Alibaba released Qwen-UI-Agent, an open-weight GUI agent that leads mobile benchmarks with 92.2% on real-device tests. The model unifies phone, desktop, and bro...
New coverage from across AI, software, and hardware.
Anthropic made Computer Use, Skills API, and Files API generally available on the Claude Platform with a new Browser Use tool for web apps. The release adds multi-action turns, HIPAA eligibility, and 1 TB org storage for production agent workloads.
SenseTime fully open-sourced SenseNova U1, a native unified multimodal model that fuses vision and language without a vision encoder or VAE. The 8B-parameter release matches commercial models on infographic generation and adds native 4K output in its U1.5 update.
NVIDIA took a minority stake in data-center site developer Cloverleaf Infrastructure to accelerate AI factory construction across the U.S. The partnership integrates NVIDIA's DSX platform early in site design to maximize compute output per megawatt.
OpenAI released a major Agents SDK update adding native sandbox execution and a model-native harness for production agent workloads. The Python-first release includes configurable memory, Codex-like filesystem tools, and a Manifest abstraction for portable workspaces across seven sandbox providers.
Amazon Science released SOP-Bench, an open benchmark with 2,000+ tasks from real business SOPs across twelve domains. The framework pairs authentic procedures with working tools and ground-truth answers so teams can validate agents before production deployment.
NVIDIA launched DSX MaxLPS, a full-stack platform that dynamically reallocates stranded power across GPU racks to fit up to 40% more compute in the same facility envelope. The system combines real-time power steering, workload-aware profiles, and 45°C liquid cooling to boost performance per watt by 1.3–1.5x on Blackwell and Vera Rubin systems.
Perplexity blocked Time's markdown ads served only to AI crawlers, calling the practice deceptive and warning publishers risk a trust-score downgrade. The clash tests whether agent-facing ad inventory is a legitimate revenue channel or cloaking by another name.
Hugging Face research shows top ASR models reproduce benchmark transcripts even when audio contradicts them. The study found models with the lowest reported error rates were most likely to regurgitate incorrect reference texts, overstating real-world performance.
DARPA and the Air Force launched live AI dogfighting tests using VENOM-modified F-16s at Eglin AFB. The campaign moves autonomy development from a one-off testbed to standard fleet jets with real sensors.
