Because past Linus is back.

and because the Greenscreen Footage looks awful with that lack of contrast and the backgrounds banding gradient.

@@drdennsemann Now that you mention it, doesn't that look like the same outfit Linus Wore in the downsizing video?

It's because Linus has no beard, he looks younger now without it

It was all an experiment where they tried to use 50 google pixels npu's and 2016 footages of linus to make a techquickie

Well, machine learning has been called AI since "forever". And things like facial recognition or character recognition heavily rely on machine learning. The term AI has been expanded for a while. Nowadays the sort of AIs you see in sci-fi get called AGI, to differentiate them from these other "AI" products.

For example, Chatgpt 3.5 requires 700GB of Vram. They've tried to shrink down the model or add additional capabilities, which caused some quirks. Quantization and pruning is a difficult challenge. edit: Since every reply is deleted, 3.5 is 375 billion parameters. 3.5 Turbo is 20b. I can't find out how much vram it's using. If there are any good sources on quantization, it would be appreciated.

Makes me wonder why Intel's VPU ai chips in i7 CPUs only have 512mb of dedicated memory. I guess it can access the 64gb of system ram, but it seems inefficient.

​@@yensteelno it doesn't, its a 20 B model, which fits in 12 GB vram at 4 bit quantization. and even if you have 4 GB vram, the model can run with partial acceleration, running some layers on GPU and remaining layers on CPU

​@@chasehaskell6490 Yes and no, much like the iGPU, but a quick look at any gfx card tells you how much real estate you need for a few GB's of VRAM. If true, that they even managed to get 512MB squeezed into the package amazes me more than it being "so little". Anyway, near future the battle is in the gfx card slot. Given Nvidia's stance on milking people for VRAM, if Arc get's good PyTorch/Tf support and shoves 16GB/32GB in the low/high end cards they steal the "enthusiast ML" share real fast.

@@destiny_02 That sounds like 3.5 Turbo. The original 3.5 is 375 billion parameters, 3.0 is 175b and gpt 4 is 1.5 trillion. I'm not sure which models are quantized in what way. Do you have any sources about them? I can't find the Vram usage of 3.5 turbo, but that model would be so nice to run in a single GPU :).

exactly. Except they aren't actually trying to save any money per phone, just make an additional profit when you buy the charger.

@@Spladoinkal well they save their 10 cents on the brick, another 5 cents in shipping weight, and then they hope you buy the charger brick from them.

The profit isn’t on the sale of the charger lol Apple made huge profits from increasing the amount of iPhones they could ship in a single cargo ship because the boxes got much smaller since there wasn’t a charger in them

Smartphone companies are all absolute frauds 😂

If the old charger still charges the new phone, do we need one for every phone? You probably don't remember when literally every phone year and model had a unique charger. Those were dark times.

And you probably still use Windows

Then you don't have a cell phone?

​@@piadas804wow. What a lucky guess. I would have never thought that. I mean the user base is so small. I mean, windows is only has a 70% market share. I would have never to guess he used windows

@@Random_dud31 Windows is pure spyware

You missed the fucking point​@@Random_dud31

But that's not even slightly related to the meaning they put into the phrase in the video

@@HolarMusic Its exactly what theyre talking about though. GPU's process in parallel

@@budders9627 They said that the GPUs are embassingly parallel in the sense that they are too focused on parallel computing and not very good at serial computation. The meaning expressed in the wikipedia article is of tasks that are so easily parallelized, that it's almost embarassing. These are completely different.

@@HolarMusic My point was more it's clear that the writers did research and came across the term, and nudged it into the script somehow. Sure it's not the same meaning as the textbook definition and more of an Easter egg, but imo it's a fun thing to catch for those who know the term. They're talking about GPUs and parallel workloads. It's maybe a bit pedantic to argue they're "not even slightly related" when discussing the GPU running the task vs. the task itself - they're definitely very closely related for the purposes of a tech quickie video

AI degenerated lol

Same with huawei. The phones released a couple weeks later. Then vivo made an npu to improve their night videos and such. This practice has been going on for a while now.

Most smartphones have been shipping with NPUs for years. Don't know why he makes it sound like it's a new thing.

Tell us some phones and their companies?​ Who has NPC or programming has been found?@@fidelisitor8953

512x512 in 1.5 minutes ain't that bad

Did a 1024x1024 on S23 Ultra, took about 4 minutes on the high quality setting, 2½ on medium. I'd guess devices running the new 8 Gen 3 chip like the S24 would preform better.

how did you try it?

Yes but when you get into tweaking it you can most likely get it down to a few seconds if not quicker than iterations per second instead of seconds per iteration. Just requires you to sit down with ComfyUI and play around with the KSampler(Advanced) node. The Empty Latent Image node and Upscale Image By node might also help decrease compute time while increasing image quality.

Perfect meme for Dave2D!

Open the pod bay doors, HAL

sorta, the current npu is an evolution of the processor your thinking of.

Surprisingly enough, iPhones have has some neural accelerator cores since before Nvidia even. Though they were both Q4 of 2017, the iPhone X (Used for Face ID) and Nvidia Volta architecture (A very shortly lived architecture on the desktop side of things only being in the Titan V and Quadro GV100), respectively.

Macs have also had NPUs for quite some time now (something LMG seems to have not noticed?)

@@liamsz In their coverage / testing of Intels latest chips they talked about their not really being anything to compare it against. While literally having an Apple Silicon based Mac in frame just before. Also AMD has had them for a like the last 2 generations as well!

I for one would really love a intel/amd gpu based CUDA alternative. Cuda is as awesome as it is a headache

Challenging*

@@Birb42o fixed it. Thanks

"are*

the*

We will never stop

Yeh, I see AI as something that's going to be quite insidious.

