Difference is chatgpt is not privacy friendly.

Is it still not privacy friendly on Azure?

Azure has access to your queries. Running locally really is the only way of having a privacy friendly LLM.

I wonder if there is some way you could do an E2EE LLM SaSS? Guess more work probably needs to be done into homomorphic encryption for that.

This would actually be a great use case for homomorphic encryption. I’m behind on what the state of the art is in that though, but my mind immediately went there.

I don’t think homomorphic encryption works like that

Well that was helpful.

It's insanely slow and probably wont be fast for anything for a long time.

From my engineering point of view, the state of the art of homomorphic encryption can do some maths very very slowly at a huge cost and can’t be used yet for any real use case. A very cool research topic, but it’s much simpler to run our software locally if you don’t want to leak your data.

It feels like you don’t need encryption here, you just need a business model that doesn’t keep user accounts and sell the query data.

Is the chatgpt api paid to openai not private to openai?

I understand azure has its own chatgpt api.

> or a reasonably capable Mac Mini

IMO, Apple's habit of cheaping out on ram is maddening. Although perhaps this is a sign for me to pick up a m2 pro mini with extra ram.

Agreed. Apple might have sped up the ram addressing by building it in this time.

The Base mac studio with 32 gigs of ram can be a good value from a ram perspective.

Let’s see if the Mac studio is discontinued or updated.

> Let’s see if the Mac studio is discontinued or updated.

I do hope that it's updated. I could see them reserving the top end chip for the Mac Pro, though. Or maybe make it a dual socket?

In any case, I much prefer the ability to run an Apple computer with a proper cooling setup. I know that cooling pads for laptops exist, but ultimately it's a bit of a janky solution compared to actually adequately cooling the system properly.

You’re bang on with this comment.

The Mac studio is surprisingly quiet and well cooled. I haven’t had to install a fan control utility as of yet.

I thought I’d be trying one of these out and sell it if my setup didn’t work, but it’s the first desktop I’m starting to consider especially if I want to leave a workload running on it instead of a decade of carrying a lot of horsepower around with me.

Instant on for 3 monitors, no need for docking station or USB hubs, everything is plugged in and works, I can run a virtual cam obs setup easily.

The studio is a great upgrade on Mac mini, which might cannibalize the Mac pro sales and why it might not get toasted or refreshed. I’ll F the max studio was a way to put a dent in hackkntoshes, it makes sense.

The M2 mini looks super decent but quickly goes up in price when ram and ssd is setup to match a studio.

For my purposes the ultra wasn’t that much faster than the M1 max on because the software has to be optimized to benefit from it. Maybe some of this ML stuff will be shortly.

You can put together a 192GB 16+ core x86 system with 16GB CUDA card and multi TB of fast storage for $2000ish. I'm not trolling, just wondering why people go to "Apple" all the time, when other approaches may be better for this kind of work. Yes, the CPU - RAM interface is not as fast, but the CUDA card is much faster, and the large cheap memory makes some things a lot more practical. If I'm not mistaken, in these approaches, GPU + VRAM + CPU + RAM are used in conjunction, so it all adds up to quite a bit more powerful system for the same amount of money if working with them is a main goal. If Apple had expandable RAM it would be a different story.

Screw that - the other day I realized that it's cheaper to buy an Intel A770 ($350) with 16gb of memory than it is to upgrade a Mac Mini with 16gb ($400) of extra memory.

Apple's optimization here is nice for the people who own their hardware, but it's totally silly to read through the comments promising the end of CUDA.

In my case I'm interested in AI, but not quite enough to spend money on a whole separate computer for exploring ML work. I want a really great single laptop I can use for everything.

I’m as much PC/Linux as I am Mac. Lots of experience putting together more computers than I can count, or having them put together.

I think there might be a different use case for me but to compare with your economics - I picked up a base mac studio (m1 max with 32 gb) for about $1370 USD with 8 months warranty remaining. It’s letting me test my daily setup to see if everything can run on Apple silicon yet without intervention.. if not, I’ll be able to get rid of it at little to no loss, and decide if I want to carry that much computing power in a laptop or not, or head on to other options.

My interest currently is computational power, per watt. Not much comes close to Apple Silicon.

The cost of a loaded pc can quickly outstrip other options with electricity costs included so it needs to be useful in any case.

The integrated speed of the Apple silicon, ram, and ssd is a little astonishing. More than I expected to admit. I don’t know if there’s anything like it on PC. If Apple silicon supported eGPUs it would interest me.

Comparable PCs have described are generally power inefficient. Still, the system you’re laying out is interesting, especially the ram, mind sharing a bill of materials?

Sure, and I also get the "Apple lifestyle" POV.

I guess my PoV is with a GPU + inexpensive RAM, I can do some things more quickly, and other things are at least possible. But granted, hardware nuts and bolts is a hobby for me too, I've always enjoyed researching and building systems, there is a huge community of people and companies, and I much prefer KDE to MacOS, Android to IOS.

If Apple released a reasonably priced system with lots of RAM, or that could take a GPU, I'd not have as much to stand on, but they don't seem inclined to do that.

Here's BoM, $2170:

$700 for 192GB https://www.corsair.com/us/en/Categories/Products/Memory/VEN...

About $200 for a LGA1700 board with four slots (currently Asus and Gigabyte support 4 X 48GB memory modules on consumer hardware)

$200+ for a CPU

$120 for an 850 watt PSU

$700 for a used 16GB quadro, or a new 12GB A2000

$150 for 2TB NVME storage

$50 for some kinda case (I use an XTIA open frame, it is the opposite of a Macbook)

These are "best prices," You'd have to pay around 10% more if you're not into finding deals.

How many watts would be needed to power the above?

If it’s 400-800w 24 hours a day, op costs quickly pile up.

It looks really reasonable for everything here. I am interested more in eGPUs for interchangeability but have enough on my plate.