I've been yelling and screaming that the future is world models after Oliver Cameron showed me how. World models are not LLMs (large language models). World models are trained mostly with video data or other kinds of data that isn't really text.
MULTIMODAL AI
-
Rapid progress from seven-fingered hands to cinematic movies
By
–
Yeah, we're in the black and white TV era of this new form of media. It'll improve; it'll just take time. It's not much time, either. You know, 24 months ago, the models could only create hands with seven fingers; now they're creating cinematic movies and things like that. In
-
Grok Imagine API Launches as Top Video Model with SpaceX IPO
By
–
[AINews] @Xai Grok Imagine API – the #1 Model, Best Pricing and Latency, merging with SpaceX for IPO
-
AI Tech Trends 2026: Systems, Agent Orchestration, Multi-Modal Dominance
By
–
AI & tech trends that will shape 2026 — Systems, agent orchestration and multi‑modal AI dominate strategic plans. #AI #CES2026 #MWC26 #IoT @IBM @IBMNews https://
ibm.com/think/news/ai-
tech-trends-predictions-2026
… -
Google Labs Releases Project Genie Foundation World Model
By
–
🚨Google Labs just released Project Genie 🚨
— Futurepedia – Learn to Leverage AI (@futurepedia_io) 30 janvier 2026
A foundation world model that generates interactive, playable environments in real-time.
Unlike traditional engines, Genie builds the world, physics, and character mechanics simultaneously from a single text or image prompt.
We are… pic.twitter.com/femihZ9ZNwGoogle Labs just released Project Genie A foundation world model that generates interactive, playable environments in real-time. Unlike traditional engines, Genie builds the world, physics, and character mechanics simultaneously from a single text or image prompt. We are
-
Qwen Open-Sources TTS and ASR Models for Free Voice AI
By
–
Lately, Qwen has been making a lot of noise—last week they open-sourced a few TTS models, and last night they open-sourced ASR too. The current three-part Voice AI setup, paired with a fully domestic open-source solution, is completely free. LLM options: Any domestic
-
AI generates Economist article and podcast via NotebookLM
By
–
It can do whatever I ask. I asked it to make me an Economist magazine article out of it and it did. Then you can copy that over to @NotebookLM and have that make a podcast out of it.
-
Genie 3 live interactive video demo from Nano Banana Pro prompt
By
–
Note this video is sped up 2x for illustration. Genie 3 generates live, interactive video at 24fps 720p Initial frame generated w/ Nano Banana Pro, supplied to Genie 3 with the Environment/Character text above as the prompt
-
Project Genie: Advanced AI Models Web Application Prototype
By
–
You might be wondering… How does Project Genie work?🤔
— Google AI (@GoogleAI) 29 janvier 2026
Great question.
Project Genie is a prototype web app powered by several of our most advanced AI models, each bringing a unique capability to the equation. From Genie 3's ability to simulate the physics and interactions… pic.twitter.com/hn3MouW4eqYou might be wondering… How does Project Genie work? Great question. Project Genie is a prototype web app powered by several of our most advanced AI models, each bringing a unique capability to the equation. From Genie 3's ability to simulate the physics and interactions