Pinned Tweet
The recent disaster in Nepal made me look for similar mountain hazards around the world.
I built Glacier Watch Atlas β a map of possible downstream routes and nearby communities, using scientific publications and official monitoring sources.
glacierwatchatlas.com
Each location includes links to the scientific sources or official monitoring source used to document it.
The routes shown are historical or terrain-based β they are not forecasts.
Found an issue, and source or a missing location? [email protected]
@ReutersGraphics @USGS @GlacierHazards @DaveRounce
1
148
Klim Nova π§ββοΈ retweeted
French Conspiracy Commentator Dimitri explains precisely whatβs happening in France - this Guy is absolutely Top Class
Everyone needs to watch this
Klim Nova π§ββοΈ retweeted
life is literally a constant cycle of losing your spark and then finding it again
Klim Nova π§ββοΈ retweeted
Eleven v4 is INSANE! π€―
Here's my 44-sec spec ad for it.
I wrote a script of everything an AI voice "can't do." Then made Eleven v4 read it out loud.
Sound on π
π€ Made with AI
Klim Nova π§ββοΈ retweeted
Wow Nvidia has just released a tool to turn any image into an explorable 3D world
And they made it 100% open source π₯
- Model available on Hugging Face
- UI code available on GitHub
Lyra 2.0 creates a world you can walk through, turn around in, and even drop a robot into for simulation.
Klim Nova π§ββοΈ retweeted
Step into the craziest visualization of the fourth dimension you have ever seen
Jev is the "Internet" moment for the AI industry
It tells your agents and LLMs what to do next, in milliseconds and at almost zero cost
If you set it up correctly, you will have the AI engineerβs stack for 2028
In this article, I show you how
Klim Nova π§ββοΈ retweeted
π₯ Today, we are truly excited to announce our technical prototype, the Generative World Simulation system, which integrates JINGοΌιοΌ, an interactive experience model, with DAOοΌιοΌ, a computable shared-world engine.
The coupled model and engine connect first-person experience with a shared world that continues to evolve beyond any individual observer.
Conditioned on actions and observation history, JING enables agent navigate, manipulate, and communicate from a first-person perspective in the world. Watch our demo video to see it in action!
On the official WBench leaderboard as of September 17, 2026, XGEN-JING ranked #1 on the Full split, and #2 on the Navi split. π
DAO maintains shared world state and rules, computes the consequences of actions, and provides JING with only what the current observer can perceive. It also supports autonomous agent decision-making, enabling agents to act independently within an evolving shared world.
Together, DAO and JING move beyond generating the next frame toward simulating the world behind it. This marks a small step towards OASIS: not just a world that responds to you, but a worldβand a societyβthat evolves with and without you. πͺ
Explore XGEN Labsο½:
π Website: xgenlabs.ai/
π€ HF: huggingface.co/XGENlabs/XGENβ¦
π¦ GitHub: github.com/XGEN-Labs/XGEN-JIβ¦
Klim Nova π§ββοΈ retweeted
This is not a videogame.
No engine. No 3D models. No code.
I built it with 3 tools:
Midjourney 8.2 for the character and the world.
Seedance 2.5 for every shot.
Topaz Astra to upscale it.
The trick is not the tools. It's how you prompt.
I described the camera like a game camera. Rigid follow distance. Snap turns. A HUD locked to the screen. The model did the rest.
Here's what I learned:
Lock your character first. One clean character sheet. Reference it in every generation. This is what stops the drift.
Prompt the medium, not just the scene. "Gameplay capture" gives you a different image than "cinematic shot". Flat exposure, deep focus, no film grain. That's what makes it read as a game.
Fights come out stiff. Everyone takes turns. Tell the model everything happens at once and re-render until it does.
Generate short clips. Cut them yourself. Add music in post. You have more control than one long generation will ever give you.
Now the bigger picture.
Video models are becoming world models. They are learning how things move, react, collide. The gap between "video that looks like a game" and "a game you can play" is closing.
Soon you won't prompt a trailer. You'll prompt the game itself. The world, the character, the rules. Then you walk in.
When that happens, the engine won't be the skill.
Your ability to direct worlds will be.
Klim Nova π§ββοΈ retweeted
We are announcing a $1,000,000 festival. Higgsfield Global Film Festival is here.
1. A $1,000,000 contest, 14 winners, Academy Award-winning jury members
2. Hell Grind, Zephyr, and Mork open-sourced, every prompt public
3. Full breakdowns of how our best films were made
Read below:
Klim Nova π§ββοΈ retweeted
Someone used Claude Code with Opus 5 to build SNOWFLOW, a browser WebGPU snow and waterbending demo with persistent terrain deformation in 9 hours.
- Full-Stack Graphics Pipeline: Synthesized custom WGSL shaders, WebGPU pipelines, and Babylon.js terrain logic from scratch.
- Interactive Terrain Deformation: Renders persistent snow trails, berms, and water-spell displacement that heal dynamically over time.
- Visual Self-Correction: Opus 5 iterated on visual polish and shader bugs directly from browser screenshots.
- 9-Hour Build Window: Delivered a production-ready WebGPU tech demo in 9 hours using ~4 million tokens.
Klim Nova π§ββοΈ retweeted
Chaotic physics-based airline crew co-op game 'Dear Passengers' has been announced.
Launching in 2026 for PC
Steam page: store.steampowered.com/app/4β¦





















