Apple's Abandoned Self-Driving Car Quietly Built the AI Chip Inside Every iPhone

Key points

• Apple's Neural Engine, the dedicated AI processor inside every modern iPhone and Mac, grew out of work on a self-driving car project that was later scrapped.
• The Neural Engine first appeared in the iPhone X and its A11 Bionic chip in 2017, initially handling face recognition and augmented reality.
• Apple plans to skip the Pro, Max, and Ultra variants of the M6 chip, its next generation of desktop processors.
• The M7 chip, due in the first half of 2027, will carry major Neural Engine upgrades.
• Apple's M7 Ultra variant is expected to power a new server product supporting up to 1.5 terabytes of RAM, enough memory to run very large AI models.

Apple spent years trying to build a self-driving car. The car never arrived. But the engineering problem it posed, specifically how to run powerful artificial intelligence directly on a vehicle's own hardware without relying on a distant data centre, planted a seed that grew into something far more lasting.

That seed is the Neural Engine, a dedicated processing unit built into every Apple chip since 2017. Think of it as a specialist worker living inside the chip: while the main processor handles general tasks, the Neural Engine does nothing but AI calculations, and it does them fast. As first reported by The Verge AI, citing Bloomberg's Mark Gurman, Apple engineers working on the car realised early on that standard chips were not going to cut it. The car processor was never finished. The Neural Engine was.

It debuted inside the A11 Bionic chip in the iPhone X. Back then it had two jobs: recognising your face to unlock the phone and powering Animoji, the animated characters that mimic facial expressions. Modest beginnings.

What followed was less modest. Apple carried the Neural Engine into its M-series chips, the processors that run MacBook and desktop computers, giving those machines the same on-device AI muscle as an iPhone. Running AI locally, rather than sending your data to Apple's servers, is also why Apple can credibly claim stronger privacy than rivals who process everything in the cloud.

Now Apple is betting bigger on that foundation. According to Gurman, the company is skipping the intermediate Pro, Max, and Ultra versions of the M6 chip entirely and accelerating straight to the M7. The M7 is expected in the first half of 2027 and will bring significant Neural Engine upgrades. The M7 Ultra, the top-end variant, should also underpin a new Apple server product capable of holding up to 1.5 terabytes of RAM. That is an enormous amount of fast memory, the kind needed to run the largest AI models without sending anything off-device.

What does this mean for people who own Apple devices?

If you bought an iPhone or a Mac in the last few years, you already carry a Neural Engine. Practically, that means features like voice transcription, photo organisation, and on-screen writing assistance happen on the device itself, not in a data centre somewhere. The M7 should make those features noticeably faster and more capable when it arrives in 2027 hardware. For now, nothing changes.