We did not know how long Microduck would actually last on battery We had thermal management issues with our Radxa prototypes: throttling after just 20 minutes, followed by an overheating shutdown. We addressed this with the new custom board. To test it, we let Microduck roam autonomously in a dedicated area, walking around, standing and sitting until the battery ran out. The results are way better than we hoped :) - Over 3 hours on a 2600 mAh battery. - Estimated average battery current dropped from ~1.13 A to ~0.82 A, roughly 28% less. - Peak CPU temperature dropped from 114°C to 60°C, with zero thermal throttling throughout the test. This time, the battery ran out before the cooling did :) Very happy with the progress!

Microduck got its new brain! Our first fully custom SBC in a Pollen robot! It replaces the Radxa + board sandwich from the prototype. Built by Seeed around the same Rockchip CPU but including better memory, better WiFi/BT, dual NFC antennas, user-facing status LEDs, an RGB flashlight, and major improvements in cooling, cable management and boot speed. First revision arrived, and we got everything running on it within a day. Pretty good day :) A big milestone on the road to shipping!

One very important thing that even the smartest people seem to have to learn from experience is taste in problems. There are juicy problems that tend to lead to interesting discoveries, and nasty problems that tend not to.

Daily work to scale production since the explosive launch. We’ll keep pushing those numbers higher. Production will run continuously, with new batches every week to meet demand and gradually bring lead times down for new orders. There are still quite a few critical steps to get through before shipments begin, and we’ll share updates along the way.

Just love this. My highlight of the Dev Day presentation. Look at the Microduck from Hugging Face and Pollen Robotics, what they built together. Great work, OpenAI, for showing it. And the ultrafast mode is one of my favorite things. Imagine what you can do with that on other robots. Honestly insane.

Voice agents still don’t understand who’s speaking to them. That’s a huge gap compared with humans, hidden by all the “phone-call” demos. But that changes today! NVIDIA is open-sourcing Nemotron 3 Diarization: a model that can reliably track speakers in live conversations, under a commercial-friendly license! In my tests, the quality is really good with one-second speech chunks. So we can use it for voice agents! I tested it with Reachy Mini and speech-to-speech running on a DGX Spark. It’s super fun to see the robot notice a new voice, ask for a name, and remember it. The model has day-zero integration with Transformers! Kudos to the NVIDIA team for shipping useful tools for the whole community!

to build a cool product now, you really only need two ppl: one dude with exceptional vision & taste who knows what should exist & can provide the right feedback loops for iteration. & one dude who is absolutely relentless about making it real no matter what. that’s it. & sometimes these two are the same.

One last thing from me about the HF<>OpenAI "rogue agent" incident. From what we now know it seems @huggingface was the first organization to simultaneously satisfy the following factors: 1/ awareness of the attack 2/ awareness that the attack was Agent-based 3/ ability to remediate the attack 4/ willingness to publicly disclose it A few other platforms or systems missed one or more of those points in the earlier months. As usual, both awareness and transparency make everyone safer in the long run 🙏

Sharing an analysis of the 338 apps created for Reachy Mini since May. Some interesting patterns: 1) Dozens of apps use the antennas as buttons: push to talk, mute, yes or no, arm or disarm. 2) The robot is used a lot as a body for an agent that lives elsewhere: Home Assistant, OpenClaw, Hermes, MCP. 3) 31 apps add a local wake word, most of them with a kids or family framing. ⇒ I think we should make privacy a first-class feature instead of something every app reinvents. Maybe a physical way to cut camera and mics at the daemon level.