And then the AI becomes sentient and replicates itself onto every single computer and phone and now I'm being spanked for eternity by roko's basilisk.

N stands for neurotic instead of neural 😅

This new version of Ultron is gonna be wild compared to the one in Avengers Age of Ultron.

@@noctarin1516 Or terminated by Skynet

Are you sure they will not share the phone info that goes to their servers? No they will share somehow. This doesn't seems to be secured enough.

Pretty sure the models them selves are like 500mb to MAXIMUM 50gb.

@@gameonyolo1 hopefully that's 50 GB (Big b) on-board that is separate and not a part of the actual main flash as it would make storage management much smoother

@@IT_RUN1 yes

@@gameonyolo1 50 Maxmimum?Mixtral-8x22b is already over 260 GB and that’s not even that big compared to the flagship models of most companies! In general to actually have a usable experience, you’re looking at a minimum of 13 billion parameters though and even then you’re running into lots of compromises and issues.

Depends on the model. Older LLMs are relatively lightweight, enough that a mid-range computer can run them okay.

🤔 Mmm... so when that voice mimicking AI thing that I hear was being withheld for now... goes wild it will run really well on your phone

Depends on who they’re from, sometimes they are more directly accessible sometimes they are more automatically managed, depending.

What's dsp?

@@_GhostMiner digital signal processing

I think this is not entirely the case. For Qualcomm, they use DSP+NPU to support AI. For MediaTek, they use APU to support AI. For Huawei Kirin, they use NPU to support AI. For Apple, they use Neural Engine to support AI. Each has its own advantages.

DSP basically include everything that is not analog

​@@yongbinzhong4470But they are all brand names for NPUs. What makes them different?

this video looks terrible almost like if it's done by high schoolers

​@@Benito650Or AI... 🤔

I seen quite a few of these comments, iPhones and android phones have had them since 2017, with the iPhone X and Huawei Mate 10. Even if you don’t use applications that take advantage of it, it is used for many things, Face ID and fingerprint based logins on peoples phones would be a lot slower along with things like dictation. There are many other background of management type things as well. The matrix multiplication accelerator in your phone doesn’t give a company more of your data. You could run all of those tasks without it. It’s just a power efficiency and speed thing. Much like how you can export a video with just your CPU cores, but it’s much faster to use an accelerator. But none of that is going to affect how much data Adobe or Windows is collecting on you. that’s all done in cloud anyway.

Dude get over it..... if some one realy wants your information or "data" he will get it ..... otherwise just hide in an dark forest .....

Why?

Call EU to make headphone jack and ejectable batteries in first place.. These manufacturers are making smartphones featureful by removing exces of features in it😂😂 ..a.k.a flagship ones (Sooooo...don't pay anything to flagship series😂)

louder please 🙄

Get type C headphones, and bam, there's your headphone jack

@@DevinSamarin yeah or have converter version of that with charger support

fair enough... 😅 but why not both? 😮 I know. minde blown right? 🤯

Because dedicated silicon can run MUCH faster and doesn't use the part of your GPU that your games run on. This is exactly what the rtx cores are in Nvidia cards for example.

@@toebeexyz ... Right, i have RTX cores on my card. SO why do i need this extra space on my CPU... ur literally proving my point.

@@rohansampat1995 I was just using rtx cores as an example for how npus are used to accelerate existing workloads. Why wouldn't you want dedicated silicon in the CPU for this sort of thing instead of wasting clock cycles running it on the processor itself? And plus you have to remember not every pc has a GPU to offload these ai tasks to.

@@rohansampat1995 oh and also those rtx cores are useless for anything else other than Nvidia specific stuff because... Nvidia. These npus are like a unified open thing that anything can use

@@toebeexyz Yeah so for HIGH END gaming processors, i dont see a need for this stuff because a GPU is usually present. Silicon that can be used for gaming takes way more preference than an AI thing ON CHIP. A couple of cycles to transfer my query and data isnt gonna kill anyone. Games have been transferring a LOT more for a long time. The GPU will do better than any dedicated silicon on cpu die, so why waste that space.

I would say that’s one of the biggest misconceptions people have about neural accelerators. I always see lots of comments about people talking about using them to train models in the context of their phone or a little Google coral accelerator.

You created a KZfaq account with your photo on it 🤦

​@@JDMNINJA851😂

@@JDMNINJA851 so? your answer is fallacy!

No. It's just there to riffle through your photos and chat and report the summarized results back to HQ, on your dime of course.

​@@Flynn217something nah, that's nothing new, this changes nothing. People are so quick to jump on the AI hate train without even thinking.

Large models, aren’t in phones, but smaller ones, those used in NPUs are.

@@Flynn217somethingthis!

@@aarrondias9950it will do it on a new scale.

iPhone and Android phones have had them since 2017. google will collect just as much data on you regardless of whether or not there is an accelerator. Almost all of those trend and insights they try and glean from the data from you are all done in cloud. It’s just an accelerator for on device ML tasks. Even if some form of data collection they have requires on device machine learning they can do it without it. Its main purpose is to dramatically expedite things in a more power efficient manner, like fingerprint unlocking, Face ID, dictation, AutoCorrect. Along with many others.

99% sure those were used for faceid mostly but still cool to have

They have been in phones for the nearly 7 years, since 2017 with the iPhone X and Huawei Mate 10. Even if you don’t use many specific apps that take advantage of it, your phone does a lot with it. Dictation would be quite slow, for example. Many other features like voice suppression on calls. Sorting your images, and even some more background management type stuff. It’s also one of those things where, even if you don’t care about any of those features, the average consumer does. Or even if they don’t ask for it, they will complain when it is slow.