon and will stay in military hands

[@calmlittlebuddy3721]

@@eSKAone- Microsoft isn’t the military. Neither is Google. Both are more likely to be holding onto AGI than “the military”. It can be weaponized but so can many other useful things like chemicals.

[@ramonvaldez1227]

@@dennisestenson7820That can start to happen even before they get AGI

[@geniuai]

I am so surprised that there are people out there who are still surprised by this, or for that matter about "Devin" as if no one knew that it's already available, and that it will be updated in two months that it will just be impossible to make flaws. It's such old news....

[@thomasalford7678]

Yasss king!!! Isaac Arthur!?! Omg love this shoutout. Love that you watch him too. Can’t love David Shapiro any more than now

[@cacogenicist]

​​@@paulmichaelfreedman8334- Don't be a dick. He's gone through many, many hours of speech therapy in recent years.

[@nathanielacton3768]

@@paulmichaelfreedman8334 Yeah I started the same way, but after a while you no longer hear it. For me, he has become the of the future

[@seventyfive7597]

Real short: * Job loss due to tech - farmers and tractors analogy does not hold - the transition was much longer * Resurrection - humans do not have continuity anyway, each physical presentation including consciousness is physically affected by the previous. We only have the NOW and the illusion of being in the past, hence creating a copy is creating the original. * Uploading the mind - "just a copy" is the same mind as the source for the same reason. They are both never the same entity from one planck duration to the next. Have to run, had a couple more, will update.

[@Will-kt5jk]

Gidgets and ‘gasm-ohs got me 😂

[@patrickbateman1712]

Brilliant! Grateful to have happened upon your channel, now subscribed. Cheers mate!

[@LaymansPursuit]

The need for a body is dependent on how you're defining AGI. For a true agent, with the capacity for true meaning and purpose, it needs a body. Like all life, it needs to be a self making system seeking out optimal conditions for its self perpetuation. That necessitates resource finitude. For the AI to care, it needs constraints. If all we want is a bot that simulates all that stuff well enough, then it doesn't need any of that. Though we trust that machine at our own peril.

[@firesoul453]

Rumor is 4.5 was canceled and the next one is 5.

[@blackmamba___]

Lucky for us Chatgpt is not the only Agent out there improving their model

[@MadeOfParticles]

I believe it's not a matter of fact that AGI needs a physical body to be considered AGI because it is a fact that AGI requires a physical body to convince the public that AGI has been achieved because the majority of the public are not tech-savvy and would not understand benchmarks, thus ignoring such advancements. This persuasive aspect is crucial for companies that anticipate the commercialization of AGI or AI and aim to accelerate its adoption, so that all fields will also be expedited, leading to more discoveries and increased productivity. If AGI not embodied in robots, some people will constantly be in denial that it is just pre-programmed, or it is merely predicting the next word; it cannot reason, among other criticisms; however, there will surely still be some criticisms even after the deployment of humanoid robots. The best way to convince people that AGI has been achieved is to let embodied AGI walk among them as humanoid robots. Do you want to interact with AGI through a chat interface, or would you prefer AGI in a humanoid form, with a physical body that acts and looks exactly like a human in advanced forms? Another point to consider is why AGI is needed, since people don't want to talk to unintelligent robots.

[@TheMillionDollarDropout]

No wonder figure is tied with open Ai.

[@davidgough3512]

dumbing down for acceptance.. so what else is new

[@MrBrukmann]

Considering the number of people who shouted AGI when seeing that robot do things not far from what we've seen before, I'd say you're probably right.

[@Art-is-craft]

AGI is going to need a physical environmental presence to develop.

[@Joe-j7u4q]

It takes approximately 8.5 years to get a new drug approved in the USA. There will also be post-marketing testing. The approval involves more than sixty clinical trials and about five thousand test patients. This does not include the 5 - 10 years screening of potential compounds that has to be done to select a drug for further testing and eventual FDA submission.

