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

MacBook Pro with M5 Pro and M5 Max

apple.com

Post reply on HN
Print view View original

771–780 of 1001 posts

Re: MacBook Pro with M5 Pro and M5 Max

#771

Post by me551ah »

bbshfishe wrote: post #666
butILoveLife wrote: post #447

Earlier quoted context omitted.

>Time to first token measured with an 8K-token prompt using a 14-billion parameter model with 4-bit quantization Oh dear 14B and 4-bit quant? There are going to be a lot of embarrassed programmers who need to explain to their engineering managers why their Macbook can't reasonably run LLMs like they said it could. (This already happened at my fortune 20 company lol)

Yeah no it didn’t. If you have a fully speced out M3/4 MacBook with enough memory you’re running pretty decent models locally already. But no one is using local models anyway.

If your company can afford fully speced out M3/4 MacBook, then it can also afford cloud AI costs.

Re: MacBook Pro with M5 Pro and M5 Max

#772

Post by gbalduzzi »

riffraff wrote: post #757
manofmanysmiles wrote: post #114

I love the following section of their copy: > Even More Value for Upgraders > The new 14- and 16-inch MacBook Pro with M5 Pro and M5 Max mark a major leap for pro users. There’s never been a better time for customers to upgrade from a previous generation of MacBook Pro with Apple silicon or an Intel-based Mac. I read as "Whoops we made the M1 Macbook Pro too good, please upgrade!" I think I will get another 2-5 years…

Yeah reading these announcements I realized my M1 Pro is supposed to be obsolete but I still see no reason to upgrade. Also, my wife's still using the older touch bar MBP, and we'll, it works fine for her too. I'm not sure who needs the newer pros.

I'm still using the touch bar MBP. For doing web work using vs code, it works very well.

You start having problems when an heavy compilation is required, e.g. Android / iOS builds

Re: MacBook Pro with M5 Pro and M5 Max

#773

Post by raw_anon_1111 »

garbageman wrote: post #754
raw_anon_1111 wrote: post #631

Earlier quoted context omitted.

The way that voice assistants work even in the age of LLMs are: Voice —> Speech to Text -> LLM to determine intent -> JSON -> API call -> response -> LLM -> text to speech. TTFT is irrelevant, you have to process everything through the pipeline before you can generate a response. A fast model is more important than a good model Source: I do this kind of stuff for call centers. Yes I know modern LLMs don’t go through…

I'm curious, what does the 'determine intent' mean in this case?

An “intent” is something that a person wants to do - set a timer, get directions, etc.

A “slot” is the variable part of an intent. For instance “I want directions to 555 MockingBird Lane”. Would trigger a Directions intent that required where you are coming from and where you are going. Of course in that case it would assume your location.

Back in the pre LLM days and the way that Siri still works, someone had to manually list all of the different “utterances” that should trigger the intent - “Take me to {x}”,”I want to go to {x}” in every supported language and then had to have follow up phrases if someone just said something like “I need directions” to ask them something like “Where are you trying to go”.

Now you can do that with an LLM and some prompting and the LLM will keep going back and forth until all of the slots are filled and then tell it to create a JSON response when it has all of the information your API needs and you call your API.

This us what a prompt would look like to use a book a flight tool.

https://chatgpt.com/share/69a7d19f-494c-8010-8e9e-4e450f0bf0...

You also get the benefit of this works in any language not just English.

Re: MacBook Pro with M5 Pro and M5 Max

#774

Post by webXL »

sneak wrote: post #358
BeetleB wrote: post #196

Earlier quoted context omitted.

Can't they simply run MacOS on a VM on existing Mac hardware?

Not if you want it to be able to use the hardware identifiers to register for use with iMessage.

I have it running in a macos VM using lume & BlueBubbles on a throwaway iCloud account. A lot of hoops to jump through, though

https://cua.ai/docs/lume https://docs.openclaw.ai/channels/bluebubbles

Re: MacBook Pro with M5 Pro and M5 Max

#775

Post by moi2388 »

trial3 wrote: post #659
stephenr wrote: post #632

Earlier quoted context omitted.

