# sponsored-post-contributed Published articles for sponsored-post-contributed. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Why human oversight is shifting from writing code to defining requirements DevFeed: [Why human oversight is shifting from writing code to defining requirements]() Original publisher: [Read original article]() Author: Naseeb Ahmed Mian Published: 2026-09-17T13:00:00Z Content type: opinion Language: en Sources: [The New Stack]() Topics: [Requirements](), [AI Agent](), [Code](), [Availability]() Tags: [agent](), [agents](), [ai-agents](), [ai-engineering](), [andela](), [automated](), [availability](), [code](), [pipeline](), [post-contributed](), [requirements](), [review](), [software-development](), [sponsor-andela](), [sponsored-post-contributed](), [tests]() ### AI overview The article argues that human oversight of AI-assisted software development should focus on defining and reviewing requirements, not only checking whether generated code conforms to them. It illustrates the risk with a flawed availability-related requirement that passed specification review, generated six passing tests, traceability checks, and automated QA while violating the feature's intended outcome. ### Source excerpt This walks through the pipeline our agents operate inside--from a recorded scoping meeting through unit specs, spec review, generated code, The post Why human oversight is shifting from writing code to defining requirements appeared first on The New Stack. ## How to attach an owner to every cloud resource you find DevFeed: [How to attach an owner to every cloud resource you find]() Original publisher: [Read original article]() Author: Zeen Rachidi Published: 2026-09-15T14:00:00Z Content type: tutorial Language: en Sources: [The New Stack]() Topics: [Cloud](), [Provisioning](), [Open Policy Agent](), [audit trail]() Tags: [audit-trail](), [cloud](), [cloud-services](), [devops](), [env-zero](), [how-to](), [logs](), [open-policy-agent](), [platform-engineering](), [policy](), [post-contributed](), [provisioning](), [sponsor-env-zero](), [sponsored-post-contributed]() ### AI overview This tutorial explains how to identify cloud resources without assigned owners and prevent new ownerless resources. It presents continuously synced inventory queries, Open Policy Agent policies requiring owner tags, and logs or audit trails for resource governance. ### Source excerpt The engineer who knew why that cloud instance existed has left the company. The instance is still running, the bill The post How to attach an owner to every cloud resource you find appeared first on The New Stack. ## Kubernetes 1.36 restores a lost guarantee for database backups DevFeed: [Kubernetes 1.36 restores a lost guarantee for database backups]() Original publisher: [Read original article]() Author: Shubham Pampattiwar Published: 2026-09-15T13:00:00Z Content type: news Language: en Sources: [Kubernetes Overview, News and Trends | The New Stack](), [The New Stack]() Topics: [Kubernetes](), [PostgreSQL](), [Databases]() Tags: [backups](), [cncf](), [consistency](), [database](), [databases](), [kubernetes](), [post-contributed](), [postgresql](), [snapshots](), [sponsor-cncf](), [sponsored-post-contributed](), [stateful](), [storage]() ### AI overview The article explains how Kubernetes 1.36 restores coordinated snapshots for applications whose state spans multiple volumes, addressing inconsistent database backups caused by taking individual PersistentVolumeClaim snapshots at different times. ### Source excerpt It's 2 a.m., and you're restoring a PostgreSQL cluster from last night's backup. Its data directory lives on one PersistentVolumeClaim The post Kubernetes 1.36 restores a lost guarantee for database backups appeared first on The New Stack. ## Chip Huyen explains how to cut inference costs without new hardware DevFeed: [Chip Huyen explains how to cut inference costs without new hardware]() Original publisher: [Read original article]() Author: Tim Koopmans Published: 2026-09-13T15:00:00Z Content type: article Language: en Sources: [The New Stack]() Topics: [Inference Performance](), [Low-Latency Inference](), [model-deployment](), [Optimization](), [Frontier Model](), [AI Engineering](), [Latency](), [math]() Tags: [ai](), [ai-agents](), [ai-engineering](), [ai-infrastructure](), [frontier-model](), [inference](), [low-latency](), [metrics](), [optimization](), [performance](), [post-contributed](), [reasoning](), [scylladb](), [sponsor-scylladb](), [sponsored](), [sponsored-post-contributed](), [tokens]() ### AI overview Chip Huyen explains why inference costs can outweigh one-time frontier-model training costs and outlines ways to optimize inference without new hardware. The article emphasizes latency metrics such as time to first token, time per output token, end-to-end latency, and goodput, especially for reasoning models. ### Source excerpt Last October, the P99 conference -- the online gathering for developers focused on high-performance, low-latency applications -- featured a cracking The post Chip Huyen explains how to cut inference costs without new hardware appeared first on The New Stack. ## It passed CI. It passed your evals. The customer still got the wrong answer. DevFeed: [It passed CI. It passed your evals. The customer still got the wrong answer.]() Original publisher: [Read original article]() Author: Sean O'Dell Published: 2026-09-13T14:00:00Z Content type: article Language: en Sources: [The New Stack]() Topics: [AI Agent](), [agent observability](), [observability](), [tracing](), [dynatrace](), [ci](), [coding]() Tags: [ai](), [ai-agent](), [ai-agents](), [ai-engineering](), [ci](), [coding](), [dynatrace](), [observability](), [post-contributed](), [sponsor-dynatrace](), [sponsored](), [sponsored-post-contributed](), [traces]() ### AI overview The article explains how AI-agent failures can pass CI and evaluations while still producing slow or incorrect customer-facing results. It presents distributed traces and agent trajectories--model calls, tool calls, arguments, and results--as evidence for debugging retrieval behavior, release context, and feature-flag state. ### Source excerpt A diff is not evidence. It's a statement of intent. The tests passed. The review's done. The change is live. The post It passed CI. It passed your evals. The customer still got the wrong answer. appeared first on The New Stack. ## Why MCP security is about permissions overhaul DevFeed: [Why MCP security is about permissions overhaul]() Original publisher: [Read original article]() Author: Mohit Bansal Published: 2026-09-12T15:00:00Z Content type: article Language: en Sources: [The New Stack]() Topics: [Model Context Protocol](), [Authorization](), [GitHub](), [anthropic]() Tags: [ai-agent](), [ai-agents](), [github](), [mcp](), [model-context-protocol-mcp](), [post-contributed](), [security](), [sponsor-webflow](), [sponsored-post-contributed](), [webflow]() ### AI overview The article argues that MCP security problems are fundamentally permission problems, not merely infrastructure flaws. It calls for compartmentalized, task-scoped access to reduce risks such as prompt injection, tool poisoning, and excessive inherited trust. ### Source excerpt Anthropic's Model Context Protocol (MCP) went into production in late 2024. It spread rapidly after that. Since then, thousands of The post Why MCP security is about permissions overhaul appeared first on The New Stack. ## The AI-native SDLC won't be one process DevFeed: [The AI-native SDLC won't be one process]() Original publisher: [Read original article]() Author: Anirudh Ramanathan Published: 2026-09-12T14:00:00Z Content type: opinion Language: en Sources: [The New Stack]() Topics: [AI Bots]() Tags: [agents](), [ai](), [ai-engineering](), [anthropic](), [compliance](), [devops](), [dynatrace](), [github](), [kiro](), [platform-engineering](), [post-contributed](), [sdlc](), [signadot](), [spec-driven-development](), [sponsor-dynatrace](), [sponsor-signadot](), [sponsored](), [sponsored-post-contributed]() ### AI overview The article argues that AI-native software development needs risk- and accountability-based process variants rather than one fixed, spec-driven workflow. It emphasizes deterministic policy enforcement, agent self-checks, human approvals, and auditable records. ### Source excerpt Anthropic recently published its AI-Native SDLC Playbook. Its central claim is that "code is no longer the bottleneck." When agents The post The AI-native SDLC won't be one process appeared first on The New Stack. ## How AWS Lambda logs every flow across thousands of microVMs per host with eBPF and Rust DevFeed: [How AWS Lambda logs every flow across thousands of microVMs per host with eBPF and Rust]() Original publisher: [Read original article]() Author: Prashant Kumar Singh Published: 2026-09-11T12:00:00Z Content type: article Language: en Sources: [The New Stack]() Topics: [AWS Lambda](), [Architecture & Design](), [SIEM, Security, Observability](), [telemetry](), [Amazon EC2](), [Amazon S3](), [VPC]() Tags: [architecture](), [aws](), [aws-lambda](), [aws-marketplace](), [compliance](), [ebpf](), [firecracker](), [incident](), [incident-response](), [logs](), [monitoring](), [observability](), [post-contributed](), [rust](), [s3](), [scale](), [security](), [server](), [serverless](), [sponsor-aws-marketplace](), [sponsored-post-contributed](), [vpc]() ### AI overview AWS Lambda describes replacing an aging network-capture system with an eBPF and Rust pipeline that records network flows across short-lived, tenant-isolated microVMs. The system prioritizes complete, correctly attributed records with minimal overhead for security investigation, metering, audit, observability, and monitoring. ### Source excerpt On any compute platform, when a security alert fires, the question is always the same. Which workload talked to that The post How AWS Lambda logs every flow across thousands of microVMs per host with eBPF and Rust appeared first on The New Stack. ## Stop AI code sprawl before it destroys your software design DevFeed: [Stop AI code sprawl before it destroys your software design]() Original publisher: [Read original article]() Author: Emmanuel Akita Published: 2026-09-10T12:30:00Z Content type: opinion Language: en Sources: [The New Stack]() Topics: [AI-assisted coding](), [CI/CD](), [ci]() Tags: [ai](), [ai-coding](), [ai-engineering](), [andela](), [architecture](), [ci-cd](), [post-contributed](), [python](), [sponsor-andela](), [sponsored-post-contributed](), [testing]() ### AI overview The article argues that AI-generated code can create "Comprehension Debt" by silently violating architectural boundaries. It advocates enforcing architecture through automated tests and CI/CD pipelines rather than relying on documentation and manual review. ### Source excerpt While AI code generators help teams ship faster than ever, that speed brings a hidden killer: Comprehension Debt. As soon The post Stop AI code sprawl before it destroys your software design appeared first on The New Stack. ## Cut GPU inference cold start from 8 minutes to less than a minute DevFeed: [Cut GPU inference cold start from 8 minutes to less than a minute]() Original publisher: [Read original article]() Author: Sajjan Gundapuneedi Published: 2026-09-03T18:30:00Z Content type: article Language: en Sources: [Kubernetes Overview, News and Trends | The New Stack]() Topics: [GPU](), [Inference](), [model-deployment](), [Amazon Elastic Kubernetes Service](), [CUDA](), [Optimization](), [Amazon S3](), [Kubernetes]() Tags: [ai-infrastructure](), [amazon-eks](), [aws-marketplace](), [cpu](), [cuda](), [gpu](), [inference](), [kubernetes](), [large-language-models](), [optimization](), [post-contributed](), [s3](), [sponsor-aws-marketplace](), [sponsored-post-contributed]() ### AI overview The article measures GPU model startup from pod creation to the first inference response and identifies six sequential phases. It reports that CUDA kernel recompilation dominates startup for a 64 GB model, while S3 weight downloads dominate for a 203 GB model. Configuration and platform changes reduced warm-node startup times by 80-93%, with additional cold-node improvements requiring Amazon EKS Auto Mode. ### Source excerpt We instrumented the full path from pod creation to first inference response on a GPU node running a 70B-class model. The post Cut GPU inference cold start from 8 minutes to less than a minute appeared first on The New Stack. ## Pulling multi-gigabyte container images in seconds on Amazon EKS DevFeed: [Pulling multi-gigabyte container images in seconds on Amazon EKS]() Original publisher: [Read original article]() Author: Sri Saran Balaji Vellore Rajakumar Published: 2026-08-10T16:00:00Z Content type: article Language: en Sources: [Kubernetes Overview, News and Trends | The New Stack]() Topics: [Amazon Elastic Kubernetes Service](), [container images](), [Machine learning](), [autoscaling](), [CUDA]() Tags: [ai-infrastructure](), [amazon-eks](), [autoscaling](), [aws-marketplace](), [container](), [container-images](), [containers](), [cuda](), [kubernetes](), [machine-learning](), [post-contributed](), [sponsor-aws-marketplace](), [sponsored-post-contributed]() ### AI