Progressive autonomy with model evolution
Models often internalize capabilities previously enforced by agent scaffolding; the article recommends auditing and removing unnecessary prompts and orchestration as newer models arrive.
GPT realtime API for speech and audio
Azure OpenAI’s GPT Realtime API delivers low-latency, speech-in/speech-out conversational capabilities and can be used via WebRTC for client apps or WebSocket for server-to-server scenarios. This article covers supported models, authentication options, deployment steps in the Azure Artificial Intelligence Foundry portal, and example client code in JavaScript, Python, and TypeScript.
NVIDIA and Samsung build artificial intelligence factory for chip manufacturing
NVIDIA and Samsung announced plans to build a new artificial intelligence factory that integrates accelerated computing directly into advanced chip manufacturing. The project will be powered by more than 50,000 NVIDIA GPUs and aims to set a global benchmark for AI-driven semiconductor production.
NVIDIA and SK Group build Artificial Intelligence factory to drive Korea’s manufacturing and digital transformation
NVIDIA and SK Group are building an Artificial Intelligence factory in Korea that will include more than 50,000 NVIDIA GPUs, with a first phase due by late 2027. The facility will support SK subsidiaries and external organizations through a GPU-as-a-service model.