Jake Steinerman 🌎

@jasteinerman • 8,816 subscribers

DevRel @CesiumJS 🌎 | ex-Meta, Spatial | Go Blue 🏈

Shorts

92,257 views

35,532 views

29,862 views

20,932 views

Videos

sweetdream.ai

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Private Show

Join now for exclusive access

Free preview available • Premium content

1,526,946 views • 1 month ago

1,817,477 views • 2 months ago

1,138,697 views • 8 months ago

198,239 views • 8 months ago

249,236 views • 1 year ago

45,124 views • 3 months ago

83,012 views • 8 months ago

50,065 views • 8 months ago

62,055 views • 1 year ago

37,994 views • 9 months ago

38,994 views • 1 year ago

29,722 views • 1 year ago

32,968 views • 1 year ago

17,387 views • 8 months ago

12,290 views • 8 months ago

No more content to load

Live Cam

Jake Steinerman 🌎

Shorts

Today, we’re introducing Meta’s latest 3D foundation model, AssetGen 2.0, which was designed to create high-quality 3D assets from text and image prompts. AssetGen 2.0 consists of two models developed within Meta: one to generate 3D meshes and another to generate textures. Read More:

Wow - Meta Ray-Ban Display and the Meta Neural Band have been selected as one of 2025's "Best Inventions" by TIME!

In the new Meta XR SDK (v83), we've made huge hand tracking improvements, including big upgrades in throwing interactions. Get this free sample scene in our Interaction SDK Samples:

Announcing the Immersive Web SDK (IWSDK)! Now developers can leverage the capabilities of the Meta Quest, all from a browser-based experience. 👐 Hand Tracking & Controller Support 😎 Support for mixed reality passthrough 🔊 Spatial Audio 🧑‍💻 Built on top of Three.js A ton more:

Videos

Watch Anya Live

The new Atlas world model is literally black magic. This shouldn't be possible from just 3 cameras 🤯

there's zero need to destroy books in order to scan them, when scanners like this have existed for years and can do 2,500 pages/hour

tHEres no gAmePLay ItS jUst ai SLoP yOU canT evEN dO anYThInG THIS THING IS CREATING 3D WORLDS AND RIGGED CHARACTERS FROM JUST SOME TEXT IN SECONDS #genie3

2022: this is just really bad chat 2023: this is just pixelated images 2024: this is just nonsensical videos 2025: this is just poorly made 3D meshes 2026: this is just a bad video game no one will ever play 🙃 #Genie3

The future arrives tomorrow.

I wanted to better understand the situation with the collapsing building in NYC, so I had Fable build an architecturally-accurate 3D model of the building (based off schematics), place the sagging beams, AND implement an animation of this should be remediated. Link below

And to think, this is the worst this tech will ever be.

“It only gives you a minute of content” “But you can’t interact with anything” “It’s only for Ultra subscribers in the US.” Then you’re missing the point. #Genie3

Funny you should mention that - we just announced that very thing - prompt &gt;3D world, is coming soon

Meta just launched an immersive language learning app for XR! And the best part? It's free and open sourced for everyone, including developers Get the code: Play for free:

Meta just announced that anyone will soon be able to add fully-embodied conversational LLM NPCs into their worlds, totally for free.

Horizon just added generative 3D tools right into the editor 🤯🤯🤯🤯

The Google Deepmind Project Genie work is mysterious but important Absolutely wild that this was made with just a prompt

Two years ago I “vibe designed” my dream car - the “Pulsar One-6”. And now thanks to #Genie3, I can actually take it for a spin.

Funny you should mention that - we just announced that very thing - prompt >3D world, is coming soon