Nvidia partners with six major financial institutions to launch compute financing platforms, while China emerges as a leading player in the race to improve weather prediction through AI. Here are this week’s big stories from the AI revolution

NVIDIA just released retargeted robot motion and simulated execution data on Hugging Face 121,500 robot episodes derived from human demonstrations, ready for robotics research.

NVIDIA Nemotron 3.5 Lightning is now live on OpenRouter. A 30B hybrid MoE with 3B active params, distilled from Nemotron 3 Ultra. Built for high-volume, specialized AI agent workloads, delivering up to 4× higher throughput and up to 30% faster task completion compared to similar models in its class.

NVIDIA is reportedly working on a feature that could let future GeForce GPUs use an SSD as extra VRAM. When a graphics card runs out of VRAM, it could use data stored on a fast NVMe SSD instead. Your SSD won’t be as fast as real VRAM, but it could help when a game or AI app needs more memory than your graphics card has. That could mean fewer stutters and better performance in some situations. The feature is reportedly based on RTX IO and Microsoft’s DirectStorage technology.

NVIDIA canceled a customer’s $4,600 order for an ASUS ROG Astral GeForce RTX 5090 after ASUS declined to honor the pre-price-hike price. The customer was instructed to place a new order at $5,100, a $500 increase. The customer says NVIDIA blamed ASUS for the cancellation, while ASUS said it wasn’t responsible.

Nvidia CEO Jensen “@Tesla stack is the most advanced autonomous vehicle stack in the world. I’m fairly certain they were already using end-to-end AI. Whether their AI did reasoning or not in somewhat secondary to that first part.” @elonmusk

NVIDIA CEO Jensen Huang was stunned by what Elon Musk's team pulled off. "What Elon and the team achieved is singular. It has never been done before." Building a massive AI supercomputer is usually measured in years. Yet 100,000 GPUs were brought online and running in just 19 days. Not months. Not years. Nineteen days. It's the kind of execution speed that rewrites expectations for what large-scale engineering teams can accomplish.