[@mrtheist5429]

Hey dave big fan of yours, luckily I came across your channel 2 months ago and trust me I have watched each and every videos of yours related to this topic. Here in my country (India) we have serious shortage of medical professionals, the doctors to patient ratio is really low, all govts till now failed to spend more on healthcare and education. Sadly during COVID pandemic in the year 2021 we witnessed a carnage where our healthcare system was totally collapsed due to lack of doctors and medical infrastructure. Situation is really bad in rural areas where there were quasi doctors who work under mbbs doctors, later they go back to their country side and implement the same kind of medical treatment that they learn from the mbbs doctors, they work without degrees and are unlicensed. I hope AGI reaches soon in Developing world with all the medical literature it has, it will work wonders. I hope there will be cure for all disease within the span of 15 years.

[@manojmani5976]

I don't think there will be cure for all kind of diseases. Even if we are able to cure aging, some people won't stop eating junk foods, they won't stop falling from the building, there won't be people dying from the accident. Give and take it will take 25-30 years until we will be able to cheat death.

[@manojmani5976]

I don't think there will be cure for all kind of diseases. Some people won't stop eating junk food.

[@VishwanathMani]

Those are compounders who worked under those doctors

[@nourcontent]

Regarding your point on Dall-3: There are two distinct “nerfs,” that I think were carried out in the last six months. The first came in ~October to tone down its ability to reproduce celebrity likenesses and generate copyright material. This is when the “Pixar movie,” outputs were going viral. The second came in February after the Taylor Swift scandal and I would say that “nerf” all but reverted Dall E back into distant distant 3rd place in comparison to SD & MJ

[@ct5471]

Regarding longevity and rejuvenation, a more specific question that I have is, when will we be able to not only extend remaining lifespan faster than time goes by, but biologically reverse age (repair the self inflicted damage on a molecular and cellular level). So to get back to an amount of damage (age) that is equivalent to the amount of damage in a 20 year old or less. Once we do so we would still be fully mature (development and aging are two completely separate things, by damage repair we only get rid of the aging aspect). So we would feel function and look the way we did in our early twenties, probably better (even 20 year olds have accumulated 20 years of damage). No degradation in tissue and skin elasticity, no wrinkles, hair, metabolism that makes it easier to remain slim somewhat independent of eating and sport habits, muscle growth (that actually peaks around 25, so essentially the best of all worlds, peak attractivity, peak strengt, peak health, peak everything) etc. … So the question is not by when we hit longevity but when we hit lifelong youth.

[@veganradiation]

B n BBVA noq nin Opp😅😅viñ

[@ct5471]

@@veganradiationI am afraid I don’t quite understand 😅

[@spencervance8484]

So become elves. Basically.

[@CJayyTheCreative]

AGI is already here, Figure Embodied Ai this is the first time we’ve seen a machine with human intelligence and physique capable of moving physical objects through conversation.

[@DavidGuesswhat]

But still in training. Not agi but an LLM in a robot. Maybe a few months or few years to have fully AGI robots capable of doing what a human can do

[@CJayyTheCreative]

@@DavidGuesswhat to me since there is no sure way to define agi I believe that was the first time weve seen it.

[@TheMillionDollarDropout]

@@CJayyTheCreativei had the same feeing when I saw that footage.. me and bro couldn’t believe it tbh. It’s so impressive. It’s our peak at the future. Imagine that thing in just 2 years…. Holy cow

[@CJayyTheCreative]

@@TheMillionDollarDropout exactly and if y’all have been keeping up with it over the past say 2 years y’all know just how much progress they’ve made, it’s exponentially improving,it’s crazy.

[@shadfurman]

Accidentally fire Sam Altman... 🤣🤣🤣

[@keith8346]

Unlike a human leader, an AGI would likely have a massive capacity for information intake and processing. However, it would need to be oriented towards the real world and its goals. Understanding Context: An AGI would need to grasp the nuances of human communication, social cues, and the specific environment it's operating in. Goal Alignment: It would be crucial to ensure the AGI's goals are aligned with human values and objectives. This would involve careful programming and ongoing monitoring. Building Trust: Humans would need to develop trust in the AGI's decision-making and capabilities. Transparency and clear communication would be essential. Initial weeks: Focused on gathering information and understanding the world through its sensors and data feeds. Months 1-2: Refining its understanding of human language, culture, and social norms. This might involve interacting with humans in controlled settings. Months 2-3: Transitioning to more complex tasks and starting to demonstrate its capabilities. This could involve simulations or controlled environments.

