It’d be short sighted to not have a wrapper around which AI to use, even without implementation for them. Like, having an abstract parent class with a Siri implementation of it would be baseline good software engineering.
I’m not even sure how they would implement these features without them being interoperable. All the AI systems use pretty similar if not identical API standards.
That exists already for Apple devices. They just never give third party models first class access to user and device data.
That arrangement will change, somewhat, later today.
And given how Apple switched out OpenAI for Gemini (to power Siri), they experienced firsthand the importance of having said wrapper.
Yeah; plus we know they're designing with potential future local-only Vs. hybrid Vs. cloud-only in mind depending on hardware/market changes. So having it be this flexible buys them a ton of future potential.
People have speculated that with FPGAs or even an ASIC you could take some smaller models we have today, turn the chip into essentially that model-as-hardware, and get some really compelling performance/power-usage characteristics.
At that point running a GOOD quantized Q8 model on a phone is not beyond the realm.