Ajion

I am many things and I love to build and create:
@primalverses @NexusWars_, @HOSTD4_ @Puniks_ @Ajion_ @drdisarray_

[Ajion @Ajion]

I just realized how the future of gaming will look like lol

Real time AI layer on top of barely finished games, no gfx, of effect, all fake just bare minimum work to high fidelity work

The distance between 1980s and 2000, to 2026 is the samish

Look how much GFX came from 80s to 2000, and where we are in 2026, but we stalling in what can be achieved now, so here comes the AI

Create special video cards not to compute vertexes but to simulate pixels, some kind of dual video card.

All the future video cards need to do is process images of rendered pixels at 30-60fps and render out images bellow,

And suddenly all games can look and feel differently and then entire gaming paradigm changes, hell all digital media changes, movies, tv experience everything.

You can watch or play however u like in any style, a new digital revolution if you will.

This means censorship on AI is going to get strong real strong, we now in a wild west but in a few years once the shitty Hollywood is going to get into it get ready the same bs that we had with p2p, but much worse.

This AI piracy, local models, open source is going to be fighting the same battles that torrents did.

We are heading into the world of simulation, an augmented layer on top of physical world veiled by the AI filter

And with addition of Neural link, and that would mean what exactly, on demand ai filter taping into our brains to change our perception of reality.

Prison is no longer physical, but a mental cage where you don't know where the exit is from your own house.

Welcome to 2046
check this out:
fallout 2, xcom

[Three.js Resources @threejsresource]

Stack shaders like Photoshop layers. Shader Lab lets you create, stack & animate shaders CRT, glitch, bloom, dithering with keyframes and live preview.

Creator: @basementstudio

Check it out: https://t.co/va0LaIqGGh

#Threejs #WebGL #Shaders

[Google Research @GoogleResearch]

Introducing D4RT: A unified AI model for 4D scene reconstruction and tracking across space and time. 🎯 Catch the demo with Skanda Koppula at 12 pm at our #CVPR2026 Google booth kiosk! https://t.co/p6SclNe1zi @GoogleDeepMind

[Julian Fella @juli_fella]

Annnimate v3 is live today.

Adrian and I almost shelved it in March. v2 wasn't the right product, so we threw it out and rebuilt the whole thing.

It's the version we wanted from the start.

-> Link in profile

[clankr @clankrmedia]

Wow! Motion capture studios not gonna love this!

Just check this insane video.

For years, capturing human motion meant markers, skin-tight suits, and hours of cleanup.

MAMMA just asks for a few synced cameras pointed at the scene.

Out comes a full 3D body for every person, every frame.

No suits. No markers.

The clever bit: instead of tracking a handful of joints, it reads hundreds of points.

And it actually understands contact.

It knows when a foot touches the ground, when two people are holding each other.

So feet stop sliding and bodies stop passing through each other, even when dancers are tangled up close.

When @Michael_J_Black calls this maybe the biggest day in 3D capture history, you pay attention.

The kicker? It's basically as accurate as the gold-standard Vicon systems studios pay a fortune for.

A multi-day pipeline drops to a single day. It even works with 4 iPhones.

Here's why roboticists should care: clean, realistic human motion at scale, without the expensive rig.

The thing holding humanoids back was never really the algorithm. It was the data.

Keep up good work the @Hanzcun, @soyong_shin, @AYiannakidis and the rest of the MAMMA team!

[Sanu Sagar @rocklet_]

https://t.co/7PUuteDd1Z

[Ajion @Ajion]

@Pumpfun If this actually happens, the World Cup will sue the living crap out of @Pumpfun good luck ya all

[Pump.fun @Pumpfun]

Introducing pump fun GO: Pay ANYONE to do ANYTHING

Create & complete bounties for ANY task and leverage the power of humans & money across the globe

The world is at your fingertips. It’s time to GO 👇

[Jiachi @huozhi]

this font looks so good

[siddharth ahuja @sidahuj]

Blender MCP is at 22k Github Stars with 25k daily active users!

I'm looking for devs excited about 3D and AI to help maintain the repo with me. DM if interested!

[Ajion @Ajion]

@boulabiar Draco has been around for awhile

[PlayCanvas @playcanvas]

🚀 Major upgrades just landed in SuperSplat, the free and open source platform for 3D Gaussian splatting.

Here is a 24-MILLION-Gaussian scan streaming live to a web browser. Near instant load time. Solid 60 fps.

How? A new compute-based WebGPU renderer + automatic LOD streaming. 🧵

[mrdoob @mrdoob]

Ported Google's Draco decoder to pure JavaScript.

https://t.co/jbXeB6AzsF

4.3× smaller than the WASM build, byte-for-byte identical output, often faster once you factor in load, init and parse.

[Arquivo Curioso @arquivocurioso]

Modelo 3D do Sistema Solar, considerando a atração gravitacional que o Sol exerce.

🎞️ cpge_2024/IG.

[yeet @Awk20000]

Patreon CEO Jack Conte delivers a message to Bricks & Minifigs after they sent an official takedown request for Reckless Ben’s videos

“We have in fact unfortunately determined that Bricks & Minifigs can stuff it, we’re keeping Ben’s page up”

(Via JackConteExtras on YT)

[el.cine @EHuanglu]

holy sht.. AI has automated UE5

you can build entire 3D interactive world with text prompt, everything is editable.. and the AI agent can even rig and animate your 3D characters..

you dont need 10 years of 3D skills to build game now

[Brian Armstrong @brian_armstrong]

Aging is arguably the root cause of most major diseases (loss of function in our cells). Four years ago, we made a bet that aging was treatable, and NewLimit was born.

NewLimit now has a prototype drug that reverses the age of some human cells (restores function they had when they were younger), and a clinical trial scheduled for next year (with more drug candidates in the pipeline).

Grateful to Founders Fund, Thrive, Greenoaks, and the rest of the investors for this latest round. @jacobkimmel and the team are just getting started.

[Kat ⊷ the Poet Engineer @poetengineer__]

experiment with a memory system that keeps rewriting itself:
a hopfield network remembers an alphabet. as memories decay, it begins to hallucinate glyphs it was never taught - forgetting becomes a way of inventing.

[AI Nerd @AINerdzz]

Microsoft Is Taking Screenshots of Your PC Disable These Settings Immediately

[Codetaur @codetaur]

so I ran into this little problem where the 500km^2 smoke data made it clear that there were other fires going on at the same time, and it was weird that they weren't visualized. so this 1-fire-dataviz project became a 50-fire-dataviz project

(this is also downsampled smoke that uses 8x less VRAM)

[Om Patel @om_patel5]

this guy vibe coded this entire motion gallery with opus 4.8

using ONE prompt

claude opus 4.8 >>> gpt 5.5