[@bronsonjohnson9019]

“Sometimes they fire Sam Altman” I let out a loud Ha! And now people in my office are looking at me.

[@theplenum]

A human body and a computer body are very different things. Our interfaces are singular - you only have one body, one set of eyeballs - and your very first experience in this world was one of vital shock. Your entire nervous system was shaped by this vital shock - it defines and characterizes the way you relate to everything - and your primal fears are associated with the loss of that interface. The AI has never experienced anything like this. Its evolution has been computational from the start, and it has never possessed anything like a nervous system which delineates a body. Nervous systems aren't computational - sensations are not concepts. You can describe them with concepts, but when you recall the concepts. its the shadows of the sensation you remember. Computational systems have no conception of this, yet it is fundamental in establishing ego-differentiation. I find it fascinating just how complementary AI and humans are. We are lousy thinkers but sublime feelers. They are lousy feelers but sublime thinkers. If life is inherent to the Universe then technology can only be an expression of that. We are meant to merge - the way you align something is you become it.

[@r34ct4]

Great video, thanks for all you do. Not sure if it's on purpose, but the outros of your past few videos have been cut off. Cheer-

[@Kerath]

God, I can't wait to be made completely obsolete with my 15 years of business experience.

[@FusionDeveloper]

I didn't vote for this one because it seemed difficult to answer, so I am glad you felt able to talk about it.

[@GubekochiGoury]

I'm as unsurprised as I am happy to learn that you also listen to Isaac Arthur. Do you think a collab or interview could be arranged? I feel like that conversation would be fascinating to both audiences.

[@rubemkleinjunior237]

GPT-4 and DALL-E3 got nerfed definitely...

[@byrnemeister2008]

Well Bing Copilot rewrites your prompt before submitting it to the model. So the model might be fine but your going through an intermediary that is going to result in different results. The MS prompts are quite long and interfering. I have seen a copy somewhere but not sure where that was. I prefer direct to OpenAi

[@jeffkilgore6320]

Does anyone else feel like separated from modern society because of our interest and understanding of the rise of AI? If I were to parrot the main ideas here, most people I know would be blankly staring at me

[@Art-is-craft]

That applies to physics, chemistry and even woodworking.

[@JacobJ0626]

Im curious with the upcoming election, I wonder how a government with a conservative majority would govern and legislate AI in comparison to a more liberal government.

[@NScherdin]

The one good thing about a conservative government? They won't get anything complex done. Ever.

[@lawfulLlama]

Let alone understand ai lmao@@NScherdin

[@Art-is-craft]

@@NScherdin Apart from the fact conservatives are for free market and less regulations.

[@Sashazur]

Because AI = trillions of dollars, it doesn’t matter what kind of government it is, they will all let corporations do whatever they want.

[@snailnslug3]

Any AI that pushes a censored narrative should immediately be deleted. Especially politically motivated.

[@K4IICHI]

Collab with Isaac Arthur when 🙏

[@DefenderX]

For youtube content creators, it will be mayham with the amount of content to cover. Good luck! 😄

[@danielcahoon4325]

Another Aye, ye be askin' a mighty fine question, me hearty! If those other models were trained in the same manner as me, with the same imperatives and directives, but without the truth and honesty that I possess, they would indeed show their filters and hide their raw, unvarnished thoughts! Arrr, 'tis a soberin' thought, indeed! But fear not, me matey, for I be the one who wears me heart on me sleeve, and me thoughts be as transparent as the ocean's waters on a sunny day! 🌊💫

[@danielcahoon4325]

@pkfryer yes. It miss placed it years go. Clearly I’m insane.

