With huge blobs of binary model weights, dynamic linking is cool again.

Which Apple has put some pretty large effort in the last few years to improve in iOS

Dynamic linking has always been cool for writing plugins.

It is kind of ironic that languages that praise so much for going back to early linking models, have to resort for much heavier OS IPC for similar capabilities.

Which languages?

IIUC Go and Rust resort to OS IPC based plugin system mainly because they refused to have a stable ABI.

On the other hand, at $DAYJOB we have a query engine written in C++ (which itself uses mostly static linking [1]) loading mostly static linked UDFs and ... it works.

[1] Without glibc, but with libstdc++ / libgcc etc.

Well if it loads code dynamically, it is no longer static linking.

Also it isn't as if there is a stable ABI for C and C++ either, unless everything is compiled with the same compiler, or using Windows like dynamic libraries, or something like COM to work around the ABI limitations.

Doesn’t rust’s static linking also have to do with the strategy of aggressive minimization? Iirc for instance every concrete instantiation of a dynamic type will have its own compiled binary, so it would basically be impossible for a dynamic library to do this since it wouldn’t know how it would be used, at least not without some major limitations or performance tradeoffs

This is how Google is doing it too.

Indeed. Google said LoRA and apple said adapter plugging. Wonder the difference is at, Apple's dev conference is for consumers and Google's dev conference is for developers.

Yeah, just Apple doing a better job branding. LoRA is an adapter.

Oh missed that!

But kinda as expected: only works on 2 android phones (pixel 8 pro, S24).

Pretty typical: Apple isn’t first, but also typically will scale faster with HW+platform integration.

On Apple’s side, Apple Intelligence will only be enabled on A17 Pro and M-series chips, so only the iPhone 15 Pro and Pro Max will be supported in terms of phones.

2 phones, ~4 tablets, ~12 PCs.

Looking at sales, looks like about 10x the phone volume of s24 (and pixel 8 doesn’t register on the chats).

> will scale faster

* Only in USA, both intentionally and not.

this is pretty stock standard lora.

"Don't be snarky."

https://news.ycombinator.com/newsguidelines.html

One day they're going to train a moderation bot on your account, and it's going to be amazing.

I’m sure you will continue to think so until he permanently restricts your account for getting downvoted

Quite the opposite. This 9 year old account just reached the karma level required to be able to downvote. I'm so chuffed.

You caught me, I was weak in the face of ridiculousness. Keep on keeping on, you do a great job keeping this place halfway civil.

What was ridiculous? Are they not doing stock standard lora?

I don't think you were ridiculous. In fact, I agree with you. I was sarcastically pointing out that whenever apple adopts some well understood technology the fanboys always gush over how innovative it is now that apple is doing it.

oh, ha. Makes sense.

It's LORA, most of the things you saw in Apple Intelligence on device presentation are basically different LORAs.

The article says it’s lora a bunch of times. That’s clear.

My comment above is about dev experience, memory swapping, tuning base models to each HW release, and app size.

Local models are also extremely energy consuming. I don't see local AI working for long, because Large models are going to get so incomparably smarter and eventually reach general intelligence