Adam Chernick

spark.js 2.0 just dropped today! This is big news! @sparkjsdev @theworldlabs @XRarchitect github.com/sparkjsdev/spa…

at @nianticspatial, we're building the real-world model for physical AI. we believe the next generation of AI will move beyond the screen, into real-world environments where some of the hardest problems need to be solved. with high-fidelity gaussian splats as the foundation – robots, AI agents, & autonomous systems can see, localize, understand, & operate in the environments that matter most.

Pixel streaming historically has not made sense for businesses (tough margins) but it's starting to make sense, and companies are noticing. The tech is becoming mature quickly. We've shipped so many critical features in over the last few months that I wanted to give an update!

Cesium 3DGS integration. The wave continues!

きたー！！！ 3DGS to 3D Tiles作るぞーーー！

Expand is now available to everyone! Extend your world in any direction you choose: around corners, into rooms, and beyond what you can see 👀

This might just be the trippiest thing I’ve ever created for @theworldlabs World Jam. Made with Marble 1.1 and images from nano banana upscale to 4k. Not what I was looking for but way more interesting than expected. #3dgs #worldfoundationmodels #worldmodels #3d #threejs

Autodesk building in 3DGS: High fidelity Digital Twins with Autodesk Platform Services! I think it’s going to become standard to toggle between polygons (BIM) and particles (3DGS). I love to see this! APS + 3DGS. I smell a @theworldlabs integration. linkedin.com/posts/mibeale_…

Three.js r184 released ⛅️ threejs.org/changelog/?r184

Lyra 2.0 just dropped today! (right after the Spark.js 2.0 drop yesterday) The momentum towards ultra high fidelity experiences in the web is mind bending. @sparkjsdev @NVIDIAAIDev #citation" target="_blank" rel="nofollow noopener">research.nvidia.com/labs/sil/proje…

Today, we released Lyra 2.0, a framework for generating persistent, explorable 3D worlds at scale, from NVIDIA Research. Generating large-scale, complex environments is difficult for AI models. Current models often “forget” what spaces look like and lose track of movement over time, causing objects to shift, blur, or appear inconsistent. This prevents them from creating the reliable 3D environments required for downstream simulations. Lyra 2.0 solves these issues by: ✅ Maintaining per-frame 3D geometry to retrieve past frames and establish spatial correspondences ✅ Using self-augmented training to correct its own temporal drifting. Lyra 2.0 turns an image into a 3D world you can walk through, look back, and drop a robot into for real-time rendering, simulation, and immersive applications. ➡️ Learn more: research.nvidia.com/labs/sil/proje… 📄 Read the paper: arxiv.org/abs/2604.13036

We built Spark 2.0 to bring the most ambitious 3DGS worlds to the web🌍 Making high-fidelity 3D accessible on any device is a big step for spatial storytelling. We’re proud to share this open-source renderer capable of streaming 100M+ 3DGS to unlock a new era of world building!

@sparkjsdev THIS IS HUGE!! Great work to the whole team!

Spark 2.0 is here! 🚀 We’re redefining what’s possible on the web with a streamable LoD system for 3D Gaussian Splatting. Built on Three.js, you can now stream massive 100M+ splat worlds to any device from mobile to VR using WebGL2. All open-source. Dive into the tech 👇

3DGS bugs. Feels like a glimpse into my brain these days. @sparkjsdev @threejs #3dgs #sparkjs #gaussiansplat #3d #SfM #threejs

@willeastcott Thanks for making an awesome tool 🫡

@ajc_builds Thanks Adam - great to hear you're finding SuperSplat useful!

In the last several months I've spent 𝐚 𝐥𝐨𝐭 of time exploring new tools across 3D capture, world models, 3dgs generation, video generation (from 3dgs assets, of course), and software development workflows to connect the dots. Here's what i've been exploring! 🧵

- Happy-coder, mobile phone connection to the CLI on my laptop back at home. I get a notification when my agent needs input from me, I give it input and then it gets back to work. Getting outside no longer hurts progress.

- Superwhisper. voice-to-text. It turns out we can talk faster than we can type. Massive productivity unlock, connect it to Claude Code. I think we are all going to be talking to our computers a lot more than typing. More robust prompts = better results.

𝐃𝐞𝐯𝐞𝐥𝐨𝐩𝐞𝐫 𝐭𝐨𝐨𝐥𝐢𝐧𝐠 𝐚𝐧𝐝 𝐰𝐨𝐫𝐤𝐟𝐥𝐨𝐰𝐬: - Anthropic's Claude Code, mind-bendingly good. It is an agentic coding tool that can run multiple agents async, deep context, skills, great UX and all through the CLI.

𝐕𝐢𝐝𝐞𝐨 𝐠𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐨𝐧: - ComfyUI, using Kling, Veo3, and Runway for video generation and camera path interpolation experiments. There are some really exciting things happening inside ComfyUI right now, definitely check it out.