Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Apple's On-Device and Server Foundation Models

machinelearning.apple.com

Post reply on HN
Print view View original

271–280 of 562 posts

Re: Apple's On-Device and Server Foundation Models

#271

Post by causal »

cube2222 wrote: post #30

Halfway down the article contains some great charts with comparisons to other relevant models, like Mistral-7B for the on-device models, and both gpt-3.5 and 4 for the server-side models. They include data about the ratio of which outputs human graders preferred (for server side it’s better than 3.5, worse than 4). BUT, the interesting chart to me is „Human Evaluation of Output Harmfulness” which is much, much ”bette…

Refusing to answer any question would result in a perfect score for the first chart since it says nothing of specificity

Re: Apple's On-Device and Server Foundation Models

#272

Post by advael »

solarkraft wrote: post #151
threeseed wrote: post #96

Earlier quoted context omitted.

> Even with root on macbooks I don't have access to everything running on it Just disable System Integrity Protection and then you do.

That has a few drawbacks, for instance you won't be able to run iOS apps anymore.

Yea, nice as it is to hear that they're nice to their dev marketshare, there's probably never going to be a sanctioned iphone the end user actually gets to control. Bread and butter and such

Re: Apple's On-Device and Server Foundation Models

#273

Post by creshal »

zer0zzz wrote: post #168
talldayo wrote: post #147

Earlier quoted context omitted.

The Steam Deck ships with 16 gigs of quad-channel LPDDR5 and it costs $400. Apple knows exaaaactly what they're doing with this sort of pricing. Can't forget about that cozy 256gb SSD either. An AI computer will need more than that, right?

Is steamdeck sold at cost? From what I know Apple has a rule that everything must be sold at 40% margins. That is prob the main reason.

40% margin on parts that cost tens of dollars isn't going to have a huge impact on the sticker price of devices costing hundreds to thousands.

Re: Apple's On-Device and Server Foundation Models

#274

Post by miven »

fudged71 wrote: post #269
bagrow wrote: post #231

Earlier quoted context omitted.

https://apple.github.io/coremltools/docs-guides/source/palet...

404

Yeah, it just got updated, here's the new link, they added sections on block-wise quantization for both the rounding-based and LUT-based approach: https://apple.github.io/coremltools/docs-guides/source/opt-p...

Re: Apple's On-Device and Server Foundation Models

#275

Post by prmoustache »

IOT_Apprentice wrote: post #246
lolinder wrote: post #185

Earlier quoted context omitted.

> For people interested in AI research, there's nothing new here. Was anyone expecting anything new? Apple has never been big on living at the cutting edge of technology exploring spaces that no one has explored before—from laptops to the iPhone to iPads to watches, every success they've had has come from taking tech that was already prototyped by many other companies and smoothing out the usability kinks to get it r…

Apple was first with 64 bit iPhone chips. Remember Qualcomm VP at the time claimed it was nothing. Apple Silicon for M1 was impressive for instant in low power high performance.

But last at bringing a calculator on the iPad =)

Re: Apple's On-Device and Server Foundation Models

#276

Post by jackothy »

theshrike79 wrote: post #242
necovek wrote: post #225

Earlier quoted context omitted.

Except that everyone has different visual acuity and different distance they use the same devices at, and in the end, "retina" means nothing at all. But this is exactly the type of marketing Apple is good at, though "retina" is probably not the most successful example.

If your "visual acuity" is so good that you can see the pixels of a retina-branded display from the intended viewing distance, you might need to be studied for science.

It's not so impossible to spot flaws if you're using worst-case testing scenarios. Which are not worthless because such patterns do actually pop up in real world usage, albeit rarely.

Re: Apple's On-Device and Server Foundation Models

#277

Post by bayindirh »

pjmlp wrote: post #249
throwaway4good wrote: post #237

Earlier quoted context omitted.

I thought the news of them using Apple Silicon rather than NVIDIA in their data centers was significant. Perhaps there is still hope of a relaunch of xserve; with the widespread use of Apple computers amongst developers Apple has a real chance of challenging NVIDIA's CUDA moat.

Not at Apple's price points.

I mean, even Apple can't match the markups nVidia has right now. If you break a GPU in your compute server, you wait months for a replacement, and the part is sent back if you can't replace it in five days.

Crazy times.

Re: Apple's On-Device and Server Foundation Models

#280

Post by throwaway4good »

pjmlp wrote: post #262
throwaway4good wrote: post #251

Earlier quoted context omitted.

I think NVIDIA has the highest hardware markup at the moment.

Depends on which card one is talking about.

Maybe. It is not really obvious how much you for the AI accellerator part of their offerings. For example the chips in iPhones are quite powerful even adjusted for price. However for some cases - like the max chip in the macbooks or the extra ram - their pricing seems high - maybe even nvidia high.
Post reply on HN