Rippertnt·Oct 26Four Robot Cameras, One NPU, Every Frame: NPU-First Perception for Physical AIonAIR-vision, the vision engine of the onAIR framework, measured on an Intel® Core™ Ultra robotics kit. General release in November 2026…
Rippertnt·Oct 15Instant Responses for Physical AI on Intel GPUsIntroducing onAIR-infer, the inference engine of Circulus’s onAIR framework: a C++ LLM and VLM server for robot fleets and for the robots…
Rippertnt·Sep 22Priced Out of NVIDIA? We Benchmarked Five LLM Engines on Intel’s 32 GB Arc Pro B70The card wasn’t the bottleneck. Five serving engines on identical silicon came out 3.9× apart — and running it five times found bugs in our…
Rippertnt·Aug 27Physical AI Doesn’t Get to Pick a VendorWe build robots on Intel, AMD and NVIDIA silicon at the same time. So we built the instrument that watches all of it — and open-sourced it…
Rippertnt·Aug 20Intel Has CPU, GPU, and NPU. Why Doesn’t It Have an NVIDIA-SMI?Building XPU-TOP: one table for CPU, GPU and NPU, on Linux and Windows
Rippertnt·Aug 15AI That Nobody Has to Ask Permission to UseOn Korea’s 81st Liberation Day, we are open-sourcing CanversON — a full generative AI studio that runs on an ordinary laptop, with the…
Rippertnt·Apr 30The $949 GPU That Embarrassed a $3,099 Rival — Intel ARC Pro B70 32GBHow Intel’s budget pro GPU beat AMD’s $1,349 card — and embarrassed a $3,099 rival on 32B AI inference
Rippertnt·Feb 20Intel Panther Lake vs. NVIDIA Jetson Thor: Which “Brain” Should Power Your Humanoid Robot?A Real-World Concurrent Benchmark for Physical AI — Performance, Power, Safety, and the “Robotic Reflex” Problem