Back to Blog
Posts tagged “Edge Computing”
An Earbud With Its Own Wi-Fi, a Model With a Thousand Tokens
Qualcomm gave the earbud a radio that reaches the cloud without the phone, and a 1-bit model that holds about four minutes of talk.- Wearable AI
- On-Device AI
- Edge Computing
- Audio
- Agent Architecture
What the Puck Can Afford to Think
Qualcomm's claim of a 3B model at 45 tokens a second on the VR Glasses chip needs the puck's entire memory bus, by my arithmetic.- On-Device AI
- Edge Computing
- Smart Glasses
- Agent Architecture
- Meta
The Silicon at Both Ends of Meta's Tether
By my arithmetic, Meta's VR Glasses panels need up to 40 Gbps uncompressed, more than the Qualcomm chip's one DisplayPort 1.4 output carries.- Smart Glasses
- Sensing
- Edge Computing
- Platform Architecture
- Meta
Persistent Context Without a Cloud Round-Trip
On-device NPUs and edge voice models converged in the same week - the ambient wearable can finally build context locally.- Wearable AI
- On-Device AI
- Ambient AI
- Personal Context
- Edge Computing
Muse Spark Starts From the Battery
Muse Spark matches Llama 4 Maverick at 10x less compute and ships on $299 glasses.- Wearable AI
- On-Device AI
- Agentic AI
- Edge Computing
- Model Architecture
White-Label AI Glasses
Qualcomm's START toolkit lets any eyewear brand ship AI glasses without building the stack.- Wearable AI
- Platform Architecture
- Agentic AI
- Edge Computing
- Ambient AI
Why Would an Agent Need Its Own Hardware?
Three platform companies shipped agent-first hardware in the same week - the agent is leaving the screen.- Agentic AI
- Agent Architecture
- Wearable AI
- Platform Architecture
- Edge Computing