overview This article explains how a production ML platform on Amazon EKS reduced multi-minute pulls of roughly 30 GB container images to seconds. Profiling found that software use of available hardware, rather than network bandwidth or the registry, was the main constraint; the resulting changes are available by default in EKS Auto Mode and were contributed upstream to containerd and the SOCI snapshotter. ### Source excerpt When the image is the bottleneck: Machine learning changed what a container image looks like. A typical application ships in The post Pulling multi-gigabyte container images in seconds on Amazon EKS appeared first on The New Stack. ## Why your KubeVirt VMs can't move between clusters -- and how EVPN fixes it DevFeed: [Why your KubeVirt VMs can't move between clusters -- and how EVPN fixes it]() Original publisher: [Read original article]() Author: Miguel Duarte Barroso Published: 2026-08-08T14:00:00Z Content type: article Language: en Sources: [Kubernetes Overview, News and Trends | The New Stack]() Topics: [evpn](), [networking](), [BGP](), [configuration]() Tags: [bgp](), [cncf](), [configuration](), [evpn](), [kubernetes](), [kubernetes-networking](), [network](), [networking](), [platform-engineering](), [post-contributed](), [sponsor-cncf](), [sponsored-post-contributed]() ### AI overview The article explains why moving KubeVirt virtual machines between Kubernetes clusters requires a stretched Layer 2 network and a separate migration path. It presents EVPN/VXLAN, managed by OpenPERouter through Kubernetes custom resources, as an overlay-based approach intended to preserve VM IP and MAC addresses while separating migration traffic. ### Source excerpt Your team has moved VMs to Kubernetes with KubeVirt. The workloads are running. The team is gaining confidence. Then someone The post Why your KubeVirt VMs can't move between clusters -- and how EVPN fixes it appeared first on The New Stack. ## How Kubernetes 1.34's Dynamic Resource Allocation improves GPU scheduling DevFeed: [How Kubernetes 1.34's Dynamic Resource Allocation improves GPU scheduling]() Original publisher: [Read original article]() Author: Dawood Abbas Published: 2026-08-06T16:00:00Z Content type: article Language: en Sources: [Kubernetes Overview, News and Trends | The New Stack]() Topics: [Kubernetes v1.34](), [GPU]() Tags: [ai-infrastructure](), [andela](), [common-expression-language](), [gpu](), [helm-charts](), [kubernetes](), [nvidia](), [platform-engineering](), [post-contributed](), [sponsor-andela](), [sponsored-post-contributed]() ### AI overview The article explains how Kubernetes 1.34's Dynamic Resource Allocation changes GPU scheduling. It describes limitations of treating GPUs as identical resources, including out-of-memory errors, rigid MIG resource types, pending jobs, and wasted capacity, then presents DRA as a way for workloads to express more explicit GPU requirements. ### Source excerpt Consider a platform team managing a shared GPU cluster with a mix of B200s, H100s, and recently added B300s. Every The post Say goodbye to K8s GPU pain: How DRA changes everything appeared first on The New Stack. ## How EKS is simplifying Kubernetes cluster lifecycle management DevFeed: [How EKS is simplifying Kubernetes cluster lifecycle management]() Original publisher: [Read original article]() Author: Spyros Angelopoulos Published: 2026-08-01T15:00:00Z Content type: article Language: en Sources: [Kubernetes Overview, News and Trends | The New Stack]() Topics: [Amazon Elastic Kubernetes Service](), [Kubernetes](), [Availability](), [Deployment]() Tags: [availability](), [aws-marketplace](), [cloud-services](), [deployment](), [devops](), [kubernetes](), [lifecycle](), [post-contributed](), [sponsor-aws-marketplace](), [sponsored-post-contributed](), [upgrades]() ### AI overview The article describes the operational challenges of Kubernetes upgrades and EKS efforts to make cluster lifecycle management easier. It highlights Extended Support, which broadens the availability of each Kubernetes version to 26 months, giving organizations more time to validate and schedule upgrades. ### Source excerpt Kubernetes moves at a pace of three minor version releases per year, and staying current is not optional if you The post Kubernetes upgrades don't have to break things: How EKS is making cluster lifecycle management simpler and safer appeared first