been doing some rebranding and uiux upgrade for @axisrobotics , try to make the life easier for everyone ps: i always hated our current ui, but don't have enough time to work that till now

I’m using pi much more for long-horizon tasks (>6h). it's simpler by design and easier to work programmatically. i rarely use pi tui, most of my work is driving it inside a bigger system/container/uiux. some takes: - pi ships with a minimal toolset and it's enough for airgapped tasks. if you have enterprise customers who want everything airgapped, pi + open-weight models is the goto solution. - pi extensions are mostly unnecessary. i only have pi-mcp-adapter and pi-vcc installed, because i need to maintain/use jina reader mcp. pi-vcc is a drop-in fix for pi's context compaction, which can bite you on long-horizon tasks (see screenshot last swimline where compaction takes more and more time in long-horizon task) - no double-dip: if you program pi with an agent like CC/Codex, you'll likely end up building another harness layer on top of pi's own harness, completely redundant glue code. every now and then you need to steer CC/Codex back to pi's design principle: keep the wrapper lean and mean, use pi native features as much as possible. - imo pi works best with open-weight and self-hosted models, or at least that's what makes pi fun to work with. But pay attention to pi/models.json: your coding agent probably doesn't know every attribute of those new open models. forget to declare image modality as an accepted input and pi suddenly starts shelling out to tesseract for ocr everything. Or leave max context length conservatively set at 65K and pi starts compacting frequently for no reason. - in the end, the nudge prompt (the one that keeps pi going forever), and workspace isolation (for multi-task/multi-tenant systems) are where you'll actually spend your effort. Not too many but that’s fine and that’s the point, for the harness just trusts pi to do the work in a very first-principled way. You can just focus on the actual task.

This is for everyone who still thinks Gen3D is useless 🤣 I generated a koi fish with clean topology using @tripoai but it was just a static mesh. No rig. No bones. Nothing. I wanted to animate it without touching Blender because I genuinely have no idea how to use Blender 😂 So I casually asked Claude if it could help me with it... And then Claude built THIS 🐟 A fish that swims, breathes, reacts to your cursor and even looks directly at you when you stop moving your cursor. It took a completely static 3D model and turned it into a fully animated fish with a swim cycle and subcarangiform kinematics. It even optimized the model and brought the file size down from 14.79MB to just 4.16MB. And also that water with ripple effects is built with TSL too. 60 FPS. WebGPU with WebGL2 fallback. All @threejs. This was inspired by @marina_uiux's website where I saw a fish swimming across the page. I immediately loved the idea and thought, "What if the fish actually felt alive, more immersive?" So I made it happen. And honestly, this is the kind of thing that makes me excited about what we can build with 3D on the web now. All thanks to AI! So for everyone who thinks you need to spend months learning Blender before you can build something like this, maybe it's time to rethink what Gen3D or AI is actually capable of :D Live: Code:

With generative UI, I really believe my old PM job is dead. No wireframe bullshit. Just evals. At this point, all I am doing is deleting all the UI/UX components that we have built and let AI decide instead. The fewer pre-defined UI components there are, the better!