Machine Learning

Some argue that bots should be entitled to ingest any content they see, because people can.

Nvidia unveils TensorRT-LLM software that promises a major boost for LLM interference.

Amazon's EC2 M7i and M7i-Flex instances run on Intel's custom Sapphire Rapids processors with AMX, DSA, IAA, and QAT accelerators.

TACC's Stampede3 packs Sapphire Rapids with HBM2E memory and Ponte Vecchio compute GPUs.

Bloomberg reports that Apple has a framework for large language models, called Ajax, and is using it to test an internal chatbot that some are calling "Apple GPT."

Big names come together to refine Ethernet standards for AI and high-performance computing.

Hermy65 has built a Raspberry Pi smart bird feeder that can recognize birds who stop by for a snack and documents them so you can see who visited later.

A wholly AI-designed RISC-V CPU was created from scratch in five hours and booted Linux, performing on par with an i486.

AMD has sensed a growing demand for AI and LLM computing acceleration and will thus add ROCm support to new RDNA 3 workstation and consumer GPUs this fall.

Ed Miller leads a team that plans to integrate Raspberry Pis into their black bear conservation efforts by tracking them with trail cameras and AI.