on The New Stack. ## Self-healing GPU nodes in Kubernetes: What we learned building the EKS node monitoring agent DevFeed: [Self-healing GPU nodes in Kubernetes: What we learned building the EKS node monitoring agent]() Original publisher: [Read original article]() Author: Sajjan Gundapuneedi Published: 2026-07-19T13:00:00Z Content type: article Language: en Sources: [Kubernetes Overview, News and Trends | The New Stack]() Topics: [Kubernetes](), [Amazon EKS](), [GPU](), [Monitoring]() Tags: [ai-infrastructure](), [amazon-eks](), [aws-marketplace](), [gpu](), [kubernetes](), [monitoring](), [open-source](), [pcie](), [post-contributed](), [self-healing](), [sponsor-aws-marketplace](), [sponsored-post-contributed]() ### AI overview The article describes how the EKS Node Monitoring Agent detects Kubernetes node failures, writes NodeConditions, and works with Karpenter to replace affected nodes. It explains design lessons from operating automatic repair at GPU scale and places the agent within EKS Auto Mode. ### Source excerpt When you run Kubernetes at the scale we do on Amazon EKS, nodes break constantly. GPUs fall off the PCIe The post Self-healing GPU nodes in Kubernetes: What we learned building the EKS node monitoring agent appeared first on The New Stack. ## From intent to enforcement: Lessons from operating Kubernetes controllers at scale DevFeed: [From intent to enforcement: Lessons from operating Kubernetes controllers at scale]() Original publisher: [Read original article]() Author: Sri Saran Balaji Vellore Rajakumar Published: 2026-07-17T12:00:00Z Content type: article Language: en Sources: [Kubernetes Overview, News and Trends | The New Stack]() Topics: [Kubernetes](), [Amazon Elastic Kubernetes Service](), [VPC]() Tags: [amazon-eks](), [aws-marketplace](), [clusters](), [controllers](), [declarative](), [kubernetes](), [networking](), [platform-engineering](), [policy-controller](), [post-contributed](), [reconciliation](), [scale](), [security](), [sponsor-aws-marketplace](), [sponsored-post-contributed](), [vpc]() ### AI overview This article explains lessons from operating Kubernetes controllers at scale in Amazon EKS. It focuses on how the Network Policy Controller and VPC Resource Controller reconcile declared intent with changing cluster state to enforce network traffic and AWS resource access policies. ### Source excerpt Kubernetes controllers are what make the platform's declarative model real. They observe the state, reconcile toward the intent, and keep The post From intent to enforcement: Lessons from operating Kubernetes controllers at scale appeared first on The New Stack. ## You don't have a deployment problem. You have a validation problem. DevFeed: [You don't have a deployment problem. You have a validation problem.]() Original publisher: [Read original article]() Author: Arjun Iyer Published: 2026-07-16T17:00:00Z Content type: opinion Language: en Sources: [Kubernetes Overview, News and Trends | The New Stack]() Topics: [Deployment](), [Microservice](), [Architecture & Design](), [feature flags]() Tags: [ai-agents](), [coding-agents](), [deployment](), [feature-flags](), [kubernetes](), [microservices](), [pipelines](), [platform-engineering](), [post-contributed](), [production](), [signadot](), [sponsor-signadot](), [sponsored-post-contributed](), [strategy]() ### AI overview The article argues that organizations often have mature deployment tooling but still release changes in batches because they lack confidence in validating individual service changes against the live versions of their dependencies. It presents validation, rather than deployment mechanics, as the main constraint on independent releases and says coding agents are increasing the volume and opacity of batch changes. ### Source excerpt Ask a platform team about their deployment capabilities, and you will usually hear a genuinely impressive story. Progressive rollouts that The post You don't have a deployment problem. You have a validation problem. appeared first on The New Stack. ## What running Kubernetes across millions of clusters taught AWS about zonal failures DevFeed: [What running Kubernetes across millions of clusters taught AWS about zonal failures]() Original publisher: [Read original article]() Author: Raghav Tripathi Published: 2026-07-10T15:00:00Z Content type: article Language: en Sources: [Kubernetes Overview, News and Trends | The New