Migrating to client-side load balancing at a million requests per second
Zalando Engineering describes their migration to client-side load balancing to handle over a million requests per second. The article details the technical challenges, architectural decisions, and benefits of shifting from traditional server-side load balancing to a more scalable client-side approach.
Background
Zalando, Europe's leading online fashion platform, engineers at massive scale — handling over a million requests per second across its microservice architecture. This post describes their migration from traditional server-side load balancing (where a dedicated load balancer like an AWS ALB or NLB distributes traffic across backend instances) to client-side load balancing (where each service client itself picks which backend instance to call, using a registry like Kubernetes endpoints or a service mesh data plane). The shift trades simpler operations for lower latency and better resource efficiency at very high throughput. The piece assumes familiarity with Kubernetes (container orchestration), Istio/Linkerd (service mesh), Envoy (a proxy commonly used in meshes), and gRPC (a high-performance RPC framework popular in microservices). It also touches on circuit breakers and retry budgets — mechanisms to prevent cascading failures when backends are slow or unavailable.
Max Weinbach says he had early access to OpenAI's new model GPT-5.6 Sol, calling it his favorite model by far. He highlights that it never gives up and will keep reasoning until it's done. OpenAI announced that GPT-5.6 Sol, along with Terra and Luna, will launch publicly on Thursday, with preview access expanding globally now.
The US government ordered Anthropic to suspend access to its Fable 5 and Mythos 5 models for all customers, citing a potential jailbreak technique that involved asking the model to review a codebase for vulnerabilities—a capability Anthropic says is available in other public models. Access was abruptly cut off on June 12.
Andrej Karpathy announces the release of Claude Fable 5, the same underlying model as Mythos but with added safeguards. He calls it a major step forward, particularly for long problem-solving sessions on difficult tasks, and describes it as state-of-the-art on nearly all benchmarks with exceptional performance in software engineering, research, and vision.
Roman Storm warns that the legal theory in his case could set a precedent making open-source developers liable for how others use their code, potentially criminalizing the mere publication of privacy, messaging, or crypto tools. He notes that developer Michael Lewellen cannot publish lawful code due to prosecution fears, and argues this chilling effect extends beyond any single case.
Meta's engineering culture is deteriorating under Mark Zuckerberg and Scale AI CEO Alexandr Wang, who have introduced keyboard tracking, reassignments to data labeling, and AI-centric performance metrics. Critics argue this incentivizes performative AI use, drives away experienced engineers, and contributed to a major Instagram hijacking incident caused by AI-written and AI-reviewed code.