Marc Pous (Developer Relations at Edge Impulse and founder of IoT Stars) reflects on how embedded teams are finally getting practical edge AI wins: not just connecting devices, but running useful inference locally with a toolchain that takes you from sensor data to deployable firmware. https://edgeimpulse.com/
—
HDMI® Technology is the foundation for the worldwide ecosystem of HDMI-connected devices; integrated with displays, set-top boxes, laptops, audio video receivers and other product types. Because of this global usage, manufacturers, resellers, integrators and consumers must be assured that their HDMI® products work seamlessly together and deliver the best possible performance by sourcing products from licensed HDMI Adopters or authorized resellers. For HDMI Cables, consumers can look for the official HDMI® Cable Certification Labels on packaging. Innovation continues with the latest HDMI 2.2 Specification that supports higher 96Gbps bandwidth and next-gen HDMI Fixed Rate Link technology to provide optimal audio and video for a wide range of device applications. Higher resolutions and refresh rates are supported, including up to 12K@120 and 16K@60. Additionally, more high-quality options are supported, including uncompressed full chroma formats such as 8K@60/4:4:4 and 4K@240/4:4:4 at 10-bit and 12-bit color.
—
Recorded around Embedded World North America 2025 in Anaheim, he recaps the IoT Stars meetup (about 200 attendees at the House of Blues) and the kind of conversations developers actually need: a fireside chat with AWS IoT leadership and Avnet, plus panels on modernizing the embedded stack with newer connectivity, CI/CD, and device-ops patterns that shorten the path from prototype to shipped device.
A big thread is maturity: early IoT hype often lacked clear business models and reliable lifecycle management, so deployments stalled at pilots. Marc’s own arc maps that evolution, from building connected devices since 2007 and launching an IoT platform startup in 2012, to fleet management work at balena in 2020 where OTA updates, rollback, security patching, and observability become non-negotiable for anything deployed at scale.
What changes the equation now is on-device ML and model cascading: multiple optimized models running on the same embedded target, with outputs feeding the next stage (for example, object detection triggering a smaller classifier, or a visual pipeline combined with time-series anomaly detection). He also points at the rise of compact LLM and vision-language model runtimes at the edge, pushing workloads from cloud APIs into MCU/SoC firmware for lower latency, lower bandwidth, and tighter data control today.
Underneath, this is a developer-experience story: reduce friction with integrated data acquisition, labeling, DSP blocks, AutoML, quantization-aware training, and compilation paths that fit tight RAM/flash budgets on real hardware, often alongside RTOS workflows like Zephyr. The broader takeaway is that communities like IoT Stars help translate “GenAI everywhere” into deployable embedded patterns you can test, update, and maintain in the field, with fewer surprises and more.
I’m publishing about 90+ videos from Embedded World North America 2025, I upload about 4 videos per day at 5AM/11AM/5PM/11PM CET/EST. Join https://www.youtube.com/charbax/join for Early Access to all 90 videos (once they’re all queued in next few days) Check out all my Embedded World North America videos in my Embedded World playlist here: https://www.youtube.com/playlist?list=PL7xXqJFxvYvjgUpdNMBkGzEWU6YVxR8Ga
This video was filmed using the DJI Pocket 3 ($669 at https://amzn.to/4aMpKIC using the dual wireless DJI Mic 2 microphones with the DJI lapel microphone https://amzn.to/3XIj3l8 ), watch all my DJI Pocket 3 videos here https://www.youtube.com/playlist?list=PL7xXqJFxvYvhDlWIAxm_pR9dp7ArSkhKK
Click the “Super Thanks” button below the video to send a highlighted comment under the video! Brands I film are welcome to support my work in this way 😁
Check out my video with Daylight Computer about their revolutionary Sunlight Readable Transflective LCD Display for Healthy Learning: https://www.youtube.com/watch?v=U98RuxkFDYY
