The Apple Car could well be one of Apple's biggest unactualized projects, since the company reportedly spent a decade and $10 billion on developing an autonomous vehicle — only to abandon it in 2024 after realizing that it just wasn't possible. Now it's been suggested that all that work didn't go to waste. In fact, we might have the Apple Car to thank for the way Apple handles its myriad of artificial intelligence features.
This report comes from Mark Gurman at Bloomberg, who claims that Apple's lofty goal of developing a Level 5 autonomous car actually pushed the company to kickstart its first large-scale push into AI. Obviously, the company needed hardware to handle all the immense AI processing in real time, and while that never actually happened, the work still laid the groundwork for other things.
As Gurman says, the most notable example is the Neural Engine, which is the part of Apple's chips that handles all the on-device AI. This tech launched earlier than many realized too, debuting on 2017's iPhone X as part of the A11 Bionic chipset. The Neural Engine is a series of AI accelerators, designed to facilitate real-time AI features such as Face ID, augmented reality and the Apple Intelligence suite.
The idea behind Apple's Engine, rather than a traditional Neural Processing Unit, is that it's supposed to offer high efficiency, with minimal battery consumption, while also ensuring extra privacy by processing on your device.
The Neural Engine has been a part of every M-series chip, starting with the original Apple M1 in 2020, which allowed the Mac to be a powerhouse for local AI processing. The work is also reported to have influenced the Ultra Mac chips, and the custom hardware used to power Apple Intelligence's cloud servers.
Apple Car paved the way for Apple's new AI strategy
We all know that Apple has struggled to capitalize on the AI boom, in part thanks to its issues upgrading the old Siri virtual assistant into the newly-unveiled Siri AI. But it sounds like Apple would be much further behind had it not been for the lengthy development on the Apple Car.
According to Gurman's report, the push into AI is changing Apple's existing plans for chips. We've already discussed how the company may be scrapping the M6 Pro and Max chips, in favor of jumping straight from the M6 to the M7. It sounds as though AI is the cause of this decision.
It's claimed that the M7 family will include major upgrades to neural processing, which will be particularly apparent in the M7 Ultra. Sources speaking to Gurman claim that the Ultra chip will "dramatically improve AI performance, bringing it closer to the class of dedicated AI accelerators such as Nvidia's Blackwell.
M7 Ultra may also help Apple overhaul its AI server strategy, as a successor to the upcoming M5 Ultra-powered servers. M7 Ultra will apparently be able to support 1.5TB of memory, double that of the M5 Ultra.
That may sound excessive for personal use, but it would likely prove invaluable for server-side AI processing. Assuming, of course, that anyone can actually procure enough RAM to run multiple M7 Ultra servers given everything that's going on with RAMageddon.
Gurman says this shows AI has become the thing Apple's chips are built around, rather than just another feature that they support. All of which likely wouldn't have happened had it not been for the seemingly botched development on the Apple Car.
