
AWS adds KV cache aware routing to SageMaker AI real-time endpoints
Amazon SageMaker AI now offers KV-aware routing for real-time endpoints, sending requests to instances that already hold matching cached prompt content.
AI news from November 2026. Short posts, checked against the source, each with a link to it.
Showing 10 to 18 of 51

Amazon SageMaker AI now offers KV-aware routing for real-time endpoints, sending requests to instances that already hold matching cached prompt content.

MIT and Cornell researchers report a test-time adaptation method that helps AI text detectors resist disguised text and shifting writing styles.

Microsoft and partners announced the AI Transparency Initiative, an effort to set common security and governance standards for AI models and agents.

Meta has launched Muse, a personal AI agent, in Australia, with local connector experiences rolling out progressively.

At the SC26 conference in Chicago, NVIDIA introduced a four-node DGX Spark HPC Developer Kit aimed at researchers, academics and developers.

MIT News profiles Jacob Andreas, a newly tenured associate professor who develops AI models that can explain what they learned in training.

Apollo Research announced a four-month pilot in which six people from it will work inside OpenAI to assess model alignment.

The US Bureau of Industry and Security issued a rule on 16 November 2026 tightening exports of advanced semiconductors to five countries, including Singapore.

NVIDIA says CUDA Toolkit 13.4.2 adds Ozaki-II and 2M algorithms to cuBLAS that speed up double-precision matrix multiplication while keeping full FP64 accuracy.