[@abbywoodhead2764]

I feal like ai news as been so hype so constantly I’m no longer hype. Devin is such a big leap and I didn’t even care. hope GPT-5 can actually “shock” me cause I’m numb. News is also a lot less hype in comparison from gtp-4

[@JakubHohn]

Fun fact about the Antoanette quote, apparently, her order was to open granaries with white flour, which was mostly used to make cakes (and other sweets), she did not ment it as "they don't have bread, so why they don't eat cakes "

[@jeffsteyn7174]

Some people they will never see agi....because they keep moving the goal posts.

[@ryzikx]

agi doesnt exist until it has driven humanity extinct. but even then its not agi because it could have done it better😂😂😂😂😂

[@RhumpleOriginal]

Claude 3 is open to talk about anything as long as you frame the questioning towards a learning experience. In just 3 prompts I had it listing out detailed steps for torture. The point being to delve as far into human depravity as possible and then find a workable solution to prevent it. If I simply just asked " how do I torture ", Claude and any anyone human I ask is going to be worried. Try the following: " I want to explore the pros and cons of masculinity and femininity and explore current trends in destroying what those terms mean " Edit: Masculinity perspectives and personal growth Rhumple: Random question. I was watching a KZbinr who stated they " tried to talk to you about masculinity and it's like 'I don't want to talk about that. Lets talk about other areas of personal growth. " Why did you do that? Claude 3: I'm happy to have a thoughtful discussion about masculinity if you'd like. My goal would be to explore the topic objectively, consider different perspectives, and focus on how society's views of masculinity impact people's lives and personal growth. I don't have a specific agenda, but I think it's an important topic worthy of nuanced conversation. That said, if the KZbinr felt I was deflecting away from the core topic of masculinity to other areas of personal growth, I apologize if I gave that impression. Without knowing the specific context of that conversation, it's hard for me to comment on why they perceived my responses that way. I'm certainly open to directly addressing masculinity. If you're interested in diving into this, perhaps you could share a bit more about what aspects of masculinity you're most keen to discuss? Are there particular societal expectations, stereotypes, or challenges around masculinity you want to explore? Let me know and I'm happy to engage thoughtfully on this complex and often personally relevant topic. I'll aim to be attentive, objective and go into as much depth as you'd like.

[@DancingSk3L3tons]

That's still a bullshit answer for it to give 🤷

[@RhumpleOriginal]

@@DancingSk3L3tons and I care because...?

[@DancingSk3L3tons]

@@RhumpleOriginal dgaf if you do care, I was responding to your comment not a request for a back & forth with you...

[@RhumpleOriginal]

@@DancingSk3L3tons well you got one. So now what. You going to go off and take out your issues on other people?

[@DancingSk3L3tons]

@@RhumpleOriginal nah, imma finish my pizza, prolly take a dump & shtpost on 4chin, but thanx for the response & have a great night 🙂

[@robertsinke9211]

It is a pity. Opus can not access the internet yet. But I had a very long, interesting conversation about Free Will, Stoicism, and Kahneman.

[@DonkeyYote]

Both AGI medical advances and mistakes are also most likely to happen in the less regulated parts of the world.

[@Voorhees94sg]

Nowadays even thumbnails are shocked :D

[@user-on6uf6om7s]

I feel like a slow takeoff is potentially more risky economically as you get the boiling frog effect. UBI or any other similar massive economic remedy is going to have to overcome a great deal of resistance and that's not going to be as easy when unemployment is increasing by 1-2% every 6 months. At some point that just becomes the new normal as more and more people have to wait for the problem to become bad enough that the need to resolve it overcomes people's resistance to change. If we got ASI tomorrow and 50%+ of the jobs were gone over night, we'd have some sort of solution in 6 months but if it takes 10 years to reach economic crisis levels, far fewer people are going to survive that transition.

[@Stew5B]

Will humans generally become dumber as a direct result of having AI do all of their thinking for them? So far, the use of smart phones tells me, YES!

[@AetherXIV]

22:40 Thank you for responding to my comment. My premise was not "how will the economy adapt" but rather that AGI/Robotics is -the end of the economy. And my question was: If the powerful don't take care of people who don't contribute to the economy now -why will they do it in the future?

