AI is big these days. Massive. More parameters, more memory, more capability. But what if the future is in tiny AI. Neural networks as small at 8 kilobytes on tiny chips, embedded in everything?
Think smart shoes.
Smart doors.
Smart … everything
In this episode of TechFirst, host John Koetsier discusses the future of smart devices with Yubei Chen, co-founder of AIzip:
The conversation explores how small-scale AI can revolutionize everyday objects like shoes, cameras, and baby monitors. They delve into how edge AI, which operates at the device level rather than in the cloud, can create efficient, reliable, and cost-effective smart solutions. Chen explains the potential and challenges of integrating AI into traditional devices, including the hardware and software requirements, and touches on the implications for product quality, safety, and cost.
Tiny AI: summary of the episode
In this episode of TechFirst, John Koetsier interviews Yubei Chen, co-founder of AIzip, about how tiny AI models—some as small as 8 kilobytes—are powering smart functionality in everyday objects without needing the cloud.
Chen explains that AI is fundamentally changing how we interact with the physical world. By embedding efficient, task-specific AI into devices like shoes, earbuds, cameras, or baby monitors, we can make them smarter, more useful, and responsive without relying on massive cloud-based models.
Examples include smart fish farm cameras that optimize feeding and reduce costs, bone conduction microphones for clear voice input in noisy environments, and wearable AI that detects posture or movement patterns. In one case, an 8KB neural network can classify 13 types of human activity.
Unlike large language models like ChatGPT or Gemini, AIzip focuses on edge AI—small models that run on-device. These models can be deployed on extremely low-power hardware, sometimes costing less than 10 cents. They’re also more private, faster, and tailored to specific use cases.
Chen highlights partnerships with chipmakers like Arm, Qualcomm, and Analog Devices to integrate these models into hardware ranging from battery-free sensors to mobile devices. Voice interfaces powered by these models could eventually replace outdated UI systems in everything from printers to baby monitors to smart home devices.
Tiny AI won’t make your shoes understand global politics, Chen jokes—but it will help them detect if you’re walking unsteadily, potentially flagging a health issue. That’s the future AIzip is building: smart, localized intelligence embedded everywhere, affordably and efficiently.
TechFirst: available on all the major podcasting platforms
Prefer to listen to your podcasts rather than watch them on YouTube?
No worries. Here you go: