Came here to ask about how they view Apple Foundation Models as a threat.

> guarantees privacy by default, works offline, and doesn't rack up a massive API bill at scale.

I’ve been really interested in on-device ML for most of my career, and now I wonder how valuable these benefits really are. LLM vendor APIs are pretty performant these days, security is security, and with an on-device model you have to provide updates every time a new model comes out.

You don’t have to bundle the weights as an asset, you can do over-the-air updates, new weights are simply downloaded.