Comment on Apple wants AI to run directly on its hardware instead of in the cloud
Ghostalmedia@lemmy.world 10 months agoJust because a certain requests don’t work offline, that doesn’t mean that Google isn’t actually running models locally for many requests.
My pixel isn’t new enough to run nano. What are some examples of offline processing not working?
I wouldn’t be surprised if the handshake between Pro and Nano was intermingled for certain requests. Some stuff done in the cloud, and some stuff done locally for speed - but if the internet is off, they kill the processing of the request entirely because half of the required platform isn’t available.
helenslunch@feddit.nl 10 months ago
Yeah? It does.
Ghostalmedia@lemmy.world 10 months ago
What a thought provoking reply.
helenslunch@feddit.nl 10 months ago
I dunno what you expect me to say. It’s not complicated.
Ghostalmedia@lemmy.world 10 months ago
You’re really going to say that Google isn’t doing anything locally with Tensor? That’s just silly.