Live data from Hacker News

Apple M5 chip

apple.com

141–150 of 1001 posts

Re: Apple M5 chip

#141

Earlier quoted context omitted.

Sixteen years ago, John Gruber wrote: > Hardware and software both matter, and Apple’s history shows that there’s a good argument to be made for developing integrated hardware and software. But if you asked me which matters more, I wouldn’t hesitate to say software. All things considered I’d much prefer a PC running Mac OS X to a Mac running Windows. https://daringfireball.net/2009/11/the_os_opportunity At the time I…

I bet most people around here would prefer fully supported linux over mac os on their apple silicon.

Fully supported Linux + proper suspend-to-RAM are the two things I want out of Apple Silicon and may never quite get. Better online low power states are fine, but I want suspend-to-RAM and suspend-then-hibernate.

If I close my laptop for a few days, I don't want significant battery drain. If I don't use it for two weeks, I want it to still have life left. And I don't want to write tens of gigabytes to disk every time I close the lid, either!

Re: Apple M5 chip

#142

The modern Apple feels like their hardware teams way outperforming the software teams.

Apple have always been a hardware company, like Google have always been a software company even if they're doing hardware too now.

Re: Apple M5 chip

#143
post #69
post #25

Earlier quoted context omitted.

Well besides software that runs in data centers/ cloud most other software is turning to crap. And people who think this crap is fine have now reached to position of responsibility at lot of companies. So things would go only worse from here.

Except community-developed open source software, which (slowly, perhaps) keeps getting better and has high resistance to enshittification.

The OSS that keeps getting "better" is one that accept lot user feature requests and/or implementation. Else maintainers are hostile to users. And when they do accept most of those requests and code we all know how it goes.

Re: Apple M5 chip

#145

Earlier quoted context omitted.

Sixteen years ago, John Gruber wrote: > Hardware and software both matter, and Apple’s history shows that there’s a good argument to be made for developing integrated hardware and software. But if you asked me which matters more, I wouldn’t hesitate to say software. All things considered I’d much prefer a PC running Mac OS X to a Mac running Windows. https://daringfireball.net/2009/11/the_os_opportunity At the time I…

I bet most people around here would prefer fully supported linux over mac os on their apple silicon.

The best part of MacOS for me is the unix tools. The command line is a real unix command line. And the rest just works. If I need a linux environment I ssh into a VPS.

Re: Apple M5 chip

#146
post #102
post #2

This is only the base model, no upgrades yet for the Pro/Max version. The memory bandwidth is 153GB/s which is not enough to run viable open source LLM models properly.

I am interested to learn why models move so much data per second. Where could I learn more that is not a ChatGPT session?

You might be interested in LLM Systems which talks about how LLMs work at the hardware level and what optimizations can be done to improve the efficiency of them in this course: https://llmsystem.github.io/llmsystem2025spring/

Re: Apple M5 chip

#148
post #26

Earlier quoted context omitted.

Apple has always been a hardware company first - think of how they sell consumers computers with the OS for free, while Microsoft primarily just sells the OS (when comparing the consumer business; I don’t want to get into all the other stuff Microsoft does). Now that they own the SoC design pipeline, they’re really able to flex these muscles.

Not really. Back in the day you wouldn't buy a MacBook because it was powerful. Most likely it had a very shitty Intel CPU with not a lot of cores and with thermal challenges, and the reason you bought it was because macOS.

The intel laptops also grounded into the user. I still can't believe they didn't have a recall to sort that out.

Re: Apple M5 chip

#149

The modern Apple feels like their hardware teams way outperforming the software teams.

Software is very easy to bloat, expand scope, and grow to do more than really needed, or just to release apps that are then forgotten about. Hardware is naturally limited in scope due to manufacturing costs, and doesn't "grow" in the same way. You replace features and components rather than constantly add to them. Apple needs someone to come in and aggressively cut scope in the software, removing features and product…

> pare down products and features

macOS has way too many products but far too few features. In terms of feature-completeness, it's already crippled. What OS features can macOS afford to lose?

Re: Apple M5 chip

#150

Are we going to see SOTA local coding models anytime soon with this hardware or is it still long way to go?

You can already do that, just how slow or fast you go depends on how much you're ready to pay for memory. It's a $1200 premium to go from 36GB to 128GB of unified memory, that cost is hard to justify unless you really need it, or if someone else is paying.

None is comparable to GPT-5 or Sonnet 4.5 experience
Post reply on HN