🔥 Top Story
Announcing zone-aware routing in Amazon ECS Service Connect
In this post, we explain how zone-aware routing works and walk you through setting up a multi-AZ ECS cluster to see it in action.
🔗 Read more · AWS Containers
Kubernetes & Cloud Native
ARC zonal shift support for EKS Auto Mode and Karpenter
AWS Containers
In this post, we walk through how zonal shift integrates with Amazon Elastic Kubernetes Service (Amazon EKS) and what happens when a shift is triggered. We also show how to enable it on both self-managed Karpenter and EKS Auto Mode (EKS Auto) clusters.
Sustaining OpenTelemetry: What a 10-week contributor cohort actually looks like
CNCF
A follow-up to our earlier post: “Sustaining OpenTelemetry: Moving from Dependency Management to Stewardship” *** In April 2026, the Cloud Native Computing Foundation (CNCF), the OpenTelemetry (OTel) project, and Bloomberg’s Open Source Program Office came together.
When Kubeflow meets Cilium: Debugging 60% idle GPUs in Kubernetes
CNCF
The symptom that made no sense The first time we saw it, we didn’t trust the dashboard. A distributed training job was scheduled and healthy — every pod was running, no crashes, no OOMKills, nothing in.
The future of AI is community driven and open
CNCF
Kubernetes has become the de facto operating system for AI. In CNCF’s 2025 Annual Cloud Native Survey, 82% of container users now run Kubernetes in production, and 66% of organizations hosting generative AI use it to.
AI & ML
Launching Health in ChatGPT
OpenAI
Health in ChatGPT now lets eligible U.S.
Cloud Updates
Introducing Cache Response Rules
Cloudflare
Perhaps you’ve seen something that should sail out of cache get dragged back to the origin by a stray Set-Cookie or Cache-Control, headers that can be difficult to change on the origin itself. Cache Response Rules is the fix, applied at the right time.
Minimize idle accelerators: Native RL job interleaving with co-operative time-slicing in llm-d
Google Cloud
The math behind reinforcement learning (RL) post-training for large language models (LLMs) is notoriously unforgiving.
Your AI agents are ready. Is your data?
Google Cloud
What’s one of the biggest bottlenecks stopping organizations from scaling their AI initiatives? It isn’t the capabilities of today’s models — it’s their access to business context and semantic meaning.
The Blueprint: How Voicify makes AI-enabled ordering a delight for customers
Google Cloud
Welcome to The Blueprint, a new feature where we highlight how Google Cloud customers are tackling unique and common challenges across industries using the latest AI and cloud technologies. We hope to inspire others looking to innovate in their work.
Red Hat Government Symposium: Keeping the mission in motion by leading through change and delivering with impact
Red Hat
Agencies are keeping missions moving while technology, security requirements, data demands, and public expectations all continue to shift at once. That’s why this year’s Red Hat Government Symposium couldn’t have come at a better time.
5 new ways Red Hat helps partners maximize business value
Red Hat
At Red Hat, our goal for the ecosystem has always been simple: build a predictable, profitable partner program for our partners to scale their business. As always, we remain committed to the future of open source, and that means continuously investing in the partners who help us bring that future to life.
Why single AI agents fail at scale: Building governed multi-agent networks
Red Hat
A secured agent that can't reach anything is just expensive autocomplete with a badge. In "Why prompt-level guardrails aren't enough," I walked through how Red Hat AI allows you to give each agent a cryptographic identity and lock down what it can touch.
DevOps & Infrastructure
OpenAI and Anthropic both speak at once with dueling voice updates
The New Stack
OpenAI and Anthropic both rolled out major voice updates on Thursday afternoon, but the frontier AI labs seem to be
Nvidia’s new DNA model learns what token prediction misses
The New Stack
The AI industry has largely focused on language-based approaches, using transformers trained on massive datasets to predict words or fill
“We love the world where we can use both”: How Nvidia thinks about local and frontier models
The New Stack
The models small enough to run on the box on your desk are getting good enough that the interesting question
The case for a cooldown: Why Dependabot now waits before issuing version updates
GitHub
A new default three-day cooldown delays version update pull requests so maintainers and security researchers can address findings in a release before it gets into your code.
⚡ Quick News
- Bringing Nunchaku 4-bit Diffusion Inference to Diffusers — Hugging Face
This digest was automatically collected from RSS feeds. Excerpts are taken verbatim from each source — see the original links for full details.