Cloud & data centers
Every day we read hundreds of stories. Only the most important ones are here — short, in our own words, with a link to the original source.
- Artificial intelligence · Data & databases · Cloud & data centers
OpenAI explains how it scaled storage for ChatGPT
OpenAI describes scaling Habitat with multi-tenancy, global caching and Azure Cosmos DB. It reports 12× faster reads for ChatGPT.
Full story at openai.com ↗ - Cybersecurity · Cloud & data centers
Cloudflare launches post-quantum geo-fenced key manager
Cloudflare is launching the PQ GeoKey Manager in closed beta for its Data Localization Suite. It keeps decryption keys accessible only in the customer's chosen geography, with general availability planned for Q1 2027.
Full story at blog.cloudflare.com ↗ - Cloud & data centers · Data & databases · Artificial intelligence
OpenAI details scaling storage for ChatGPT's growth
OpenAI explains how it scaled its Habitat storage system using Azure Cosmos DB to serve over a billion ChatGPT users. The company says the changes deliver 12 times faster reads.
Full story at openai.com ↗ - Chips & hardware · Cloud & data centers
New Nvidia driver speeds up game launches
Nvidia released GPU driver 621.01, which uses Microsoft's new Advanced Shader Delivery tech to speed up game loading. The feature offloads heavy shader processing to the cloud, reducing CPU strain.
Full story at MobileSyrup ↗ - Cloud & data centers · Networking
Cloudflare improves handling of large-file range requests
Cloudflare rebuilt how its cache handles range requests, cutting wasted bandwidth and disk operations. For R2, this roughly halved p99 time to first byte and reduced tiered cache traffic.
Full story at blog.cloudflare.com ↗ - Cybersecurity · Cloud & data centers
Cloudflare launches post-quantum key manager
Cloudflare launched a post-quantum, geographically restricted key manager in closed beta as part of its Data Localization Suite. It ensures customer decryption keys stay accessible only within their chosen geography, with general availability planned for Q1 2027.
Full story at blog.cloudflare.com ↗ - Cloud & data centers · Artificial intelligence
DigitalOcean cuts AI prompt costs
Prompt caching is now generally available on DigitalOcean Serverless Inference. Cached input costs up to 90 percent less and time to first response drops by up to 80 percent.
Full story at digitalocean.com ↗ - Cloud & data centers · Programming & dev tools
Vercel adds more free domain options
Eight more top-level domains are now eligible for a free domain under Vercel's Pro plan. This gives developers more choice when naming their projects.
Full story at Vercel ↗ - Cloud & data centers · DevOps & containers
AWS lowers EMR on EKS pricing
Amazon is cutting the EMR charge for running on EKS by 30 percent, affecting both per-vCPU-hour and per-GB-hour fees. Apache Spark workloads on EKS automatically benefit from the lower cost with no action needed.
Full story at aws.amazon.com ↗ - Cloud & data centers · Networking
AWS previews last-mile link with Megaport
AWS launched a preview of AWS Interconnect - last mile with Megaport, letting customers connect branch offices and data centers to AWS easily. It uses Megaport's large software-defined network spanning thousands of data centers worldwide.
Full story at aws.amazon.com ↗
An AI writes the short texts from the source's stories.
Free by e-mail
Choose your topics. You only get the most important news on them.