This is NVIDIA’s new GPU 

They don't call him Linus Drop Tips for nothing

Since they are bare dies, I'm pretty sure, there is nothing there to break.

the way that Yvonne rushed in lol

In hospital, probably

Lol wife to the rescue 😂

Maybe a new house my guy.

no you don't

@@dzello damn, it wont fit

No, a new house

Nah bro for new gpus you need to buy a new country + planet to barely fit this thing 💀💀💀

so it processes giants... love it.

Nah; that's an AI produced monster that will surely lead to our downfall within a few integrations in the near future..

@@51Archives And that is what we want, our downfall, after all we all have to die eventually, if we die as the last humans in hisotry then we are special.

The G’s for “Grill”, right?

No all you have to do to survive is have Linus drop it on purpose or take off the cooling and turn it on

The amount of power these use is less than what was used just a couple of years ago, and the next generation will use less power too, so you'll eventually have the computer power required for chatgpt in your desktop.

@@pcmason great explaination ngl

It's good for global warming predictions. Switch it on. Boom. See - I was right.

Genius

@@pcmason you already can have it with GPT4ALL. It can run on your cpu or use vulkan, opencl, cuda or the M series of the macbooks and it is pretty fast if you have a gpu with 6 or more gb of ram

underrated comment !

Next is Exaflop followed by Zettaflop FYI, if you care to know. The Russian military is already a Z-Flop.

its kinda funny cuz a flip-flop is also a computer thing. but 2 flip flops is like 2 bits of storage so not very impressive

How many petaflops in a flip flop?

XD

Isn't that technically what their SFF certification is?

​@@DajovaI mean I would want a case with actual cooking so a radiator case that's just a GPU that I could hook my water loop into the case so maybe we could have a chance to watercolor the RTX 50 cards

yes. a lot of stupid people would buy it

Sure it's fast but can it run elden ring?

@@bluflame5381 This I dream about powerful PC yet I probably would just still stream RU-vid half the time and play Elden Ring/Battlefield and Cyberpunk the other half... Which runs fine on my 4060.

Lmaoo

And that will not change anytime soon I think.

I mean,... you would have to probably cover the whole world with 'super' computers of old (Zuse anyone?) and wouldn't have a faction of calculation power of one of these bad boys

Computers gets compact releasing the space that could be filled with even more computers

@@GroovingDrums You mean fraction, don't you? 0o

That one rack could probably simulate every mainframe that ever existed on a molecular level in real time.

Isnt that his wife

@@mpresto15 It is.

​@@ACHonezGaming She* is

@@gonthyalavishalchandan1193 "is *that* John?" "yes, *it* is" That's a common type of exchange, most people don't wanna be referred to with *it* or *that,* but it's common to use those pronouns in this specific case, I'm sure no disrespect was meant

Love how she rushed in like she was thinking "WE CANT AFFORD THIS DROP LINUS!!" 😂

IT WOULD HAVE BEEN A MASTERCLASS if the cameraman had rushed too dropping his camera.

‘Sorry Linus, you pay me to film you and not to catch stuff … got a solid clip tho bro’

It feels like there's linus clause for tech companies.

@@grze149 so,Top Gear/Grand Tour Hammond similarity? :)

I bet he has to take out a policy every time he does these kinda projects.

i wonder how powerful it'd be if nvidia could actually build a single gpu which is built out of like 1000 blackwell superchips that would fill up multiple rooms. And i wonder what we'd be able to do with such thing...

I mean, almost? These things are meant for datacenters, so you'd have dozens or hundreds of racks like these, all connected with extremely fast interconnects. That's almost like having a GPU the size of a building.

YES! The "Nvidia Univac"

@@SimplCup You also had to build a nuclear power plant next door, just to power that thing!

IKR. I was noticing that the boards were the size of VLSI PDP-11 or VAXen boards... All hail the return of the vector-based supercomputer.

my room is 11 degrees celcius right now so if only they could somehow route the excess heat to my home, then the problem would be solved

ikr? isn't she korean?

They did great! - LS

Now what is this going to mean for the 50 series..boooom

at first i though what jake doin standing over there now i know, haha

so thats what she was doing there. I kind of wondered why she was just standing there.

Great content well made

Linus Tech Tips brought to you by NVIDIA.

probably in debt

Linus drop tips

I mean, he's said many times that LMG wouldn't exist without her. That was just the latest example of why lol.

She looked extremely ready to react and I'm guessing that wasn't staged :)

Key words US

We got DX12 and Vulcan...... That either no one bothers trying to use, or no dev bothers doing the "less work than back then" to enable..... Gimme back SLI / Crossfire damit!