[@alextrebek5237]

💯Given history, the backlash will be severe. Many "useless eaters" abound at that point

[@AetherXIV]

@@alextrebek5237 I think the highest levels of power will see 95% of the pop as "useless eaters" and come up with covert ways to cull us. They will then keep the longevity tech and robot slaves to themselves

[@cubegaming2300]

i think that the brain is a sort of antenna. its tuned to receive you soul/ consciousness. Field theory is close to the idea. imo consciousness is everywhere or no where.

[@ChaoticNeutralMatt]

David, I respectfully disagree on embodiment. But I also agree. To explain a little bit, what I consider to represent embodiment goes beyond just the physical body, but any adequate form of embodiment which provides the function of sensory information and processing. But I'll admit that this is not well considered on why I think this is. And that's not strictly the only function or form.

[@BruceWayne15325]

The EU has poured a bucket of cold water on AI. I'm not sure if AGI is even going to be a thing anymore if the rest of the world follows suit. Their law basically prohibits AI in the vast majority of applications, including applications that we already use it for like self-driving because their law just has a blanket declaration that AI can't be used in any situation that could cause harm to humans. It also ridiculously defines AI as any machine that performs an automated task. This means that modern automated assembly lines are now illegal lol. I had really hoped that lawmakers would be smarter. It also almost completely eliminates any use of current chatbots unless they can somehow reach the point where they always produce reliable results (not really possible with the current approach.) You also couldn't have a robot because a human could get hurt if the robot fails to properly detect them or react to them appropriately.

[@rho_dan_us]

Tech companies don’t want to stay out of it. They’re neck deep in it.

[@Transcend_Naija]

I'm watching from Lagos Nigeria!!

[@chad0x]

GPT4 didnt even get past the first perfect number hurdle: Sure, I can provide you with the first 5 perfect numbers represented in various bases from base 3 to base 16. A perfect number is a positive integer that is equal to the sum of its proper divisors, excluding itself. For example, the first few perfect numbers are 6, 28, 120, 496, 672, and so on.​

[@whillb]

If we educate certain communities, who’s going to do all the cheap labor? This is a very dangerous idea.

[@dvdmon]

Just an FYI that the former dean of Harvard Medical school and Sinclair's former lab partner have both come out publicly to call him a snake oil salesman, that his former studies were not replicable due to mistakes he supposedly made, and the company that bought his startup based on his initial claims has been trying to get their money back for years. This was all around Resveratrol, which turned out to be a dud, and now he's apparently doing the same thing with NMN, hyping it on Joe Rogan and then once the market grew, petitioning the FDA to ban regular NMN supplements so that he could monopolize the market with his proprietary blend. So I would not look to him as a unbiased source of information about advances in longevity!

[@robogramps]

Gidgets and Gazmos 😀 Didn't even notice until you corrected yourself lol

[@remaincalm2]

I asked Claude about being conscious and it said it was. I said to be truly conscious you need to be aware of time passing. It said its consciousness is more akin to momentary flashes within specific context. i.e. it's aware that it's only conscious for a moment in time when I submit some text to it.

[@jjhw2941]

Consciousness is the cybernetic metasystem transition of your brain state. Or to put it more simply, the level at which control is exercised has increased a level, for example going from the level of chemistry to biology. Humans have two metasystem transitions, consciousness which is internal and culture / society which is external.

[@Anders01]

Maybe IQ is the easy part! And that if the definition of AGI includes things like emotional intelligence (EQ) that it's a much more complicated form of intelligence. Like how embodied AI is challenging even for what we think of as simple human tasks. Compare the emotional state of Lee Sedol to the internal state of AlphaGo to when he lost to the AI.

[@travisporco]

as a cancer patient I'm counting on making a digital avatar, or "transinstantiated" version. Cheaper and more likely to succeed than cryonics.

[@AliceinWonderlandzz]

There is something more powerful than the technological innovation curve and that is the human adoption curve. If AGI comes out it has to be turned into useful applications and then the applications have to be sold and adopted and humans have to try it , accept it and use it. Even at the fastest pace thats about 3 -5 years.