Stack]() Topics: [Amazon EKS](), [Kubernetes](), [Amazon Web Services](), [Resilience](), [Availability]() Tags: [amazon-eks](), [api](), [availability](), [aws](), [aws-marketplace](), [cloud-services](), [health-checks](), [kubectl](), [kubernetes](), [networking](), [operations](), [outage](), [post-contributed](), [resilience](), [sponsor-aws-marketplace](), [sponsored-post-contributed]() ### AI overview AWS describes how years of engineering on Amazon EKS addressed zonal failures, including gray failures where a zone is degraded but still passes some health checks. The approach emphasizes static stability, preserving capacity, and routing around the impaired Availability Zone. ### Source excerpt Handling the obvious failures is the easy part: a server goes down, you spin up another. The failures that actually The post What running Kubernetes across millions of clusters taught AWS about zonal failures appeared first on The New Stack. ## Operating Kubernetes at scale: a few stories from running Amazon EKS DevFeed: [Operating Kubernetes at scale: a few stories from running Amazon EKS]() Original publisher: [Read original article]() Author: Neelendra Bhandari Published: 2026-06-30T13:00:00Z Content type: article Language: en Sources: [Kubernetes Overview, News and Trends | The New Stack]() Topics: [Amazon EKS](), [Kubernetes](), [Availability](), [systems](), [Apache Spark](), [AI Platform]() Tags: [agentic-ai](), [ai-infrastructure](), [amazon-eks](), [apache-spark](), [availability](), [aws-marketplace](), [cloud-services](), [data](), [gpu](), [kubernetes](), [post-contributed](), [real-time](), [sponsor-aws-marketplace](), [sponsored-post-contributed](), [systems]() ### AI overview This article describes how operating Amazon EKS at very large scale shaped approaches to Kubernetes control-plane resilience. It argues that availability problems often arise when components amplify faults, and explains how changing workload patterns--including foundation-model training, real-time inference, Apache Spark analytics, and agentic AI--create extremely rapid state transitions that challenge traditional Kubernetes operating assumptions. ### Source excerpt Amazon EKS runs hundreds of thousands of Kubernetes clusters across more than thirty AWS regions. Operating at that scale has The post Operating Kubernetes at scale: a few stories from running Amazon EKS appeared first on The New Stack. ## Agentic Development Loops Shift the Unit of Work and Increase the Need for Verification DevFeed: [Agentic Development Loops Shift the Unit of Work and Increase the Need for Verification]() Original publisher: [Read original article]() Author: Arjun Iyer Published: 2026-06-13T16:00:00Z Content type: opinion Language: en Sources: [Kubernetes Overview, News and Trends | The New Stack]() Topics: [ai-coding](), [Development](), [coding](), [Kubernetes](), [Cloud]() Tags: [agentic-development](), [agents](), [ai](), [ai-coding](), [ai-engineering](), [cloud-native](), [coding](), [development](), [engineering](), [kubernetes](), [loops](), [platform-engineering](), [post-contributed](), [signadot](), [sponsor-signadot](), [sponsored-post-contributed](), [verification]() ### AI overview The article argues that agentic development is moving from prompt-driven and specification-driven workflows toward loops that generate, evaluate, and retry work. For cloud-native teams, this shift increases the importance of verification and the surrounding infrastructure needed to help agent-driven work converge on correct results. ### Source excerpt Something shifted in the AI coding discourse this month. The argument is no longer about whether agents can write production The post Loops are replacing prompts. Verification is about to be your biggest problem. appeared first on The New Stack. ## Cloud native application challenges: installing the walking skeleton DevFeed: [Cloud native application challenges: installing the walking skeleton]() Original publisher: [Read original article]() Author: Manning Book Authors Published: 2026-05-13T13:00:00Z Content type: tutorial Language: en Sources: [Kubernetes Overview, News and Trends | The New Stack]() Topics: [Kubernetes](), [YAML](), [Containers](), [Platform Engineering]() Tags: [applications](), [article](), [chronosphere](), [cloud-native-ecosystem](), [configuration](), [container](), [engineering](), [environment-variables](), [kubernetes](), [platform](), [platform-engineering](), [post-contributed](), [secrets](), [sponsor-chronosphere](), [sponsored-post-contributed](), [yaml]() ### AI