Magic Leap One Ships: Reflections on Launch Day
We shipped a mixed reality headset. Reflections on what it means, what we got right, what we got wrong, and what comes next.
Magic Leap One Creator Edition is shipping today. After two and a half years, the device is real and going to customers.
What We Shipped
The perception system in every Magic Leap One includes:
- 6DoF head tracking: Visual-inertial odometry at 60Hz, under 1mm accuracy indoors
- Spatial mapping: Real-time 3D mesh generation
- Plane detection: Horizontal and vertical surfaces for content placement
- Eye tracking: Gaze vector for foveated rendering and interaction
- Image tracking: Fiducial markers for spatial anchors
Each of these was a research problem when I started. Each is now a production feature.
What Went Right
Synthetic data investment paid off: Our eye tracking and hand tracking models benefit enormously from procedural data generation. We couldn't have collected enough real data.
Calibration infrastructure: The production calibration system works. Yield is above target. Quality is consistent.
Sensor architecture choices: ToF depth and global shutter tracking cameras were the right calls. We're not fighting sensor limitations.
Team resilience: The final push was brutal, but the team held together. Nobody burned out catastrophically.
What Went Wrong
Outdoor performance: SLAM doesn't work reliably outside. We knew this, but hoped to solve it. We didn't. It's a known limitation.
Power consumption: We're higher than spec. Battery life is shorter than we wanted. Thermal throttling kicks in sooner than ideal.
Hand tracking scope: Gesture recognition was cut. Users get basic hand tracking but not the natural interaction we envisioned.
Polish gap: Many edge cases have rough edges. The core works, but it doesn't feel finished in the way Apple products do.
Market Reality
The reviews are... mixed. The technology is impressive. The price ($2,295) is high. The content ecosystem is thin. The form factor is chunky.
We built what we could build. The market will decide if it's enough.
What I Learned
Shipping is a muscle: You only learn to ship by shipping. All the planning, process, and preparation matter less than the experience of actually getting something out the door.
Hardware is unforgiving: Software bugs can be patched. Hardware ships with its limitations baked in. The decisions we made in 2016 determined what was possible in 2018.
The goal isn't the device: The goal is enabling experiences that weren't possible before. The device is necessary but not sufficient.
What's Next
For the product:
- Software updates to improve tracking
- Content partnerships to fill the experience gap
- Iteration toward V2 with lessons learned
For me:
- Shifting focus from V1 firefighting to V2 architecture
- Scaling the synthetic data platform
- Developing the next generation of perception capabilities
We shipped. Now the real work begins.