Bradley is tweeting about watching Sports in VR. Thats how you know its going to be good.
I was thoroughly surprised!
XR veterans are hard to surprise. Videos can’t quite capture what Sphenomenon feels like. These reactions can. Without excited developers, there’s no thriving spatial computing ecosystem.
@finkd @sama @satyanadella @sundarpichai @elonmusk @boztank @DavidSHolz want to try what got them this excited? I’d love to give you a personal demo.
The VR Industry has a huge blind spot. The people building it don’t watch sports.
Live immersive sports content on lightweight headsets will sell more VR headsets than VR games ever have.
Suno will be wiped off the map within 1 year, its obvious to anyone actually paying attention.
It took a lot of effort getting these working correctly! They make Fluid way more usable.
We are now one of the only android browsers that actually support chrome extensions.
MLB on Vision Pro with friends is the killer VR app.
If Apple can drive down vision’s price and weight, they will sell millions of devices.
MLB on Vision Pro is legitimately the most excitement I’ve heard for VR in a long time.
Sports are going to be what drives most normies to immersive media.
My favorite view was the bullpen, nice and up close to the pitcher where you can see their form really well.
My main nitpicks are, the Jumbotron and IRL screens showing scores, highlights and ads were super mushy and hard to see. I would LOVE to have those video textures be composited into the headset as their own high res layers. I also prefer to have the main broadcast audio as an option.
Regardless it’s the best sporting content ever in VR, amazing work @Apple
Rob retweeted
I spent two innings watching this game on Apple Immersive Video and WOW. This is the future. I would swear I was in the on-deck circle. Hope everyone gets a chance to see a game like this! 🥽
Full story coming at @MLB.
I have been building a egocentric data capture tool with @jmdagdelen. Got Superdex working and put some of our data thru it. Worked surprisingly well first try!
Meta just open-sourced its dexterity stack! 🪬
Most physics simulators were built for things that move through space.
Walking robots, drones, cars. Contact is the part they approximate worst, and obviously dexterous manipulation is nothing but contact.
Project SuperDex, from Meta Reality Labs Research, is built the other way around, a contact-first physics engine with the whole platform stacked on top of it.
The cool part is that it's on GitHub.
The engine runs one solver across rigid bodies, soft bodies, rods and tendons, shells and cloth, in the same model.
→ Non-convex collision with accurate contact force distributions, so a multi-finger grasp gets simulated rather than approximated
→ Tactile sensors and soft contact as first-class primitives
→ Numerical stability without the tight time-step limits explicit solvers force on you
→ Constraint-aware inverse kinematics running on the same optimization core as the forward dynamics
Then the data layer. Put on a Quest 3, teleoperate the simulated hand with haptic feedback, and generate demonstration datasets without touching real hardware.
They show a shape-sorting policy trained entirely in simulation and deployed zero-shot on a real robotic hand.
Robot hands are getting good. Data for them isn't that fast.
Meta is betting the cheapest way to collect contact-rich demonstrations is a headset people already own, pointed at a simulator instead of a game.
🔗 Here's the project page: projectsuperdex.com/
~~
♻️ Join the weekly robotics newsletter, and never miss any news → ziegler.substack.com