✍️ I just published "Best resources to learn about data and distributed systems" Happy learning 😊 #data #distributedsystem pierrezemb.fr/posts/distsys-…

Software Maker > Software Writer

There's nothing kind about letting good people live in a fantasy world that no longer exists. You have to tell them, even if it hurts. Because the sooner they accept reality, the sooner they can adapt to the future.

It's pencils down, people. Writing code by hand is no longer an economically viable skill for most programmers at most companies. But the future of making software has never been brighter. Don't you dare black pill this beautiful moment! piped.video/vDjW_dRyKXY?si=6Fsf…

As promised — #Ursa and #UFK (Ursa for #ApacheKafka) are now open source, under the lakestream project: openlakestream.org/ We believe streams are foundational to solving real-time context for #AI and #agents. And like tables, streams need a storage standard to solve the interoperability problem between vendors. That is why we open sourced it, and published the specification alongside the implementation. Both are public. We would love to work with the community — and with others across the Kafka, Pulsar, and streaming ecosystem — to build this together. Checkout the github repos: - Ursa: github.com/openlakestream/ur… - UFK: github.com/openlakestream/ka…

I'm sorry I had to make this meme Let me know if you agree 😅

I used Opus 5.5 to formally verify the Claude Agent SDK using Lean. A couple short prompts = 16 PRs fixing various bugs and race conditions. Video attached. TLA+ also works well. I sometimes combine Lean and TLA+ to look for issues around data flow, concurrency, and state mgmt. I don't know either language well, but Claude is excellent at both. This approach is super useful for formally modeling your code and finding bugs that a human probably wouldn't have spotted. Is formal verification the future of coding (or at least, bug finding)?

Introducing Claude Opus 5.5, the first model in our new Claude 5.5 family. It performs at the level of Claude Fable 5.1 for most tasks, and costs 40% less to run than Opus 5.

Please welcome GPT-6 Sol and GPT-6 Luna to the GPT-6 universe. GPT-6 Sol and Luna build on the advances behind GPT-6 Astra, bringing much of its strengths into faster and more affordable models to support work at scale. We’ve also made caching and inference more efficient, and we’re passing the savings directly to you: 50% lower API prices for Sol and Luna compared with GPT‑5.6 promotional pricing.

[𝗘𝗩𝗘𝗡𝗧] Deux jours, deux talks et l’équipe Clever à Clermont-Ferrand : direction @VolcampIO ! 🌋 @PierreZ & Alexandre Burgoni parleront d’ETCD et Kubernetes, @LostInBrittany d’architecture cloud. 📍 1 & 2/10 billetweb.fr/volcamp-2026 🧵👇 Thread

Jev introduces a new shape of LLM—System One, aka Decision Models simonwillison.net/2026/Sep/2…

Orphaned VMs: Running VMs Uninterrupted While Host Kernel Is Offline For Reboots/Updates phoronix.com/news/Orphaned-V…

GLM 5.3, hosted on Mistral, is now in Vibe Code, and the default in the web app. 1M context window and generous limits included. Happy 🛳️!

The architecture of Neki — PlanetScale planetscale.com/blog/the-arc…

FoundationDB is now powering all the major services in @tensorlake. 1. Our new sandbox orchestrator uses FoundationDB for storing the WAL for the cluster scheduler, route tables of sandboxes, watches for replicas which replays the WAL to in-memory indexes for fast responses to API calls. 2. Durable functions (which hasn't been released) uses FDB for storing the current execution graph of a request. 3. Versioned File System and SCM infra uses it for storing metadata of file systems and git repositories. We use the K8s operator, and it's been working pretty well.

Solving a Rubik's Cube with graph theory.

Great VLDB paper from the Azure Cosmos DB team. arxiv.org/abs/2608.09173 What caught my attention is how similar their approach is to what we’re building for the new TiKV auto-scaler: production data → learn → decide → simulate → deploy. It also makes me wonder: should PD scheduling and auto-scaling eventually share the same workload model? And apparently, better scheduling can be worth $100M+/year. 😂 Scheduling is money.

We're adding support for AGENTS.md to Claude Code. Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md. You can toggle this behavior in /config.

"Rust for infra and Go for web," nah. Don't even bother with Go. Just use Rust for everything.

8 parallel workers (and Chromium processes) with a simple interactive CLI dashboard, exploring TodoMVC. It's getting really interesting...

Any Nix package, live in your browser fzakaria.com/2026/09/04/any-…