alt Hacker NewsIt's the same plan. Apple's model is:
Handle the query on device. If the device cannot handle the query, push the query to Private Cloud, If Private Cloud cannot handle the query, push the query to a third party of the users choosing.
Which is pretty much the same as what they announced a few years ago.
Apple underestimated the amount of time and work needed to get to work and really the only bit that I think changed is that Private Cloud (and possibly the on device model) is a white label Google model rather than being developed in-house by Apple.
The problem with that approach is that “how do I handle this query”, and “did I handle that query ok” are both AI-hard problems, and must be tackled near the user, where the large model is not.
It also requires a relatively complex distributed architecture.
I worry about how successful they can be with this approach, in terms of best user experience.