The AI ‘Slowdown’ Is an Antitrust Mess22m ago Microsoft exec called AI scraping ‘the largest theft of labor in human history,’ new unredacted filings reveal35m ago Anthropic Reports Claude Optimized 30+ Open-Source Biomolecular Models37m ago Gemini 3.8 Live Transforms Conversational AI46m ago AI Pioneer Andrew Ng Calls Extinction Fears ‘Science Fiction’50m ago Inside the suddenly explosive world of AI safety52m ago Calls for AI slowdown raise new challenges for open-weight models53m ago AI changes the ROI equation. Here’s how some have found success1h ago Influencers Are Using Meta’s AI-Glasses to Film Manipulative Feel-Good Slop of People in Public1h ago AI needs to have 'reasonable guidelines,' Palantir's Karp tells CNBC1h ago Claude Code’s revised projects adds AI orchestration, but local developers must wait1h ago McKinsey wants ambitious technologists, not just MBAs1h ago Uber employees say AI is doing everything from writing support chat responses to answering questions in Slack1h ago Run Terminal-Bench and other Harbor evals on Vercel Sandbox1h ago

The AI ‘Slowdown’ Is an Antitrust Mess22m ago Microsoft exec called AI scraping ‘the largest theft of labor in human history,’ new unredacted filings reveal35m ago Anthropic Reports Claude Optimized 30+ Open-Source Biomolecular Models37m ago Gemini 3.8 Live Transforms Conversational AI46m ago AI Pioneer Andrew Ng Calls Extinction Fears ‘Science Fiction’50m ago Inside the suddenly explosive world of AI safety52m ago Calls for AI slowdown raise new challenges for open-weight models53m ago AI changes the ROI equation. Here’s how some have found success1h ago Influencers Are Using Meta’s AI-Glasses to Film Manipulative Feel-Good Slop of People in Public1h ago AI needs to have 'reasonable guidelines,' Palantir's Karp tells CNBC1h ago Claude Code’s revised projects adds AI orchestration, but local developers must wait1h ago McKinsey wants ambitious technologists, not just MBAs1h ago Uber employees say AI is doing everything from writing support chat responses to answering questions in Slack1h ago Run Terminal-Bench and other Harbor evals on Vercel Sandbox1h ago

Chips & Compute Machine Learning5 min reading time

NVIDIA Vera Rubin NVL72 Posts First MLPerf Inference Preview Results

Unite.AIPublished 1 day ago

NVIDIA announced its Vera Rubin NVL72 system's first MLPerf Inference v6.1 preview results, showing up to 3.7x higher throughput than its GB300 NVL72 system on the Qwen3-VL benchmark. The system also achieved 2.5x higher throughput on DeepSeek-R1, demonstrating significant performance improvements through hardware-software codesign.

#deepseek-r1 #inference-benchmarking #mlperf-inference #nvidia #qwen3-vl #vera-rubin-nvl72

More in Chips & Compute

Chips & Compute4 min read

Crusoe Secures $3.9B Series F at $30.9B Valuation to Build AI Factories

Covered by 2 sources3h ago

Chips & Compute

Huawei Accelerates Launch of New AI Chip to Take On Nvidia

Covered by 2 sources21h ago

Chips & Compute

Nvidia’s Huang Expects to Sell Twice as Many Chips Next Year

Covered by 2 sources5h ago