Viggle AI

Viggle AI · Launch Video Breakdown: Hook, Pacing & Motion Design

JST-2, a full-stack physics-native world foundation model

0:00 · The Hook · The Four-Year Simulation Question
0:00 / 0:00
AI & MLProductionOctober 19, 2026

Founder philosophical question & direct address

9.8

Cuts / min

1:44

Runtime

788K

Views

1,586

Likes

0

Reposts

0

Replies

Scene-by-scene timeline & spoken transcript

  1. The Hook

    The Four-Year Simulation Question

    “For the past four years, we've been focused on one question: If the world we live in could be simulated, what would its architecture look like? That question is what our company Viggle was built to answer.”

    On screen
    4 YEARS 4 YEARS 1 QUESTION If the world we live in could be simulated, what would its architecture look like? Hang Chu Co-founder and CEO
    Camera
    Static medium shot with subtle digital push-in on presenter.
    Motion
    Text fade-ins and animated kinetic typography beside speaker.
  2. Problem Agitation

    Pixels vs True 3D Modeling

    “Most video models only learn what the world looks like through pixels. Our team built JST to model what the world actually is.”

    On screen
    Generated with JST-2
    Camera
    Smooth virtual fly-through pans across 3D generative scenes.
    Motion
    Rapid montage cuts of high-fidelity rendered architectural spaces.
  3. Product Reveal

    Physics-Native Token Architecture

    “Persistent 3D atoms with learned vectors encoding their physical attributes and dynamics over time. Everything was built around this physics-native principle: from tokenization, architecture, pre- and post-training, and our data engine—the full stack.”

    On screen
    Physics-Native Token Position Explicit xyz · 0.46, 0.40, 0.34 Attributes Learned vector Dynamics Learned vector Tokenization Architecture Pre-training Post-training Data engine Full-stack physics-native Multimodal prompt JST generator JST decoder Image output Image input JST encoder Persistent atoms in 3D space Viewpoint Motion / force 3D Gaussian splats
    Camera
    Static framed presenter cutting to 2D technical diagram overview.
    Motion
    Animated isometric point cloud and expanding layered architecture schematic.
  4. Feature Teaser

    JST-2 Capabilities & Real-Time Rendering

    “The result is JST-2. The world's first full-stack, physics-native world foundation model. One model generates characters, motion, and scenes. JST-2 outperforms every specialist model we benchmarked across multiple tasks. It generates a full scene in about a second for under a cent. And every JST-2 world is real 3D. Generated once, then render locally in the browser from any angle without rerunning the model.”

    On screen
    JST-2 JST-2 Full-stack, physics-native World foundation model Characters Motion Scenes Generated with JST-2 Generate a scene in ~1s, < 1 cent Generate once Render locally
    Camera
    Dynamic orbiting 3D camera paths around generated environments.
    Motion
    On-screen metric callouts, camera frustum HUD overlays, and freeform camera orbiting.
  5. Feature Teaser

    Interactive Robotics Simulation

    “The same efficiency changes what's possible in robotics. In this demo, JST-2 generates the environments, people, and actions, pointing to a scalable path to robot training. JST-3 will further replace rule-based physics with learned physics.”

    On screen
    A scene generated by JST-2 Generate characters and their behavior together Control interactions through language World view Robot view Real-time generation Have the robot pick up the box on the left. Picking up the box. Add a woman walking out of the kitchen. Character and motion generated. Add a father and child. Characters generated. Have the robot hand the box to the child. Handing over the box.
    Camera
    Third-person tracking camera orbiting robotic manipulation task.
    Motion
    Split-screen dashboard with live prompt stream and synchronized multi-viewport camera feeds.
  6. Call to Action

    Synthesis and Call to Action

    “Four years ago, we asked what it would take to simulate the world. JST-2 proves the architecture works with real quality, efficiency, and scale. Try JST-2 for free today at viggle.ai/jst2, and read the architecture and benchmarks in our research blog.”

    On screen
    VIGGLE Try for free viggle.ai/jst2 | Try for free API & MCP available
    Camera
    Presenter close-up cutting to smooth wave transition and centered title card.
    Motion
    Fluid organic gradient wave morphing into centered CTA typography.

Related AI & ML Product Launches

Explore all AI & ML launches →
Grok Bot 1.0 — AI teammates for your team
@bot
AI & ML
@bot
Grok Bot 1.0 — AI teammates for your team@bot
Tauvus
@tavus
AI & ML
@tavus
Tauvus@tavus
Fish Audio
@FishAudio
AI & ML
@FishAudio
Fish Audio@FishAudio