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

Apple Silicon Exec Explains Mac Mini AI Demand and On-Device Future

macrumors.com

Post reply on HN
Print view View original

321–327 of 327 posts

Re: Apple Silicon Exec Explains Mac Mini AI Demand and On-Device Future

#321

Post by master_crab »

ttul wrote: post #269
habosa wrote: post #219

Apple has totally failed to deliver interesting AI experiences so far ... and I still think they're going to be the dominant provider of AI in 5 years. We're just one or two advances in chips / models / both away from being able to run very good local models for free on mid-tier Apple devices. The privacy, cost, and latency story there will be too much for OpenAI/Anthropic/Google to beat. Just writing this down so I…

Here’s the two main reasons why local inference won’t compete any time soon with the cloud: 1. Most useful LLM work is done in parallel. A Mac Mini can run one LLM inference thread at a time. The cloud can spool up dozens and spread that inference across efficiently batched operations over a fleet of hardware. 2. Faster inference hardware such as the chips from Cerebras and Groq cannot be run locally. But the advanta…

100%. Orchestrating multiple sub agents is a key requirement for many workflows. If only because it minimizes context sprawl (amongst multiple other reasons).

There is probably a middle ground though. Something like a main thread agent (say a local model for Hermes) orchestrating cloud based sub agents.

Re: Apple Silicon Exec Explains Mac Mini AI Demand and On-Device Future

#322

Post by coldtea »

narrator wrote: post #235
ralusek wrote: post #222

Earlier quoted context omitted.

1.) China is not communist, even remotely so. China is fascist in every sense of the word. 2.) Authoritarianism can move faster than anything. They can just say "wipe out that village, build the coal plant there, data center here, fab here. 3.) If it's red tape and regulation holding the US back, then that's clearly not "capitalism."

I think the most ironic fact of the 21st century is that there are less than 20,000 naturalized citizens in China. Western leftists don't really have a good explanation for that one and it definitely leans into the fascist characterization.

How is that ironic or necessary? Why should they hand out citizenships, when work or resident permits will do?

And that's somehow fascist, as if the problem with fascist Italy or nazi Germany was that they didn't hand out citizenships?

Re: Apple Silicon Exec Explains Mac Mini AI Demand and On-Device Future

#323

Post by windex »

stasomatic wrote: post #253
windex wrote: post #96

Earlier quoted context omitted.

Yup, for openclaw and APIs you dont need a big PC. I run something lightweight on the RPI4 8gb. Many people run local LLMs which is where a mac is useful. Frankly I dont think you can beat the value of an openrouter subscription and API calls.

If you or anyone else don’t mind, I have a have a question or 2. I use Claude Pro ($20/m) as a glorified search engine (no ads/SEO) plus simple hobbyist dev things (shell scripts, managing my Mac, apps etc. I also use it for tasks like - “search the web for top ten selling EVs, put them in a table” and then iterate - pivot tables, charts, additional research”. It could be cars, it could be broccoli. Code Work has fac…

You should try Google Edge Gallery and Gemma4 on your local pc

Re: Apple Silicon Exec Explains Mac Mini AI Demand and On-Device Future

#324

Post by stasomatic »

windex wrote: post #323
stasomatic wrote: post #253

Earlier quoted context omitted.

If you or anyone else don’t mind, I have a have a question or 2. I use Claude Pro ($20/m) as a glorified search engine (no ads/SEO) plus simple hobbyist dev things (shell scripts, managing my Mac, apps etc. I also use it for tasks like - “search the web for top ten selling EVs, put them in a table” and then iterate - pivot tables, charts, additional research”. It could be cars, it could be broccoli. Code Work has fac…

You should try Google Edge Gallery and Gemma4 on your local pc

Thanks, on it!

Re: Apple Silicon Exec Explains Mac Mini AI Demand and On-Device Future

#325

Post by officeplant »

dansquizsoft wrote: post #304
officeplant wrote: post #251

Earlier quoted context omitted.

And? I just upgraded my 2008 Thinkpad R61i to 8GB of DDR2 a few months ago while I was also upgrading to a core2duo. DDR2 and DDR3 are still in active use by SBC manufacturers.

> I just upgraded my 2008 Thinkpad R61i to 8GB of DDR2 a few months ago while I was also upgrading to a core2duo Uhhh… ok… good for you I guess…

Some of us keep the worthwhile trash alive forever. This laptop is gonna be twenty years old soon and it's too comfortable of a machine to be tossed to ewaste.

Re: Apple Silicon Exec Explains Mac Mini AI Demand and On-Device Future

#327

Post by tomaskafka »

cosmic_cheese wrote: post #177
lucky_cloud wrote: post #160

Earlier quoted context omitted.

I'm curious what you mean. I have been accessing Macs remotely over SSH and VNC for like 20 years and it's always been easy and as performant as the network would allow.

The built in high rez screen sharing between Macs works well too. Through Tailscale I’ve accessed my main Mac from both the opposite coast of the US and from the other side of the Pacific and it works great. Host resolution automatically matches that of client, image quality is great, framerate is decent, latency is minimal. The host creates virtual screens for the connection so connected screens don’t light up and t…

Thanks, I'll revisit that - it definitely wasn't working like this when I needed this 10+ years ago.
Post reply on HN