It runs on Android too, with AI Core or even with llama.cpp

srslyTrying2hlp 8 hours ago | parent [-]

Its more impressive when Apple does it because they are so far behind.

I remember being excited when Apple got widgets because then I could add my 'Next Alarm time' to my home screen. Made my company work phone usable on trips.

I wonder when they are going to get NVIDIA cards or CUDA? Then they can actually run LLMs and not just trick people into buying it under the 30 year old idea of 'Unified Memory'.

▲

bigyabai 8 hours ago | parent [-]

It's kinda funny that macOS supported CUDA when it was a tech demo, but then ideologically objects to it once it's a $3 trillion business.

They've had to be dragged kicking and screaming away from the NPU model only to admit that GPGPU tech was the right choice.

	▲	srslyTrying2hlp 7 hours ago \| parent [-]
		Yeah I remember that. Very Apple of them. 'Cool demo' -> Doesnt convert to tangible things. Wont attempt to compete with companies better than them, but go their own route. "oh look it consumes low power!" (Things no one cared about). They are the Nintendo of tech.