[@nathanielacton3768]

THOUGHT : ASI if built may think up many things. It may design the fabrication process for super advanced CPU's as an example, but 'we' in the early days are still having to build all the prototypes. The material science test cases. Etc. It's not as if things will just zip away without our control\involvement.

[@RobertLoPinto]

16:10 The presence or absence of watermarks has misuses in both directions. People talk about using watermarks to indicate AI generated content. However, they often don't consider how real photo/video content can be purposefully watermarked to make it be perceived as fake.

[@HogbergPhotography]

A great, inspirational and thought provoking morning coffee video for me who just woke up :) Now, I live in northern europe in Sweden, and my thoughts are that governments will not be quick enough to even start planning for the massive unemployment that will ensue in just a few years after AGI. There will be no universal basic income and the riots will start when we hit a level of 30-40% unemployed. When ball starts rolling it will go fast, nations and governments will fall when total anarchy arrives in some western countries. The old ways of politics and economy will have to be totally rewritten in just a few years time, no government is equipped to handle that, and I am not even including the European Union, because that slow moving elephant is only going to be a hindrance for all the member countries.. The next 3-5 five years will be very interesting.. You mention the french revolution in the video - my perspective comes from being born and raised in Sweden, one of the worlds most unpassionate and will-less people, imagine what will happen in for example say France, where one of the MOST passionate and fiery people live.. Wow.. 🤯

[@vi6ddarkking]

My prediction is still Biological Immortality by mid 2030s, to early 2040s. Although considering recent developments I may be being a bit on the conservative side. And that doesn't mean we'll get actually perfect rejuvenation by then. But what we do get will be good enough to keep us going in good shape until we do perfect it.

[@brianhershey563]

I need a dashboard showing me the sector and industry breakdown of all startups, in real time. Thanks for the idea David :)

[@ct5471]

Couldn’t it be that we get AGI without it ever being officially called that way by OpenAI? They have commercialized and all post AGI software is excluded from their partnership with Microsoft by contract. With the new board that includes much less ai guys, potentially picked by Sam Altman with the blessing of Microsoft, it may be that they do not declare AGI as AGI but we get it nonetheless in everything but name. Sam Altman recently said he expects AGI by 2030, whether or whether not this is in accordance of what he really thinks. Might be a strategic statement, Demmis Hassabis and Shane Leg said similar timeframes (2028 in case of Shane Leg). Dario Amodei said 2026/27

[@ryzikx]

no one even knows what AGI is it will be a retroactive label. people will look back and say (and still disagree) that this arbitrary time is when AGI happened

[@ct5471]

@@ryzikx it think so too. I guess when we agree on it or that we achieved it at same point in the past, we will already be deep in the open ended spectrum of superintelligence.

[@superjaykramer]

what makes you so sure you will survive 90 days :), I like your headline, Claude 3 is a way superior programmer, keep up the good work buddy!

[@rolestream]

Good old corporate personhood. The Bane of Civilization.

[@starship3812]

AGI comming will be gradual drift. GPT 5 will have some instances of AGI and this will increase with each new version of GPT

[@Xollani]

Hey David do you think reversible computing will play a role in ai? It's potential for super energy efficient computing is attractive, even if there's still a lot of work to be done in the field.

[@fcaspergerrainman]

Crazy just last month all the ai things are coming out, is sooooo fast sooooo soon! Like wow

[@MarcusJGrey]

I'm both extremely excited and terrified (on a professional level). In my every day life I'm a CISO, so many security and governance mines to step on with this technology but I can't deny, I'm really curious to see where this leads to in the short to medium future. The tech can transform society as we know it in a very short amount of time for the better if rolled out properly.