Well hopefully amd is cooking up something

It sucked and nobody used it anyway...

@@littlefrank90 TF is "nobody?" Speak for yourself 🤣

They were ready to hold it

@@xugro I think you mean catch it, which they did. Because again, Linus is Linus.

Catcher

wait, what happened the first time?! Lmao

@@Aonoexorcist100 he dropped a 3090 during it's review... C'mon it's not been that long.

duct tape them together

you mean 50?

I believe in Alex

You're gonna need some real heavy gauge wires for that (and ideally at 240v)

@@ZaHandle Just use those industrial red power plugs. Youll need at least one of those for the rig if not more. That puppy can supply over 300,000 watts. Psu? Who needs that crap just plug it straight into a nuclear reactor. The rack likes raw unfiltered energy kappa.

Hades had 200,000 lines of dialogue alone. Putting that amount of text into a custom-trained AI model is going to give far superior results than using ChatGPT.

@@p_serdiuk For now

@@p_serdiuk I just googled that and you have an extra zero there, it had 20,000 lines of dialog. Still impressive but far short of 200k.

@@p_serdiuk I don't know about you, but when playing Hades I didn't think "Boy wouldn't it be cool to talk to these characters myself". I trusted that the writers had written better dialog for the main character than I could roleplay anyway, which negates the need for any AI modeling. I'll give you that "triple A" studios will probably run with models like the one presented in the video, and who knows, maybe some of these games will even be decent. But rest assured these aren't going to be written by superstar writers, or even indie darlings. That's going to be outsourced to the lowest bidding contractor, and I don't think it's going to be what makes a game really stand out.

@@screwaccountnames I mean, you're conflating entirely different ways of interacting with the world. Do you also hate being able to control your movement freely, or would you prefer to go back to point and click gameplay? Surely the art designers knew what the best angles to view the world from were!

yes it sure will

If not just return it, someone will appreciate an open box deal.

LMAOOO 😂😂😂

If you use the chip as a side panel maybe

yes you just need apple's hydraulic press

The ideas and techniques being used in this business grade technology will, in time, become consumer level technology.

at least they managed to dunk on Microsoft by having it on device

@@RFDN0 I can`t wait for 10KW GPUs

It is gamer related, the moment Chat GPT 3.5 came out it was immediately obvious to me and millions of others the gaming relevance. It took all of 2 weeks after the API was released for there to be a mod that allowed Skyrim NPC's to talk back to players, a research paper was launched in less then a month demonstrating a couple dozen AI agents communicating and coordinating in a simulated gaming village. It wasn't long after that you had AI tools for gaming and art hitting every major development platform, and they are already in use making voices, creating sounds, textures, and thats not even touching on the more direct usages that existed in DM's and tabletop creators using these directly to help them craft campaigns, plots, dialogue, and more. The biggest limitation was that the very earliest models weren't yet refined well enough to do rapid inference in real time on consumer level hardware. That's pretty much already done now, these giant data centers are used to train these models, and train them so well and so efficiently that they can increasingly run on ever less power for inference, and while that's happening we're starting to get specialized hardware for AI utilization integrated into our GPUs more and more on a consumer level AND that's not even counting the release of consumer specialized AI hardware that is starting to be made and may be commonplace in a decade or so. I would venture a guess that interactive AI will be commonplace in the gaming industry for all NPC's in less than a decade, and that's not because it can't happen sooner, but more because the major triple A titles being released in the next 4 years are already in development, and AAA developers are too risk averse to be early adopters on unproven tech, so you will probably see indie releases utilizing this tech in about 5 years, and the AAA variants 5 years later. The fact that we're in prototype stage from the hardware designers now doing the demos is proof that while the tech is ready, the industry is still lagging behind like it always does. But... suggesting its not related is a bit off, its obviously related, its just still a bit far out.

@@dragoonsunitecan’t wait for a future where games are so boring and un-artistic because every NPC will be as boring as the average dude at the bar.

And will only hit 20fps in Minecraft....

That'll likely already be around 2035

i bet we could still crash it using tnt or redstone.

🤣🤣🤣🤣

Lol. 2050? Don't think the world is gonna be in a good enough shape for that my friend...

Minimum requirement for GTA6 720p 30 fps

@@hannes0000 seriously, that's what i am wishing to play gta 6 at gtx 1080

With how optimization has been going the past couple of years. I think you're going to be lucky to get a solid 60fps Using a 5090 at 4k.

Just put a ps5 or Xbox series s/x console cause it won’t be out for pc day one but for console it will

​@@hokahn6313you def will buy it

But can it run Crysis?

