Vision3D with full Muse support update is now live on the App Store.

Meta VR Glasses just mogged Apple Vision Pro. But the real question is how long will they have the spotlight? Should the entire VPG at Apple give up? Will Apple even try to build a next-generation device? I’ve seen photos showing Zuckerberg being compared to Jobs (lol). It seems like most of the VR industry is hyped. It’s great to see the industry moving forward as technology allows for it. Meta is attempting to make a massive move to capture the spatial computing market. Will they dominate this market, or will Apple produce its next-generation device in time? Looking forward to seeing visionOS running on a similar type of hardware.

Doing some final preparations to get AngioPilot ready for World Medical Innovation Forum 2026! Come get a demo of the first ever vascular catheterization simulation for Apple Vision Pro. Experience an immersive medical training simulation designed to help clinicians practice complex vascular procedures in spatial computing. See you at #WMIF2026! 🚀🫀

Come see MedVR x Mass General Bridgham at #WMIF2026! We’re excited to be showcasing what we’ve been building with MGB: a fully immersive vascular catheterization simulator for Apple Vision Pro. The experience is designed to simulate the complete vascular catheterization procedure in spatial computing, giving clinicians and trainees the ability to practice the workflow hands-on in an interactive, repeatable environment. The goal is to explore a new approach to medical simulation: making high-fidelity procedural training more accessible, scalable, and available wherever clinicians learn and practice. Come by and get a hands on demo today or tomorrow at the World Medical Innovation Forum 2026!

Local Jev? 🤔 Going to try integrating this in my agentic apps soon.

Jev could change how we build AI agents. I reverse engineered the idea and built Mini Jev from scratch. Trained on 50K agentic logs. Fully working. Open source on Hugging Face. Now I am gathering a team to push it toward production. huggingface.co/samatv256/min…

I just released mini Jev, demo: lnkd.in/gnnZe7vn Now I’m building the actual model from scratch for local agentic harnesses and enterprises that need private models. Target: 128K context 25 ms decision latency Input: TEXT, AUDIO, VIDEO. IMAGE

What if Apple Vision Pro could actually help save lives? That’s exactly what we’re trying to do with Codeblue Sim, a medical simulation app for Apple Vision Pro. We’re working with physicians and healthcare professionals to develop an advanced medical code simulator. The goal: give healthcare providers a way to practice responding to medical emergencies in an immersive spatial environment. More to come soon.

do not use @whop to accept payments it’s a vibecoded payment system by dumb ass engineers avoid losing your hard earned money just stick to stripe or a good MOR that handles fraud otherwise you are so done like me yesterday really fucked up situation

I built an AI Duolingo! Now we can learn any topic we want in the levels based way 😆

Why did Apple create the most realistic telepresence ability in the world, and then forget to market it or show it off in any meaningful way? Has anyone else noticed how SharePlay FaceTime calls have barely been featured in major marketing campaigns for Apple Vision Pro? It’s quite odd. Also I built one of the top spatial SharePlay apps for AVP (Crayon), and have agreements to give permission to use it in marketing footage. It’s been over a year, and in general I’ve seen 0 major marketing featuring the live multiplayer ability of SharePlay FaceTime calls. How do you create the most advanced live avatar call system, and then just not promote it? Hopefully they are saving this up their sleeve for the next generation.

I’ve been researching depth-residual routing & delta memory- Kimi K3 proved this holds at 2.8T params. But only for models trained this way I then asked: can you retrofit this onto existing LLM/world models? Introducing Retro-DARC: a Delta Attention Residual Compute adapter  that retrofits depth-selective memory onto existing models without retraining: EA exact no-op at insertion (bitwise 0.0 deviation on 3 public checkpoints - proven exact even through MoE routing and early exit), adapter-only training, exact rollback, and content-level memory audits that weight-touching adapters can't express by construction. The early results are promising. A ~262K-param adapter beat LoRA on a frozen public checkpoint, inserted at zero behavioral risk. And it's the first memory you can audit: zero the bank and the frozen loss returns to machine precision; shuffle it and 70–107% of the gain vanishes. That's a model measurably using its own computation history. Retro-DARC is useful for improving K3 too. K3 serves in MXFP4/MXFP8, and layer outputs - exactly what its AttnRes retrieves - collapse under that corruption in my tests (0.04–0.75 top-1) while normalized delta keys hold 0.86–0.99. A Softmax1 null route with proven mass bounds lets the router decline to retrieve instead of forcing the sinks and outliers OASIS documented; typed memory turns "what is depth retrieval doing?" into a runnable audit. And one experiment is free: K3 already computes a per-step KDA update magnitude and throws it away - that's a depth-saliency prior waiting to be read. For world models, the same contract becomes one typed memory interface: Retro-DARC-X gives world/action planners a single bank - observations, actions, tools, latent causes, traces, physics residuals, failures - the substrates a planner needs to remember in order to act over long horizons in the physical world. You can experience the thesis yourself. I created lucidre.am/memory which runs the paper's memory contract inside a walkable AI world. Innovation Memory makes your interactions survive looking away or reloading, and Dream Residue turns your movement into an inspectable glowing trace. Join the main Lucidre.am co-creation exhibition - the contest opens Wednesday. One of the six memory applications of the paper - saliency-weighted curation, will rank worlds by genuine novelty rather than recency and pick each world's most surprising viewpoint. And we're bringing live shows to SF + LA next month: screens showcasing worlds that remember, so you can literally play hide-and-seek with a dream that knows where you hide. Hide-and-seek is the exact test every 2026 world-model benchmark says the field fails, something leaves the frame, keeps changing, and has to come back right. This has been a fun little one-person research project so far! I’d love feedback and keep working on it. I’ve had over 100 references- thanks for all the prior work from teams that inspired me! I'd also love to intern at a GPU-rich lab (lol) and keep making beautiful worlds - if you let me keep running my remaining tests :) 2MB adapter kit, demo, prior iterations:adacyb0rg.github.io/retro-da… Paper: adacyb0rg.github.io/retro-da…

It's exciting to see developers continue pushing the limits of visionOS. Updates like this show how spatial apps are becoming more capable, more immersive, and more practical for everyday use.

AI is changing game development faster than most people realize. Seeing a playable Apple Vision Pro game come together in such a short time shows how quickly ideas can move from imagination to reality. The barrier to building keeps getting lower.

Palmo is an open-source Mac project that turns your webcam into a hands-free control surface. New feature: 🗣️ Shout to dictate Privacy first, by design: - All handtracking pipelines run locally through Apple's Vision framework - The assistant runs locally through Apple Intelligence. - Camera frames are never uploaded or stored, and your chat history stays on your Mac. Gesture - Action: ✋ Open palm up - Summon the orb menu 🤏 Pinch - Select an orb / click ✊ Fist - Scroll the frontmost window ✌️ Peace sign - Take a screenshot 👍 Thumbs-up - Play / Pause media 🗣️ Shout - Dictate

DicyaninLabs is proudly one of the leading visionOS open-source contributors with over 25+ Swift packages available to help with your Vision Pro application development.

Major updates are coming soon to Earth Eyes Pro! This is one of my best-selling Apple Vision Pro apps, so I am excited to add more features and improvements.