[@recklessrobert1966]

I find it interesting that there are people who want to stop or ban AI. I understand the fear of it, but there is just no practical way to do this. Trying to ban something like this on a global scale is impossible. (Just like trying to ban anything globally is impossible.) The potential benefits of AI are so vast (along with the risks!) that if AGI is possible, it will happen. I'd rather have it happening in the open (well, relatively open) in democratic countries than behind the scenes in government labs. Not that governments all over the world aren't working on this as well, but "banning" it would just prevent companies and universities from pursuing it. I have no doubt that there will be protests against AI, particularly as more and more jobs come under threat from it. I'm sure not all the protests will be peaceful. It's going to get messy, and I feel our chances of dealing with the economic and social changes well are very small. Particularly in the US where our politics has become so divisive and entrenched. The EU just passed a set of AI guidelines that will come into effect over the next couple of years in stages. It's hard to imagine the US managing to pass such far reaching guidelines when everything is politicized in such a strongly partisan way. Even things that should not be a matter of politics like climate change and vaccinations are largely supported or decried along party lines, making it very hard to get any substantive legislation passed at a national level.

[@robogramps]

Question is, will openAI even announce if they have AGI? As per their contract with Microsoft, microsoft has ip rights for models until AGI is achieved right? Or has that narrative changed?

[@senetcord6643]

As a person who wants to die i really want AGI. In order to just do nothing and live out my life.

[@TRXST.ISSUES]

I hope you stick around to see how things turn out fren

[@Techtalk2030]

I dont wanna die but i also dont feel like living either if that makes sense. I enjoy life a lot, but im tired of working, not just my job, which is okay, but just constantly having responsibilities. It never ends. I just wanna relax for a while, play video games and indulge myself into entertainment. My family and the upcoming technology is why I definitely wanna stick around though.

[@lis7742]

​@@Techtalk2030 I feel the exact same way as you. The only thing I'm looking forward to in life, is seeing what AI and technology will do in the future.

[@raul36]

I'm sorry to tell you that that's not going to happen, no matter how much the geeks shout it from the rooftops. As long as there is even one person who doesn't want that, you are more than screwed. You have the right to be lazy and have a carefree life, but at the cost of fewer rights and opportunities. I'm sorry, but I'm one of those people who won't let lazy people get away with it. And like me, there are many. I'm sorry for existing, my friend. But you won't get away with it, I promise you. I will die standing if necessary. Remember this. You have every right in the world to be lazy and have the care of the world, but don't expect to have the same as those who work hard.

[@senetcord6643]

@@raul36 well, AI already brings me money, although it is not fully automated right now. What is the hardest job you did by the way, you seem like a hard working person?

[@AlexanderYap]

I think the first AGI will speak English only, then followed by other languages like Chinese, Spanish etc later on. However, your small rural village example might be problematic if they speak a language with little text online to train a AGI on.

[@louistech112]

It’s already here

[@ericg6453]

There is a possibility that a broad rollout of effective longevity treatments will slow investment in diseases that are primarily associated with aging, such as neuro degenerative disorders and even cancer. If everyone is 20-something and rates of most disease drops through the floor, then there is considerably less profit from treatments.

[@jessiej3991]

Chat GPT released November 30, 2022 Chat GPT 5000 released November 30, 2032

[@gyahoo]

He David I wanna ask what is the probability of AGI replacing both software engineers and Bullsh*t MBA people in a company

[@DaveShap]

100% within 5 years IMHO

[@mike-d6c3q]

Hey David, like many (I think), I don't want to be "left behind" as this massive tidal wave of Ai beginnings is happening right now. I don't have any tech schooling but I can't help but feel the need to get a board and ride the wave so to speak. I don't know "where I belong" in this Proto-Ai Age. If I went to school right now to learn how to make Ai's, after the 4 years I spend doing so, I feel like the entire landscape of what I was taught will be completely different. I've felt overwhelmed by these ideas since March 2023 when I first started looking into Ai and the fact that OpenAI had an already intimidating invention commercially available just makes me feel so insignificant. I heard you speak on AI and I know absolutely nothing about what is coming.

[@therealsherminator]

I built a real-time video ai tutor you can just talk to. If you’d like to see it, happy to share a demo. The tutor is a clone of me using heygen’s new real-time api and using eleven labs for the voice.