overview This excerpt from Platform Engineering on Kubernetes explains how Kubernetes YAML defines and configures containerized applications. It introduces Deployments, Services, Ingress, and ConfigMaps or secrets, including their roles in replication, traffic routing, service discovery, and configuration management. ### Source excerpt Editor's note: This article is an excerpt from Chapter 1 of the Manning book, Platform Engineering on Kubernetes. This excerpt The post Cloud native application challenges: installing the walking skeleton appeared first on The New Stack. ## Why Prometheus couldn't see Cilium metrics at 2 a.m. DevFeed: [Why Prometheus couldn't see Cilium metrics at 2 a.m.]() Original publisher: [Read original article]() Author: Rishi Mondal Published: 2026-05-10T14:00:00Z Content type: article Language: en Sources: [Kubernetes Overview, News and Trends | The New Stack]() Topics: [Prometheus](), [Cilium](), [Grafana](), [Kubernetes](), [Cloud Native Ecosystem](), [Monitoring]() Tags: [cilium](), [cloud-native-ecosystem](), [cncf](), [grafana](), [kubernetes](), [monitoring](), [network](), [networking](), [platform-engineering](), [post-contributed](), [prometheus](), [sponsor-cncf](), [sponsored-post-contributed](), [tls]() ### AI overview This article examines the integration tax that platform teams encounter when combining CNCF projects in production. It uses Prometheus and Cilium metrics as an example, and discusses integration failures involving Hubble, Grafana, cert-manager, ingress controllers, and cloud DNS configuration. ### Source excerpt I still remember the first time we lost sleep over something that wasn't a bug. It was a Tuesday. Grafana The post Why Prometheus couldn't see Cilium metrics at 2 a.m. appeared first on The New Stack. ## Kubernetes User Namespaces Improve Pod Isolation but Do Not Isolate the Shared Kernel DevFeed: [Kubernetes User Namespaces Improve Pod Isolation but Do Not Isolate the Shared Kernel]() Original publisher: [Read original article]() Author: Kaylin Trychon Published: 2026-05-06T14:50:05Z Content type: opinion Language: en Sources: [Kubernetes Overview, News and Trends | The New Stack]() Topics: [Kubernetes](), [Security](), [Kernel](), [Cloud Native Ecosystem](), [Containers]() Tags: [cloud-native](), [cloud-native-ecosystem](), [containers](), [cves](), [edera](), [kubernetes](), [post-contributed](), [security](), [sponsor-edera](), [sponsored-post-contributed]() ### AI overview Kubernetes user namespaces can reduce the impact of some container escapes by remapping pod root identities to unprivileged host identities. The article argues that this improves isolation but does not address the security limitations of a shared kernel. ### Source excerpt Kubernetes shipped a long-awaited security feature last week: user namespace support for pods. It may sound like an obscure feature The post Kubernetes finally lands user namespace support, but shared kernel problem remains appeared first on The New Stack. ## NetEase Games reduced LLM model load time to 3 minutes with Fluid prefetching DevFeed: [NetEase Games reduced LLM model load time to 3 minutes with Fluid prefetching]() Original publisher: [Read original article]() Author: Haifeng Liao Published: 2026-05-06T13:00:00Z Content type: article Language: en Sources: [Kubernetes Overview, News and Trends | The New Stack]() Topics: [Large Language Model](), [AI Inference](), [AI Platform](), [autoscaling](), [Kubernetes](), [Cache](), [Serverless](), [GPU]() Tags: [ai-infrastructure](), [ai-platform](), [autoscaling](), [cache](), [cncf](), [gpu](), [inference](), [kubernetes](), [large-language-models](), [latency](), [llm](), [post-contributed](), [serverless](), [sponsor-cncf](), [sponsored-post-contributed]() ### AI overview NetEase Games describes how slow model loading limited serverless LLM inference across regions. Using an Alluxio-based cache and then Fluid's prefetching workflow, the representative model load time fell from 42 minutes to 3 minutes. ### Source excerpt At NetEase Games, we learned a hard lesson about large language model (LLM) inference in production: elastic compute is only The post How NetEase Games cut LLM cold starts from 42 minutes to 30 seconds appeared first on The New Stack.