logoalt Hacker News

taybintoday at 12:52 PM4 repliesview on HN

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.


Replies

Someone1234today at 1:51 PM

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.

show 1 reply
Grombobuloustoday at 2:06 PM

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.

dd8601fntoday at 2:46 PM

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.

tiffanyhtoday at 2:13 PM

And given how Apple switched out OpenAI for Gemini (to power Siri), they experienced firsthand the importance of having said wrapper.