Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
If you don't run your own LLM proxy, how do you even know what's going on?
Jared Siegel argues that anyone using LLMs at home or at work should route traffic through their own proxy, so they can see prompts, responses, token spend and data paths instead of trusting a provider's black box.
2 min · 496 words
Evolving the cloud-native foundation for the next generation of AI
Microsoft Azure describes how it is advancing cloud-native infrastructure so organizations can build, run, and optimize applications and agents at scale for the next generation of AI workloads.
7 min · 1,552 words
Native Prometheus integration with NGINX
Categorica open-sources nginx-stats-prometheus, an MIT-licensed NGINX module that exposes Prometheus metrics directly from NGINX instead of running the separate NGINX Prometheus Exporter sidecar with its own web server, and explains the design and trade-offs.
5 min · 1,150 words
We fine-tuned a 235B model on four GPUs. Then we didn't need it.
Vertexcover's Savitha Suresh recounts fine-tuning Qwen3-235B-A22B-Thinking for document entity classification on four GPUs: Axolotl, Unsloth, FSDP+QLoRA and LlamaFactory setups failed before DeepSpeed ZeRO-3 with CPU offload worked, lifting F1 by 7.6 points, before newer open models made it unnecessary.
7 min · 1,541 words
Hyper Optimizing Kimi K3 in vLLM: Moving Fast and Responsibly
The vLLM team and NVIDIA describe using coding agents to build a unified CuTe DSL decode path for Kimi K3 on NVIDIA GB300, reaching over 840 tokens/s at batch 1 on 16 GPUs, and the guardrails (isolated changes, correctness tests, reproducible benchmarks) used to land agent-written kernels responsibly.
10 min · 2,277 words
Postgres DELETE Can Actually Scale
DBOS explains how Postgres actually deletes rows and how it made workflow retention deletes scale: batched deletes of the oldest workflows, dropping foreign keys so tables are cleaned in phases, debugging a 20-minute index lookup, and why it chose DELETE over dropping partitions.
7 min · 1,532 words
PwnEscape: Guest-to-Host KVM Escape (CVE-2026-99999)
pwn.ai's write-up of how Vercel's $1M Sandbox challenge led to a Linux networking bug where guest-controlled checksum metadata could rewrite an IPv4 header after validation, escalating from a 32-byte host-memory disclosure to a full guest-to-host KVM escape, with the upstream fix and patch timeline.
18 min · 4,202 words
Day 0 support for Muse Spark Open on vLLM
The vLLM team explains its day-0 support for Meta's Muse Spark Open, an 816B-total, 42B-active MoE model with 1M context and multimodal inputs: usage, model architecture details, DSpark speculative decoding, NVIDIA, AMD and initial TPU serving, and reinforcement learning support in vLLM.
7 min · 1,561 words
What changes when your search index lives on S3?
Infino explains how putting a full-text search index on object storage changes the cost and latency model: every random read is a billed GET taking tens of milliseconds, and how superfiles, manifests and careful layout keep agent queries fast without packing the working set on local disks.
9 min · 2,019 words
Forgejo announces version 17.0 of the community-driven Git forge, covering notable changes, upgrade notes and release artifacts for self-hosted teams that want an open alternative to proprietary code hosts.
8 min · 1,863 words
Yandex outage: Data shows that instead of going dark, malicious bots went on the move
Cloudflare uses Radar and Bot Management data to show that after reported strikes on Yandex data centers, the traffic drop from Yandex Search was mostly verified crawlers, while malicious automation on Yandex.Cloud largely migrated to other hosting providers, a reminder that ASN traffic volume is a poor proxy for bot behavior.
7 min · 1,622 words
Virtual Oxide Labs: Emulating a Full Oxide Rack
Oxide's Product Assurance team introduces Voxel, a tool that emulates a full Oxide rack, including its real control plane, switches, service processors and customer-like networking topologies, so the team can test current software without scarce hardware; it covers image creation, launch, SP emulation and the MPL 2.0 release.
18 min · 4,170 words
Geoff Huston examines the fragility of the ~1.5M km of subsea communications cables underpinning global telecoms — from Taiwan's Matsu Islands outages to repair capacity, sabotage risks and what resilience really requires.
16 min · 3,769 words
A slightly faster slimmer curl
Daniel Stenberg describes recent curl and libcurl work that trims binary size and improves performance: removing unused code paths, tighter defaults, and build-time options that make curl slightly faster and leaner without changing its familiar CLI behavior.
3 min · 707 words
Everyone is doing Git on S3 wrong
Enroute explains why Git is hard to put on object storage, where write-ahead-log designs fall short, and how its Rust, Raft and S3-backed Git server, built on modern database principles, reaches 7,600+ concurrent pushes per second on a single repository, with benchmarks and an open-source 0.3.0 release.
17 min · 3,860 words
How Cogent Runs Cloud Agents Securely
Cogent's engineering team describes how it runs cloud security agents assuming the sandbox may be compromised: trusted systems outside the sandbox control credentials, network and data access while still letting agents verify their work.
7 min · 1,553 words
Building a Linearizable Log on READ COMMITTED Isolation
Materialize describes how a metastable incident under PostgreSQL SERIALIZABLE led them to build a linearizable metadata log on READ COMMITTED isolation, achieving 3x write throughput, backed by a Lean 4 proof.
20 min · 4,657 words
Why I Started Moving Inference In-House
Nicholas Reese explains why he moved the AI behind USA Arms onto in-house hardware — three servers with four AMD Radeon AI PRO R9700 cards each — covering costs, the parts list, the build video, and a free build guide meant to hand to an AI.
9 min · 2,029 words
The Lix team’s seventh major release focuses on security, debugger support, quality-of-life fixes, and continued work toward Cap’n Proto RPC and Rust support in the Nix-compatible package manager.
8 min · 1,792 words
Announcing pg_vectorsearch: Scalable Open-Source Vector Search in PostgreSQL
Tiger Data launches pg_vectorsearch, an open-source PostgreSQL extension whose PRISM index uses partitioning and compression instead of HNSW graphs to deliver faster vector queries with far less memory and quicker index builds.
11 min · 2,613 words