Live data from Hacker News

Dell admits consumers don't care about AI PCs

pcgamer.com

381–390 of 418 posts

Re: Dell admits consumers don't care about AI PCs

#381

I don't know how many others here have a CoPilot+ PC but the NPU on it is basically useless. There isn't any meaningful feature I get by having that NPU. They are far too limited to ever do any meaningful local LLM inference, image processing or generation. It handles stuff like video chat background blurring, but users' PC's have been doing that for years now without an NPU.

I did some research on if the transistor budget for the NPU was spent on something else in the SoC/CPU, what could you get?

You could have 4-10 additional CPU cores, or 30-100MB more L3 cache. I would definitely rather have more cores or cache, than a slightly more efficient background blurring engine.

Re: Dell admits consumers don't care about AI PCs

#382

Earlier quoted context omitted.

What is with Microsoft and demanding a key for every new thing they come up with?

When had Microsoft done this before? For Cortana maybe? I can't recall them ever mandating dedicated physical keys for anything other than the Windows key, but that was over 30 years ago and I assume that's not what you're talking about.

Ah, my memory was off - it was PC manufacturers who kept adding more and weird keys (media keys, for example).

All I remember is having all sorts of fun trying to get those keys to work at all in Linux; they often were insanely setup and dependent on windows drivers (some would send a combination keystroke, some wouldn't work unless polled, etc).

Re: Dell admits consumers don't care about AI PCs

#383

Earlier quoted context omitted.

So... what was the answer?

Pretty much the same as what you see in the comments here. For certain workloads, NPU is faster than CPU by quite a bit, and I think he gave some detailed examples at the low level (what types of computations are faster, etc). But nothing that translated to real world end user experience (other than things like live transcription). I recall I specifically asked "Will Stable Diffusion be much faster than a CPU?" in my…

> For certain workloads, NPU is faster than CPU by quite a bit

WTF is an NPU ? What kind of instructions does it support ? Can it add 3 and 5 ? Can it compute matrices ?

Re: Dell admits consumers don't care about AI PCs

#384

I did use whisper last night to get the captions out of a video file. The standard whisper tool from OpenAI uses CPU. It took more than 20 minutes to fully process a video file that was a little more than an hour long. During that time my 20-Core CPU was pegged at 100% utilization and the fan got very loud. I then downloaded an Intel version that used the NPU. CPUs stayed close to 0% and fans remained quiet. Total ta…

I suggest trying whisper-cpp if you haven't. It's probably the fastest CPU only version. But yeah, NPUs likely will be faster.

faster-whisper can be faster in many cases, even on CPU.

Re: Dell admits consumers don't care about AI PCs

#385

I think the moral of the story is just don't buy any electronics until you absolutely have to now: your laptop, your desktop, your car, your phone, your tv's. Go third party for maintenance when you can. Install Linux when you can. Only buy things that can be maintained and enjoy what you have.

I got a new Subaru and the touchscreen is making me insane. I will avoid electronics in cars as much as possible going forward. It literally has a warning that displays every time you start the car: "Watching this screen and making selections while driving can lead to serious accidents". Then you have to press agree before you can use the A/C or stereo. Like oh attempting to turn the air conditioner on in your car ca…

Unless you return it and explain why, then you've supported them with your wallet, the most powerful method of support.

Re: Dell admits consumers don't care about AI PCs

#386

Earlier quoted context omitted.

I suggest trying whisper-cpp if you haven't. It's probably the fastest CPU only version. But yeah, NPUs likely will be faster.

faster-whisper can be faster in many cases, even on CPU.

Looking at that page, it doesn't seem particularly faster than whisper-cpp, except when using batches - but I'm not clear on what that means.

Does it have a command line utility I can embed into my scripts?

Re: Dell admits consumers don't care about AI PCs

#387

Earlier quoted context omitted.

I used to work at Intel until recently. Pat Gelsinger (the prior CEO) had made one of the top goals for 2024 the marketing of the "AI PC". Every quarter he would have an all company meeting, and people would get to post questions on a site, and they would pick the top voted questions to answer. I posted mine: "We're well into the year, and I still don't know what an AI PC is and why anyone would want it instead of a…

The only people who are actually paying good money for a PC nowadays are gamers- and they sure as hell aren't paying 3k so that they can use copilot.

Also professionals that need powerful computers ("workstations") in their jobs, like video editing

A lot of them are incorporating AI in their workflow, so making local AI better would be a plus. Unfortunately I don't see this happening unless GPUs come with more VRAM (and AI companies don't want that, and are willing to spend top dollar to hoard RAM)

Re: Dell admits consumers don't care about AI PCs

#388

Earlier quoted context omitted.

faster-whisper can be faster in many cases, even on CPU.

Looking at that page, it doesn't seem particularly faster than whisper-cpp, except when using batches - but I'm not clear on what that means. Does it have a command line utility I can embed into my scripts?

Batching is essentially running multiple instances at once, ie bundling 8 segments and running them simultaneously on the processing unit, but which obviously takes more RAM to do. Notice, however, that if you drop the precision to int8 from fp16, you use basically the same amount of RAM as whisper.cpp yet it completes in a fraction of the time using batching [0].

Yes, if you check their community integrations section on faster-whisper [1], you can see a lot of different CLIs, GUIs, and libraries. I recommend WhisperX [2], it's the most complete CLI so far and has features like diarization which whisper.cpp does not have in a production-ready capacity.

[0] https://github.com/SYSTRAN/faster-whisper#benchmark

[1] https://github.com/SYSTRAN/faster-whisper#community-integrat...

[2] https://github.com/m-bain/whisperX

Re: Dell admits consumers don't care about AI PCs

#389
post #56

Earlier quoted context omitted.

The only thing Apple is behind on in the AI race is LLMs. They've been vastly ahead of everyone else with things like text OCR, image element recognition / extraction, microphone noise suppression, etc. iPhones have had these features 2-5 years before Android did.

Apple’s AI powered image editor (like removing something from the background) is near unusable. Samsung’s is near magic, Google’s seems great. So there’s a big gap here.

That is rather funny because I think Google's and Samsung's AI image actions are completely garbage, butchering things to the point where I'd rather do it manually on my desktop or use prompt editing (which to Google's credit Gemini is fantastic at). Whereas Apple's is flawless in discerning everything within a scene or allowing me to extract single items from within a picture. For example say, a backpack in the background.

Re: Dell admits consumers don't care about AI PCs

#390
post #115
post #38

Consumers are not idiots. We know all this AI PC crap is it's mostly a useless gimmick. One day it will be very cool to run something like ChatGPT, Claude, or Gemini locally in our phones but we're still very, very far away from that.

Not that far away, you can run a useful model on flagship phones today, something around GPT 3.5's level. So we're probably only a few years out from today's SOTA models on our phones.

> you can run a useful model on flagship phones today

How?

Post reply on HN