AI Briefing#nvidia
The latest AI and developer news about #nvidia, with the original source and a short summary.
The latest AI and developer news about #nvidia, with the original source and a short summary.
GPT-6 Astra Ultrafast is now available in the OpenAI API and to eligible ChatGPT Work and Codex users, offering up to 8x faster token generation than Astra Standard.
SemiAnalysis data shows NVIDIA Vera Rubin NVL72 systems deliver over 30x higher throughput per megawatt than GB300 NVL72.
Applications are due October 30, 2026, and require a mandatory in-person internship in summer 2027.
Cognition benchmarks show Vera Rubin NVL72 delivers up to 4.8x higher token throughput for SWE-2 inference compared to GB200 NVL72.
The open-source project replicates the 71-block Swin/ViT architecture of DLSS-NR build 310.8.0 using FP8 tensor cores, achieving byte-for-byte intermediate matches with the original.
Kumo Tabular achieves state-of-the-art accuracy on TabArena with ELO 1950 while being 17x faster than LimiX-2, trained entirely on synthetic data.
Presents an infrastructure strategy connecting simulation to edge deployment using SageMaker and IoT Greengrass
The new authorization brings Nvidia's total remaining buyback capacity to $235 billion, the largest in history.
The 550B-parameter model scored 535.4 out of 600 on the IOI 2026 problem set, surpassing the top human contestant's score of 498.27.
Huang's comments contradict Treasury Secretary Scott Bessent, who recently labeled distillation 'theft' and threatened sanctions against overseas companies using it.
Liquid AI has released LFM2.5-VL-3B-DSpark, a draft model for speculative decoding of its VLM LFM2.5-VL-3B, which improves decoding speed by up to 3.13x on the Apple M5 Max.
NVIDIA announced the Open Agent Safety Platform, an open software platform for AI security, while Anthropic collaborated to integrate its Claude Managed Agents with NVIDIA's OpenShell to provide layered security and control.
The platform combines the open-source NVIDIA OpenShell runtime and the NVIDIA Sentry reference system design to enable full-stack governance across software, hardware, compute, and robotics systems.
A commentator argues that Jensen Huang's insistence on shipping only safe products logically demands shutting down frontier AI labs that cannot guarantee absolute safety, while highlighting contradictions in his views on AI risk and regulation.
The dataset, generated using AlphaFold2 and NVIDIA BioNeMo, includes 30% of protein interactions that are completely new to science.
Ultimate members can stream CONTROL Resonant with RTX 5080-class performance and receive the game free with a 12-month membership purchased by Sept. 27.
CLM-8B achieves SOTA on agent coding benchmarks by separately encoding and caching states and actions.
It presents migration procedures and performance tuning tips for scaling the SO-101 robot arm to up to 2,048 parallel GPU environments.
An NVIDIA verification engineer introduced the process of ensuring large-scale stability for AI hardware.
An open-source project has been released that enables running NVIDIA's Parakeet speech recognition model on the JVM with native-like performance.
NVIDIA has released Nemotron 3 Diarization, a 100M parameter open-weight model that ranked first on the Voice Arena Diarization-Bench.
NVIDIA introduced a new framework for AI agent evaluation that emphasizes task completion and cost efficiency over tool-calling accuracy.
NVIDIA unveiled its strategy and partnerships for accelerating AI and HPC across Southeast Asia at AI Day Singapore, with Sea Limited becoming the first in ASEAN to adopt the NVIDIA Vera Rubin platform.
NVIDIA has released Isaac ROS 5.0, featuring enhanced AI agent workflows and GPU acceleration capabilities.