They found references to both ComputeModule13.1 and ComputeModule13.3 in iOS 16.4 beta files at the time. There’s now also ComputeModule14.1, which is the server Apple uses for AI features.
Apple Intelligence works with both on-device and online language models, but to ensure user privacy, Apple built PCC with its own chips to process end-to-end encrypted requests. This approach ensures that neither Apple nor outside organizations can access user data after the computations are complete and the information is deleted.
Previous iterations, including ComputeModule13.1 and ComputeModule13.3 running on the M1, are still heavily used by Apple, presumably for non-AI tasks.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
