AIHardware
Inside NVIDIA Rubin GPU Architecture: Powering the Era of Agentic AI
NVIDIA's Rubin GPU architecture advances AI hardware to support always-on AI factories powering complex agentic AI workflows at scale.
Tech News
The auto-updated technology brief
105 stories
ProgrammingHardware
Make Long-Running NVIDIA TensorRT Engine Builds Observable and Cancelable in Python or C++
NVIDIA introduces ways to monitor and cancel long-running TensorRT engine builds in Python or C++, addressing issues with large models and new GPUs causing long build times.
HardwareProduct Release
Lenovo's first Googlebooks have leaked
Lenovo has developed new laptops and a 2-in-1 device for the Googlebook initiative, which have recently leaked.
ProgrammingHardware
Run High-Performance Core Math at Scale with NVIDIA nvmath-python
NVIDIA nvmath-python bridges Python scientific computing with CUDA-X math libraries, enabling high-performance math operations on CPUs, GPUs, and multi-node systems without disrupting workflows.
MobileSecurity
A $2 sticker lets bypass Meta Glasses' anti-creep feature
Meta's smart glasses are designed to alert bystanders when recording, but this safety feature can be easily bypassed with a simple $2 sticker.
SecurityHardware
Defcon's new badge is a security key you can see inside
Defcon's 2026 badge, designed by Andrew “bunnie” Huang, features an innovative open source chip that enhances security and transparency, allowing hackers to inspect and reuse their badges.
AIResearch
Six Agent Harness Capabilities for Higher Model Performance
Building an effective AI agent requires more than selecting the right models; the surrounding harness architecture significantly impacts outcomes, including benchmark results and token costs.
AIOpen Source
NVIDIA Ising Enables Fully Automated Quantum Computer Calibration with Enhanced In-Context Learning
NVIDIA releases Ising Calibration 1.5, an open source vision language model that automates quantum processor tuning by interpreting diagnostic outputs without prior training examples.
AIHardware
NVIDIA Exemplar Cloud: Lessons for Unlocking Full Performance on AI Infrastructure
Two AI computing clusters built from identical NVIDIA H100, GB200 NVL72, or GB300 NVL72 systems can deliver materially different training throughput due to configuration choices.