> Nano-texture is worth the upgrade if you are on a macbookpro whatever M and dont have it. Oh really, it's universally better? > For those of us with astigmatism it's really night and day experience. Oh. So it's better for someone else with a specific eye condition, who is practically guaranteed to never use a MacBook that I buy?

lmao you're coming in pretty hot, stephen. it is actually possible that from time to time you may encounter comments written on the internet that do not perfectly reference every aspect of your lived experience

Oh the audacity of not catering to my specific persona

Re: MacBook Pro with M5 Pro and M5 Max

#776

Post by bsimpson »

spopejoy wrote: post #668
bsimpson wrote: post #394

Earlier quoted context omitted.

Nope - they removed that feature, so now come the end of the year, they're all e-waste. It feels really stupid to have to throw away a perfectly capable machine with 64GB of RAM in 2026.

Throw asahi on it? I have access to one of those beasts and am considering it ...

It's Intel - you could run any Linux.

Unfortunately, I don't know that Linux handles the bespoke 5k graphics. Moreover, our corp Linux distribution is only certified for particular devices. Even if the screen worked, you wouldn't be allowed on the network, which is the whole problem with Intel support being dropped in the first place.

Re: MacBook Pro with M5 Pro and M5 Max

#777

Post by palad1n »

manofmanysmiles wrote: post #114

I love the following section of their copy: > Even More Value for Upgraders > The new 14- and 16-inch MacBook Pro with M5 Pro and M5 Max mark a major leap for pro users. There’s never been a better time for customers to upgrade from a previous generation of MacBook Pro with Apple silicon or an Intel-based Mac. I read as "Whoops we made the M1 Macbook Pro too good, please upgrade!" I think I will get another 2-5 years…

Haha! I bought an M1 Max Macbook Pro and I maxed most of the specs. 64GB memory! (Except for the SSD, which I got the 2TB option.) I have not even THOUGHT about “upgrading” to a newer model. I have yet to even tax my system to any significant degree. Bad for Apple? How much are they worth?

Re: MacBook Pro with M5 Pro and M5 Max

#778

Post by bartvk »

re-thc wrote: post #454
whynotmaybe wrote: post #433

Earlier quoted context omitted.

Quite interesting that it's now a selling point just like fps in Crysis was a long time ago.

Next is the fps of an AI playing Crysis.

If AI actually becomes somewhat sentient, it may be bored out of its skull in between our queries, and may want to do some "light gaming".

Re: MacBook Pro with M5 Pro and M5 Max

#779

Post by Zanfa »

testing22321 wrote: post #709
bsimpson wrote: post #394

Earlier quoted context omitted.

Nope - they removed that feature, so now come the end of the year, they're all e-waste. It feels really stupid to have to throw away a perfectly capable machine with 64GB of RAM in 2026.

Tons of people pull the 5k iMac apart, gut the insides and install a driver board to run the screen. For a few hundred bucks you get a wicked 5k screen

Did exactly that a while ago to salvage the nano texture panel from my 5k iMac. It takes a bit of research to figure out the correct driver board for the specific panel / peripheral combo, but the build process itself was pretty straightforward and it works like a charm.

Re: MacBook Pro with M5 Pro and M5 Max

#780

Post by EagnaIonat »

wincy wrote: post #12

I typed “RAM” to search for it and boy they hammer home how lucky I am to be getting 1TB SSD standard, but no mention of RAM anywhere on this page. Anyway, the MacBook Pro starts with 16GB of RAM. It’s $400 to go from 16GB to 32GB. Interestingly, 36-128GB models are showing as “currently unavailable” on the store page, and you can’t even place an order for them right now? But for anyone curious, it’s quoting $5099 fo…

ARM RAM is not like your typical RAM. 16GB will easily run intensive software where you would x2+ on a windows machine.

Unless you are planning to do some serious inferencing, or complex multi-agent setup, then you don't need the memory.

Post reply on HN