Dev Systems - Building Systems That Scale

Show HN: Distributed, deterministically secure agentic swarm runtime. Enclawed

A Deterministic Security Runtime for LLM Agents on MPI and Batch-Scheduled HPC Systems: Consensus-Governed, Hardware-Rooted Supervision of Every Rank

Beyond API Compatibility: Building a Tool to Measure the Blast Radius of Library Changes

By Roberto Perez Alcolea, Java Platform TeamQuasar connects a proposed API change with observed references in consumer repositories, giving the producer evidence for a release decisionAt Netflix, shared Java libraries support applications developed a...

Single-tenant Titus: VM-level isolation on a multi-tenant container platform

Samartha Chandrashekar & Nick ParkerYou click play on a Friday night, and in the second that follows, dozens of services answer in milliseconds. Most of them run on Titus, our internal container platform. Titus is, in essence, a Kubernetes-based...

Single-tenant Titus: VM-level isolation on a multi-tenant container platform

Run iOS Live Activities reliably for very large audiences

Now available on Ably Pub/Sub, with push-to-start and Apple broadcast channel support. Live Activities let your users follow a game, a delivery, or a flight from their Lock Screen at a glance, without ever opening your app. But customers running Live...

Architecting for uncertainty - part 5: DevOps defines how a fast-flow organization works

This is the fifth in a series of articles based on my talk Architecting for Fast Flow: Thriving Amid Uncertainty.In this series, I define the term fast flow and explain why it has become an essential software delivery capability.I discuss how fast fl...

Show HN: Rouler – Steer Windows traffic per app or IP across multiple interfaces

Hi HN,Rouler is "rules for your routes". It allows you to steer network traffic across multiple network interfaces on Windows. For example:- Run Tailscale, Mullvad and OpenVPN official clients simultaneously.- Use Rouler to send Slack via t...

Show HN: Agent-Zero – Starter template for AI-native coding projects

Hi All,Agent-Zero is a GitHub template that you can use for new coding projects that use AI-first development workflows. It includes the minimum necessary to nudge agents to write good code, work well in sandboxes, and get stuff done on GitHub (e.g....

Automate medical coding with Step Functions and Amazon Bedrock AgentCore

With AI agents, you can automate medical coding while keeping the workflow deterministic, auditable, and subject to human approval. The key is division of labor: the workflow engine owns sequencing and approval gates, while agents reason within indiv...

Show HN: IDE for a general-purpose visual programming language "Pipe"

I'm happy to announce the release of the web-based Pipe IDE, availablle by clicking button "Try Pipe IDE" on website.Pipe IDE requires no account - all data is stored locally in your browser's database, keeping friction to a minim...

Architecture Decision Record: now in many more languages

I maintain the architecture decision record repository and today I'm launching many links for many languages:https://github.com/architecture-decision-record/architecture-decision-recordI get a lot of people requesting transla...

Backpressure in AI streaming: change how tokens move, keep each response one message

Backpressure in AI streaming can build anywhere from inference to the client, but delivery is where handling it can change the response itself. The three usual approaches there (buffering, batching, and rewriting a stored record) can change how the r...

What a room of engineers asked me about realtime resilience

I spoke about Ably's approach to resilience at the AWS Cloud Resilience Roadshow in Dublin on 22 September 2026, and the questions afterwards covered CDNs, regional failover, outages, message ordering, and capacity. They got me reflecting on which pa...

GenRecs Tokenization: Transforming Ads Recommendation at Meta with Stable Model Vocabulary

Generative Recommenders (GenRecs) represent a paradigm shift from scoring every ad to reasoning about ad content and user preferences together in order to predict the best outcome for advertisers. Leveraging the world knowledge built into LLMs makes...

The Thin Orchestrator: How We Made Our AI Agents More Reliable by Giving the Router Less to Do

Sometimes, giving an AI agent all of the knowledge it needs is the wrong approach. At Meta, we’ve seen notable improvements in efficiency and accuracy by keeping the orchestration layer of our data pipeline agents deliberately thin: It routes w...

Inside Prometheus: Meta’s Journey to a Gigawatt-Scale Supercluster

With the recent release of the Muse family of foundational models, we want to take you inside the infrastructure that has made it all possible.The first phase of Prometheus, our gigawatt-scale supercluster, is already complete and we’re working towar...

Show HN: Beeline Multiplayer Agent Harness

Shipped Beeline today. It's a team chat for humans and agents - a kind of multiplayer harness. You can bring your codex, Claude code, opencode subscriptions and also works with pi and goose. We built beeline itself with early versions of beelin...

Show HN: Gondwana, a code-first C#/.NET game engine with WebGL

Gondwana is a 2D/2.5D game engine for C#/.NET 8 that I’ve been building over the past 16 months, using SkiaSharp for rendering. I've spent my career creating web and distributed apps and that has influenced the engine's developmen...

Ontology-Driven Observability: Building an End-to-End Knowledge Graph at Netflix Scale

Prasanna Vijayanathan, Renzo Sanchez-SilvaWhen Jake Paul and Mike Tyson stepped into the ring in November 2024, we delivered the fight to roughly 65 million concurrent streams. On an ordinary day our infrastructure takes in more than 2 billion reques...

How are you centralising AI for development at your company?

I'm asking this because I'm seeing some frustrating patterns and if I may be bold, I think my answer is the correct one.Here's one I'm seeing: its the SDLC agent pattern and I think its wrong.Step 1: you have good AGENTS.md docume...