been exploring mascots and japan’s influence on character design. one thing led to another, and now this little guy reacts to you mediapipe for gesture tracking + gemini flash for the videos

trying a light editor on duo. i like the idea of using that second screen for different editors, instead of just a keyboard first project by our designer @alx_mindset (!)

i spent 4 weeks on my vision for working with ai agents i don't like how it works today: you jump between chats, babysit their questions, and they take over your screen our v0.1: - just say what you need, it handles the rest - agents use apps in the background - one tiny icon shows progress and questions - generated stuff appears beside it i think this pattern matters, and nobody has nailed it yet. i'll post more soon

design experiment with jev + astra + gpt voice + maplibre + apple photos + gps metadata i connected all of this just so i could name places over spongebob music and fly around a map with my vacation photos 💀

iphone duo could open up a whole new way to work with ai we need interfaces that grow with the task: chat, memory, products, a 3d scene, whatever you need along the way here’s my vision for how these blocks take shape and work together