Apple’s failed self-driving car program left a legacy of powerful AI chips

2026-07-12 · Source: The Verge · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems, Emerging Technologies & Innovation · Depth: Fundamental Awareness, quick

Summary

Apple's powerful Neural Engine, central to its on-device AI processing, originated from the company's now-defunct self-driving car program, "Project Titan." Recognizing the need for robust on-device AI for autonomous vehicles, Apple developed the Neural Engine, which first appeared in the iPhone X with the A11 Bionic chip. Initially used for computer vision tasks like FaceID and Animoji, this technology later expanded to desktops via M-series chips, establishing Apple as an early leader in integrated AI hardware. Despite lagging in AI software, Apple is now making its AI hardware a strategic cornerstone, reportedly skipping M6 Pro, Max, and Ultra versions to accelerate the M7 chip's development. The M7, expected in the first half of 2027, will feature significant Neural Engine upgrades, with the M7 Ultra potentially forming the basis for a new server product supporting up to 1.5TB of RAM, also bolstering privacy by reducing cloud data reliance.

Key takeaway

For Directors of AI/ML evaluating future hardware roadmaps, Apple's strategy underscores the value of custom silicon for on-device AI. You should prioritize developing or integrating specialized AI accelerators to enhance privacy and performance, especially for edge computing applications. Consider how dedicated hardware can differentiate your offerings and enable new capabilities, like the M7 Ultra's potential server applications. Your long-term hardware investments should align with evolving AI processing demands.

Key insights

Apple's failed self-driving car project unexpectedly catalyzed its powerful Neural Engine, now central to its AI hardware strategy.

Principles

• Strategic pivots can yield unexpected core technologies.
• On-device AI enhances privacy and performance.
• Hardware-software co-development is crucial for AI.

In practice

• Prioritize on-device AI for privacy-sensitive applications.
• Invest in custom silicon for AI performance gains.
• Explore unexpected R&D outcomes for new product lines.

Topics

• Apple Neural Engine
• On-device AI
• Custom AI Silicon
• M-series Chips
• AI Hardware Strategy
• Edge AI Privacy

Best for: CTO, VP of Engineering/Data, Executive, AI Hardware Engineer, Director of AI/ML, Tech Journalist

Related on AIssential

• Apple to skip M6 Pro and Max chips, fast-tracks M7 lineup for AI focus — Apple prioritizes AI performance by fast-tracking M7 chips with enhanced Neural Engines, altering its traditional release cycle.
• Apple could ‘run the table’ on AI if it does things right — Apple's AI strategy emphasizes on-device and private cloud deployment, aiming to democratize access and reduce reliance on external frontier models.
• OpenAI’s Jalapeño chip is Big Tech’s spiciest move away from Nvidia — Major tech firms are developing custom AI chips to gain control and optimize performance, reducing reliance on single suppliers.
• AI Is Eating Memory: The Chip Crisis Hitting Apple and Tesla — The AI boom's profit pool is shifting from software to physical infrastructure, with memory becoming a critical bottleneck.
• Apple Wins The AI Hardware Race — Apple's hardware, particularly Mac Mini, is a surprising winner in the AI market despite software delays.
• Apple seeks AI chip acquisitions to fix server performance woes — Apple is pursuing AI chip acquisitions to overcome server performance limitations and bolster its in-house AI infrastructure.

See Counsel's argued verdicts on the open AI decisions leaders are weighing →

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by The Verge.