The Datadog team introduced a new upsert query to track inactive hosts, but it unexpectedly increased disk writes and WAL syncs due to row locking. By digging into Postgres's Write-Ahead Logging (WAL) and rewriting the query using a Common Table Expression (CTE), they avoided unnecessary overhead an.. read more  

The compaction pipeline at Mixpanel ran into memory estimation issues causing OOMKills. By implementing AI-assisted analysis, they were able to reduce median estimation errorby 99%, leading to a significant improvement in memory estimation accuracy. Through thorough analysis and exploration of alter.. read more  

Zef's AST-walking interpreter posts a 16.6× speed-up. The gains come from surgical changes:64-bit tagged values,AST node & RMW specialization,symbol hash-consing,inline caches, and a shapedobject model. Developers built it onFil-C++and later ported it toYolo-C++. The Yolo build adds ~4x speed, at th.. read more  

Kubernetes v1.36 rolls out Memory QoS (alpha). Opt-inmemory reservation. Tiered protection by QoS class. Kubelet observability metrics. Kernel-version warnings. It separatesthrottlingfromreservation. A feature gate enables throttling. A kubelet config field controls tieredcgroup v2protection:Guarant.. read more  

Kubernetes v1.36 moves In-Place Pod-Level Resources Vertical Scaling to Beta and flips the feature gate on by default. Operators can patch a Pod's aggregate resource to resize running Pods. Often no container restart is needed. Kubelet breaks the Pod-level change into per-container resize events. It.. read more  

With the March 2026 retirement ofIngress NGINX, teams face an urgent compliance mandate. They must replace unpatched controllers. EnterHigress. Built onEnvoyandIstio. It unifies LLM protocols, enforces token rate limits, caches prompts, hostsMCP, and usesxDSfor zero-downtime. AnAI agentpaired withhi.. read more  

STCLab built an AI investigation pipeline withHolmesGPT, a 200-linePythonplaybook, andOpenTelemetry. It streamedMimir,Loki, andTempointo Slack threads. Metadata-driven markdownrunbookslimited tools per namespace, cut wasted tool calls from 16 to 2, and let the same model resolve alerts faster... read more  

Kubernetes v1.36 shipsclient-goatomicFIFOprocessing and cache-introspection APIs. Controllers detect stale informer state and skip acting on it. kube-controller-managerenables the capability by default for four high-contention pod controllers. It addsalpha metricsfor skipped syncs and informer resou.. read more  

Traditional software is predictable due to determinism, while generative AI is unpredictable. Engineers need a new infrastructure layer, the AI Evaluation Stack, to ship enterprise-ready AI products. The stack includes deterministic assertions and model-based assertions to ensure structural integrit.. read more  

Cloudflare wired AI into the engineering stack. LLM traffic funnels through aproxy WorkerandAI Gateway. It shippedWorkers AIand theAgents SDK. Daily users hit 3,683 (93% R&D). MR throughput climbed to ~10,952/week.Workers AIhandled 51B input tokens and cut a security agent's inference spend by 77%... read more