News

Apple announced its suite of personal AI features at called . It will be coming to iPhones, Macs, and iPads later this year. However, not all of Apple's devices will be compatible. . As a result, many users are curious about this requirement. Happily, this question was posed to Apple executives at The Talk Show Live From WWDC 2024. Host John Gruber (of Daring Fireball) asked Apple's AI chief John Giannandrea about this requirement and this was his reply: So these models, when you run them at run times, it's called inference, and the inference of large language models is incredibly computationally expensive. And so it's a combination of bandwidth in the device, it's the size of the Apple Neural Engine, it's the oomph in the device to actually do these models fast enough to be useful. You could, in theory, run these models on a very old device, but it would be so slow that it would not be useful. Gruber jokingly followed up and said, "So this is not a scheme to sell new iPhones?"  To which Joswiak chimed in, "No, not at all. Otherwise, we would have been smart enough just to do our most recent iPads and Macs, too, wouldn't we?" To provide some context, the iPhone 15 Pro and Pro Max are both powered by the A17 Pro – Apple's latest and greatest smartphone chip. One of its highlights is a much faster Neural Engine. The A17 Pro's Neural Engine is said to be capable of - that's double that of the A16 Bionic, whose Neural Engine can deliver performance of up to 17 trillion operations per second. Federighi also said during the talk that memory is another consideration and the devices that can support Apple Intelligence all have at least 8GB of RAM. To recap, Apple Intelligence will introduce features such as systemwide Writing Tools, personal context, and onscreen awareness. However, . Source: via