How to build a single global queue for distributed systems on object storage: Start with a single file on object storage, then add write batching, a stateless broker, and high-availability.
Thanks for giving me a viable business model Amazon!
Various thoughts on programming and technology.
Back pressure for agents You might notice a pattern in the most successful applications of agents over the last year. Projects that are able to setup structure around the agent itself, to provide it with automated feedback on quality and correctness, have been able to push them to work on longer horizon tasks. This…
An attacker gained unauthorized access to environment variables for a subset of organizations. We've blocked the exploit and emailed all impacted account owners with steps to mitigate.
Backblaze's 2025 Year-End Drive Stats Report provides an in-depth analysis of hard drive failure rates for Q4, the full year, and lifetime performance across its data center fleet.
Learn how to run NanoClaw, a Claude-powered WhatsApp assistant, inside a Docker Sandboxes shell sandbox for stronger isolation and proxy-managed API keys.
a post from alan w. smith
We gave 64 real coding tasks to self-hosted GPUs, rented hardware and commercial APIs. Owning a box lands in the same cost ballpark as renting one.
Wiz Research discovered CodeBreach, a critical vulnerability that risked the AWS Console supply chain. Learn how to secure your AWS CodeBuild pipelines.
Proceed at your own risk! (... it's worth it)
A comprehensive deep dive into the gRPC protocol, from service definitions and streaming models to the low-level HTTP/2 framing and wire format.
A practical deep dive into Tailscale exit nodes: route changes, traceroute evidence, DERP fallback, trust boundaries, and why this model can be free.
Hetzner has launched an experimental LLM inference API. I tested its Qwen model—and have a few guesses about where the product could go next.
Solving the conflicting subnet problem with overlay addressing, WireGuard, and 1:1 NAT.
Code, Apps and Thoughts @lawrencegripper
Inference techniques either move a deployment along the latency–throughput frontier or push the entire frontier out, creating more efficiency to allocate.
My brother and I spent a lot of time designing our eBPF security agent to be really fast from the ground up, but recently we discovered we could make it much faster using memoization! A couple of weeks ago, I profiled the eBPF code and found that the most expensive part of the protection isn’t actually enforcing a…
Chevron Corporation (NYSE: CVX) today announced that Energy Forge One LLC, a wholly owned subsidiary, has signed an agreement with Microsoft Corp. (NASDAQ: MSFT) to develop a co-located power facility in West Texas that will provide dedicated electricity to a Microsoft-operated data center under a 20-year power…
Discover Snowflake Postgres Mirroring. Learn how push-based change data capture delivers transactional replication to your data lake with zero lag.
Firecracker needs KVM and therefore a Linux host, and the image tooling around it needs loop mounts and Linux userland. We rebuilt the stack on Apple's Virtualization.framework to boot the same OCI images as microVMs on macOS and on Linux.
Prototyping a Home NAS with RAID1 on FreeBSD on a virtual machine: system installation via SSH with bsdinstall, configuring ZFS mirror and working with datasets
A February 2026 campaign used a internal JSP path and in-memory Java class loaders to quietly seed persistent access across Ivanti EPMM deployments - then walked away. We break down the tradecraft.
Self hosting my media library with Jellyfin & Wireguard on Hetzner
In case you were wondering whether this would mean... writing zone files with some arcane syntax that BIND 9 is apparently famous of, I hereby present the main point of this post a recommendation for which DNS server to choose.
If you run a server with cPanel or WHM, you need to read this carefully. On May 8, 2026 — just ten days after the cPanel CVE-2026-41940 authentication bypass was used to compromise 44,000 web hosting servers and deploy ransomware — cPanel quietly released a second emergency security patch. This one covers three new…
NVL72 puts all 72 GPUs in a rack on one NVLink fabric, but only rack-local jobs get the speedup. How SkyPilot keeps multi-node training and inference on NVLink with topology-aware placement, in-place recovery from GPU failures, and automatic defragmentation.
I was reading Jason Gorman’s article “The Wall Confronting Reliable Coding Agent Autonomy” and he says: the journey from 90% to 99% reliability is just as hard…