The cost of power per compute has been greatly improved.

I really hope it's renewable

@@Safetytrousers Sure, and if all you do is play games with the exact same framerate and graphics settings as before then you'll use less power. But people won't do that.

@@Safetytrousers that's gonna create more demand and gap in the AI training market so there's that too

Our AI overlords will apparently win through creation of ecological collapse.

because it didn't. you're either viewing this on a Nokia phone from 2004, or half blind. his hand would even dissapear every time he waved it in front of it

I was searching for this comment

Nvidia enters the SFF market

He said with the last demo that it supposedly runs on device (no data is sent anywhere)

then you pick Linux and a non-AI bs GPU

Have you tried turning off your internet

@@frankhuurman3955 or better yet, pick nothingness. Maybe now u're not forced to use AI, but sooner or later u would be. At this point someone should amass a "no tech" campaign, since pretty tech nowadays are the same -- making you rely on them.

Gougable pricing utility.

This makes much more sense than it should. Rip GPGPU.

He doesn't give a shit about you or any home user. He's got almost a laser focus on the datacenter. Sales of gaming GPUs are just the cherry on top of the cake for him.

@@arnox4554 I mean ngl, Datacenters has more purpose than games.

You can’t be serious with a comment like this.

Everyone and their mom knows the 50-series is launching this year. If you spent hundreds of dollars on an upgrade without researching that, it’s on you.

@@trapical My mom doesnt know that

@@trapical I didn't know you are able to read people mind trough your monitor.

@@trapical Comprehension isn’t your strong suit. You literally took my words and made them mean what you wanted them to so you could argue. Try reading again… slower… and see if you come out with the same result. L

lmao i bought my 4090 last week as well. its so sad...

I wonder if that would be enough to passively cool a 4090

But effectively useless unless you have data centre level airflow generators

*Segway* Two-wheeled, self-balancing personal vehicle. A Segway is a two-wheeled, self-balancing personal transporter device invented by Dean Kamen. It is a registered trademark of Segway Inc. It was brought to market in 2001 as the Segway HT, and then subsequently as the Segway PT. HT is an initialism for "human transporter" and PT for "personal transporter." A lesser known fact about Segway is that the company's previous owner died when he fell off a cliff while riding a Segway, kind of ironic. Those things aren't safe, let me tell you. Also, the word you're looking for is 'segue'.

Moran

@@TriggerHippie🫡

It's almost sounds like an audio glitch, it was so well timed. I kept scrolling comments till i found someone who agreed, lol

Nono he would say "I'm gonna have to tell you.. about this segue to our sponsor!"

Jensen: 😅

Simple, MS Winblows used to run like ass on ARM and Nvidia is too dumb for everything else (and burned all goodwill so no one else will do it for 'em).

they make ARM chips because they don't have a x86 licence so they don't have much choice

I mean they have the Shield as a standalone product, along with their Jetson series to some extent. As for selling bare CPUs, there is no standard platform yet on the market to my knowledge. So you end up with proprietary junk on Apple side for consumer Arm, and more proprietary junk on the datacenter space from Nvidia. AMD and Intel are in no hurry to move away from x86 yet. Nvidia and Apple both love money so I don't see how Arm PCs are gonna happen anytime soon. Kind of a shame.

They are going to, in a partnership with MediaTek, it's supposed to be a snapdragon X elite like competitor. Is expected around end of year or 2025 (don't quote me on these numbers, I don't remember it too well)

They have had ARM SoC's for well over a decade. For example the Nintendo Switch has a NVIDIA Tegra X1 from 2015

too bad he prefers mini itx cases

Oh my

​@@ech 😂😂😂😂😂😂😂 this got me dying

@@ech nearly spit my drink out

Lol​@@ech

That's what a firewall is supposed to do. Block everything and from there you allow only what you actually need.

@@DJDocsVideosmost people have no idea what they need to allow and would click yes on any water falling green text app that requested it

are u certain they have the same functions? i'm just checking to make sure.

@@tor13128 Neuro will make jokes about whats happening in game, she insults peoples gaming set ups within moments. shes a personal buddy to the creator, and hes just one guy. before chat gbt was even a thing

@@novadestry i was mainly wondering if the ai in this presentation are using more advanced stuff or not. for example the clip where the ai can react to moving game footage. i'm not sure what else the ai does so i was wondering if neuro is indeed doing everything it can do and more. i was just wondering how an entire company with lots of budget still can't make something equal/better than 1 person. that would be quite shocking and they really need to go back to school.

AI can only simulate so much. Actual bodies aren't... as straightforward and will still need clinical trials

🤣🤣🤣