[EGreg]

Here is my question…

This is the first time that millions of people will actually download and run a model on their own devices.

The question is… will Apple be constantly tweaking these models, or only during OS upgrades?

I for one really like local software. Call me old-fashioned, but I enjoy when a company doesn’t switch up software anytime on the server, or phone the results home all the time in order to extract more profits from their collective users.

[alwillis]

> The question is… will Apple be constantly tweaking these models, or only during OS upgrades?

Certainly when new updates are released--going from macOS 26 to 26.1).

They can probably push model updates between releases if necessary.

[floam]

Per the PDF in this post:

> “Adapters produced by the toolkit are fully compatible with the Foundation Models framework. However, each adapter is compatible with a single specific model version, meaning that a new adapter must be trained for each new version of the base model.”

Any changes should require retraining any LoRA adapters that has been built & distributed by third party developers, so they wouldn’t update the models outside OS updates at the drop of a hat I don’t think.

LoRA adapters can be distributed via Background Assets, but the base model itself should be version-locked to the OS build (e.g. iOS 26.0 → 26.1) and updates only when Apple ships a new OS image.

[alwillis]

Makes sense; thanks for the clarification.

[wmf]

The model is gigabytes so I doubt they will push updates frequently.

[robotresearcher]

Educate me: is there any work on modifying models in a way that changes relatively few parameters, so an update is a smaller payload?

[wmf]

Yeah, LoRAs. Apple uses them to specialize a single model for different uses.

[robotresearcher]

Thanks! Very interesting. Lead inventor Edward Hu describes them, and their usage, incredibly well in this video:

https://youtu.be/DhRoTONcyZE?si=vM2N5zNslbQ5z8gv