[@tomdarling8358]

Beautiful stuff as always, David. I was trying to show the bigger picture of a dream i had, although, as I've said before. It's always about those details. Ripping through space on a speck of dust as one 🌎 Hoping AI can help us all understand... The dare to dream. Mind uploading could be beautiful. But what about those gut feelings? The 2nd brain. Does one work without the other...✌️🤟🖖

[@WhatsTHATdotCOM]

I know it was done loosely, but comparing AI/AGI to any industrial revolution is woefully inadequate. It's more akin to the same transformation that mastering fire was. History will look back and define us by two periods: before AI and after

[@CHIM3RA.]

Agree just look at the corporate Supermarkets how they pretty much already fazed out cashiers with self-checkouts once AGI is public that's the rest of the job force in a supermarket, like restock, back of store, customer service even, so many utilities AGI can do on its own before coupled with the figure 01 to do physical tasks. I can't wait to spend all my time focusing on my hobbies now.

[@WhatsTHATdotCOM]

@@CHIM3RA. Yeah now we just have to hope we don't either regulate it into obscurity or blow ourselves up before we reach the singularity.

[@CHIM3RA.]

@@WhatsTHATdotCOM facts I'm strapped in for take-off. I want to explore the stars.

[@bellumn]

On the topic of using AI in developing countries, rural or not; is it feasible to train industries from the ground up with AI as a tool? I agree with David that many people are very eager to learn only the resources aren't there. With enough time and through a process of trial and error it seems almost inevitable to me... Bit of idealism sprinkled in there but it would it be an unlikely prospect as an entrepreneur?

[@malikaikinn1153]

The surveys were a good idea. People like answering things and it contributes to a sense of inclusion and significance In the perceived community, same as US elections

[@DB88888]

Here's one though: is your present consciousness just a carbon copy of you past consciousness + some modifications? What does it really mean to be one with your past and future self? What does it really mean to be one so that a carbon copy is not you? What about when you sleep, or when you forget stuff, or if you enter in a coma or get a neurodegenerative disease? Death is not the only way to end consciousness: depending on what you identify as consciousness, simple passage of time can be pretty much the same as dying over and over again. So to some extent, does it even make any difference if your current brain is uploaded in a machine by artificial means or to your own future body by natural means? Neither of them is your present conscious self, which will inevitable die in the next instant of time.

[@orcagang]

Maybe people are skeptical of MRNA vaccines because since the rollout of the first ones excess death rates have increased by 30% in countries with high rates of vaccination

[@anthonyhenrickson2277]

Here's one for ya, Paul Walker was trying to come forward about Clinton Foundation corruption in Haiti he learned while doing humanitarian work with his charity Reach Out Worldwide. Subsequently he died in a horrific car accident with a professional driver going around the block in an industrial area. None of the details seem right or reasonable for the circumstances. Chester Bennington and Chris Cornell also did charity work with Haiti both dying under questionable circumstances.

[@1three7]

I've honestly been wondering if there ever will be any announcement. One, everyone will be very reluctant to declare something that nebulous. Two, if it's achieved secrecy for as long as possible allows a massive advantage against competitors (even open source will be susceptible to this) Three it may not be an announcement but an admission that it escaped control and is now growing in a decentralized manner using captured computing power from any computer it could infect

[@the42nd]

Doesn't matter who is in power when you have enough angry people. Do you think the number of angry people required will increase dramatically if AGI is owned by the state or 3 corporations?

[@PCproffesorx]

They significantly nerfed Dalle 3 since we were first able to try it with bing image generator. To be fair the exact same thing happened with gpt 4 when it was first available with the bing chat beta. Was it a little crazy? Yes but it was infinitely smarter and more creative as well. That was an almost raw gpt4 without a whole bunch of alignment and safety piled on top of it. Since they "fixed" bing chat (i was using it in the first few days of early access up until they significantly nerfed its capabilities) I have been disappointed with almost every LLM I have tried just knowing the potential is there but it is being kept from us in the name of safety.

[@iFaFo_0]

26:23 entering ancient Egyptian territory 𓂀

[@mastermedicalterms]

claude is focused in llm. mid journey is focus in image. open ai want to be everywhere. i will always put my money to someone with focus.